A composable framework for building reliable LLM agents on a harness you fully control. The same code runs the agentic loop on every model tier, local 4B to frontier with tool-call healing, verification, and durable crash-resume, on a typed 12-phase engine where every step emits an event you can hook into. Effect-TS, MCP-native, MIT
tylerjrbuell/reactive-agents-ts має індекс здоров’я 78 зі 100, що відповідає смузі «Добрий». Найвищий показник — Vitality (87/100), найнижчий — Sustainability & Governance (49/100). Останнє оновлення було 7 днів тому. Більшість нещодавньої роботи виконує один учасник.
78
загалом / 100
Добрий
Індекс здоров'я програмного забезпечення
Метрики згруповано у зважені категорії на шкалі 1–100. Загальна оцінка починається як їхнє зважене середнє, відкаліброване за розподілом публічного реєстру, тож діапазони мають перцентильний зміст; коли публічні дані активують Політику юрисдикцій високого ризику, рейтинг коригується й отримує верхню межу 34 («У зоні ризику»).
78
Винятковий93-100Верхній щабель реєстру (≈ топ-5%); відповідає практично всім перевіреним критеріям
Відмінний80-92Сильний за всіма напрямами; незначні прогалини
Добрий65-79Здоровий; прогалини обмежені та керовані
Помірний50-64Прийнятний, але з помітними прогалинами; рекомендовано перевірку
Слабкий35-49Суттєві недоліки в кількох сферах
У зоні ризику20-34Суттєві слабкі місця; впровадження потребує обережності
Критичний1-19Серйозні проблеми (покинутий, єдиний мейнтейнер, без базової гігієни)
Профіль оцінок
Кожна вісь — окрема категорія. Форма важить більше, ніж середнє: здоровий об'єкт заповнює всю фігуру, тоді як профіль із піками та провалами означає, що сила в одному вимірі маскує ризик в іншому.
Зважений загальний бал 67 калібровано до 78 за шкалою опублікованого індексу (калібрування реєстру 2026-08-02).
Прямі залежності без відомих сповіщень — жодна пряма залежність не має відомих сповіщень
14.4/25
Непрямі залежності без відомих сповіщень — уражено 1: @opentelemetry/core 2.6.0 (moderate 5.3)
40/40
Немає задавнених сповіщень — жодне сповіщення не є публічним довше за 90 дн.
Використані вхідні дані
source
osv
advisories
1
affected_packages
1
assessed_packages
233
unassessed_packages
0
affected_by_severity
moderate 1
direct_affected_packages
0
Звірено з runtime-замиканням залежностей npm:@reactive-agents/cli@0.14.0 — тим, що тягне за собою встановлення опублікованого пакета, — 233 пакетів. Досяжність не аналізується.
Наскільки репозиторій оснащений для розробки та супроводу за участі ШІ-агентів? Має свідомо малу вагу (4%): агентний інструментарій — реальний сигнал супроводу, але репозиторій без нього все одно може отримати 100/100.
Придатні до запуску приклади — cookbook, demos, examples
Використані вхідні дані
example_dirs
cookbook, demos, examples
has_mcp_signal
так
api_schema_files
—
Ключові факти
19зірок GitHub
2контриб'юторів
3 410комітів за останні 12 місяців
7днів від останнього пушу
35релізів
1бас-фактор
32відкритих issue
npmпакетних екосистем
Попередження щодо збору даних
Star history unavailable: GitHub GraphQL error: Resource not accessible by personal access token
GitHub dependency-graph SBOM unavailable (404); the dependency graph may be disabled for this repository
Докладніше
Історія зірок і форків 0 ★ / 4 ⇿
0Зірки
4Форки
17Релізи
Коли додано кожну зірку й форк — зібрано з GitHub і згруповано за днями. Кумулятивне зростання розміщено просто над денними додаваннями, з яких воно складається, тож їх видно одне проти одного: рівномірне органічне накопичення виглядає зовсім інакше, ніж різкий короткочасний сплеск. Там, де цю різницю можна виміряти, її подано як автентичність росту.
Мажорні 0Мінорні 6Патчі 11
OpenSSF Scorecard 4.6 / 10
4.6сукупно
Незалежна, не прив'язана до інструментів оцінка безпеки від відкритого проєкту OpenSSF Scorecard. Кожна перевірка винагороджує практику безпеки, а не інструмент конкретного постачальника. Перевірки, які Scorecard не зміг визначити, позначено н/д і виключено з оцінки безпеки (вони ніколи не зараховуються як нуль).Scorecard v5.5.0 · 2026-07-30 20:59 UTC
Не вдалося зібрати розв'язаний набір залежностей для цього звіту: GitHub dependency-graph SBOM unavailable (404); the dependency graph may be disabled for this repository
Сповіщення про залежності 1
Встановлення npm:@reactive-agents/cli@0.14.0 тягне 233 пакетів, прямих і транзитивних: 1 мають відомі сповіщення, з них 0 — прямі залежності.
Пакет
Версія
Зв'язок
Критичність
Сповіщень
Виправлено в
@opentelemetry/core
2.6.0
непряма
помірна
1
2.8.0
Сповіщення означає, що версія, записана в графі залежностей, потрапляє в уражений діапазон. Досяжність не аналізується, а граф містить піниї розробки й тестування — знахідка може стосуватися інструментів, а не поставленого коду.
Звіт у форматі JSON машиночитний
{
"data": {
"repo": {
"topics": [
"agent-framework",
"agent-observability",
"agent-orchestration",
"agentic-ai",
"anthropic",
"bun",
"composable",
"effect-ts",
"google-ai",
"llm",
"multi-agent",
"ollama",
"openai",
"type-safe",
"typescript",
"automation",
"ai-agents",
"gateway",
"mcp",
"streaming"
],
"is_fork": false,
"size_kb": 32391,
"has_wiki": false,
"homepage": "https://docs.reactiveagents.dev",
"languages": {
"CSS": 85033,
"MDX": 300190,
"HTML": 239882,
"Astro": 95564,
"Shell": 53153,
"Svelte": 725566,
"Dockerfile": 6554,
"JavaScript": 68067,
"TypeScript": 13890804
},
"pushed_at": "2026-07-22T22:06:34Z",
"created_at": "2026-02-19T14:01:27Z",
"owner_type": "User",
"updated_at": "2026-07-23T16:57:32Z",
"description": "A composable framework for building reliable LLM agents on a harness you fully control. The same code runs the agentic loop on every model tier, local 4B to frontier with tool-call healing, verification, and durable crash-resume, on a typed 12-phase engine where every step emits an event you can hook into. Effect-TS, MCP-native, MIT",
"is_archived": false,
"is_disabled": false,
"license_spdx": "MIT",
"default_branch": "main",
"license_spdx_raw": "MIT",
"primary_language": "TypeScript",
"significant_languages": [
"TypeScript"
]
},
"owner": {
"blog": null,
"name": "Tyler Buell",
"type": "User",
"login": "tylerjrbuell",
"company": "@luduscom",
"location": "Kalamazoo, MI",
"followers": 3,
"avatar_url": "https://avatars.githubusercontent.com/u/89788783?v=4",
"created_at": "2021-08-30T13:46:59Z",
"is_verified": null,
"public_repos": 12,
"account_age_days": 1795
},
"license": {
"state": "standard",
"spdx_id": "MIT",
"raw_spdx": "MIT",
"file_present": true,
"scorecard_found": true,
"profile_has_license": true
},
"activity": {
"releases": [
{
"tag": "v0.14.0",
"kind": "minor",
"published_at": "2026-07-22T00:47:00Z"
},
{
"tag": "v0.13.6",
"kind": "patch",
"published_at": "2026-07-06T12:58:07Z"
},
{
"tag": "v0.13.5",
"kind": "patch",
"published_at": "2026-07-06T02:11:25Z"
},
{
"tag": "v0.13.0",
"kind": "minor",
"published_at": "2026-07-02T04:13:11Z"
},
{
"tag": "v0.12.0",
"kind": "minor",
"published_at": "2026-06-17T02:41:00Z"
},
{
"tag": "v0.11.2",
"kind": "patch",
"published_at": "2026-06-11T00:10:54Z"
},
{
"tag": "v0.11.1",
"kind": "patch",
"published_at": "2026-05-17T14:44:09Z"
},
{
"tag": "v0.11.0",
"kind": "minor",
"published_at": "2026-05-17T03:31:03Z"
},
{
"tag": "v0.10.6",
"kind": "patch",
"published_at": "2026-05-06T01:23:56Z"
},
{
"tag": "v0.10.4",
"kind": "patch",
"published_at": "2026-05-06T00:17:27Z"
},
{
"tag": "v0.10.2",
"kind": "patch",
"published_at": "2026-05-05T03:31:10Z"
},
{
"tag": "v0.10.1",
"kind": "patch",
"published_at": "2026-05-05T03:07:49Z"
},
{
"tag": "v0.10.0",
"kind": "minor",
"published_at": "2026-05-05T02:44:29Z"
},
{
"tag": "v0.9.0",
"kind": "minor",
"published_at": "2026-03-29T03:01:32Z"
},
{
"tag": "v0.8.0",
"kind": "minor",
"published_at": "2026-03-15T23:06:36Z"
},
{
"tag": "v0.7.8",
"kind": "patch",
"published_at": "2026-03-12T14:59:15Z"
},
{
"tag": "v0.7.6",
"kind": "patch",
"published_at": "2026-03-12T14:14:40Z"
},
{
"tag": "v0.7.5",
"kind": "patch",
"published_at": "2026-03-12T02:39:33Z"
},
{
"tag": "v0.7.0",
"kind": "minor",
"published_at": "2026-03-10T18:42:13Z"
},
{
"tag": "v0.6.3",
"kind": "patch",
"published_at": "2026-03-05T16:06:54Z"
},
{
"tag": "v0.6.2",
"kind": "patch",
"published_at": "2026-03-05T15:13:47Z"
},
{
"tag": "v0.6.1",
"kind": "patch",
"published_at": "2026-03-05T14:13:56Z"
},
{
"tag": "v0.6.0",
"kind": "minor",
"published_at": "2026-03-05T04:05:26Z"
},
{
"tag": "v0.5.6",
"kind": "patch",
"published_at": "2026-03-05T00:33:56Z"
},
{
"tag": "v0.5.5",
"kind": "patch",
"published_at": "2026-03-05T00:33:55Z"
},
{
"tag": "v0.5.4",
"kind": "patch",
"published_at": "2026-03-05T00:38:48Z"
},
{
"tag": "v0.5.3",
"kind": "patch",
"published_at": "2026-03-05T00:33:53Z"
},
{
"tag": "v0.5.2",
"kind": "patch",
"published_at": "2026-03-05T00:33:52Z"
},
{
"tag": "v0.5.0",
"kind": "minor",
"published_at": "2026-03-05T00:33:51Z"
},
{
"tag": "v0.4.0",
"kind": "minor",
"published_at": "2026-03-05T00:33:50Z"
},
{
"tag": "v0.3.1",
"kind": "patch",
"published_at": "2026-03-05T00:33:49Z"
},
{
"tag": "v0.3.0",
"kind": "minor",
"published_at": "2026-03-05T00:33:48Z"
},
{
"tag": "v0.2.1",
"kind": "patch",
"published_at": "2026-03-05T00:33:47Z"
},
{
"tag": "v0.2.0",
"kind": "minor",
"published_at": "2026-03-05T00:33:46Z"
},
{
"tag": "v0.1.0",
"kind": "minor",
"published_at": "2026-03-05T00:33:45Z"
}
],
"recent_commits": [
{
"oid": "45cbacdb3acf81c05c706b2cefa5f732b1584175",
"body": null,
"is_bot": false,
"headline": "test(replay): return replayed steps through harness handle (#197)",
"author_name": "ZentropyLabs.ai",
"author_login": "HarperZ9",
"committed_at": "2026-07-22T22:06:34Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "cc051cf91b5d7ce5e57d2e83cedd2bfbdd816f9c",
"body": "…-arena pass\n\nThe workflow (Probe→Diagnose→Hypothesize→Fix→Verify→Commit) and the core\ncommands (rax:diagnose, weakness-queue, apps/cli bench, rax eval\ngate/ledger) are all still current. Fixed five concrete staleness/gap items\nfound while actually running the loop:\n\n- Phase 5 'rebuild every package\n[…]\ntructured file → parse error, trust=claimed-but-wrong).\n- Calibrated-model set corrected: gemma4:* is NOT in STATIC_CAPABILITIES\n (using it as an SUT yields 0 cells); listed the verified current set.",
"is_bot": false,
"headline": "docs(skill): update harness-improvement-loop from the 2026-07-22 eval…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-22T01:56:35Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "c3d2ad98f547fa20377c1d9f62a7bae3324b1c37",
"body": "…fence-unwrap fix)",
"is_bot": false,
"headline": "docs(agents): memory sync — eval-arena harness hardening (file-write …",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-22T01:48:07Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "1ce838abba5795bcf6ebca18923721b4344a971e",
"body": "…erables\n\nCross-tier probe (haiku, rw-1, 2026-07-22) surfaced a real production\ndefect: asked to write databases.json, the model wrote the JSON wrapped\nin a ```json … ``` fence (a near-universal LLM habit). file-write stored\nit verbatim, so the .json deliverable failed to parse ('Unrecognized\ntoken \n[…]\nl wrote.\n\nRed-on-cut: 6 cases (lone json/csv unwrap, preamble extract, clean-file\nuntouched, .md untouched, non-parseable-kept); cutting the normalizer\nflips the 3 unwrap cases red. tools suite 934/0.",
"is_bot": false,
"headline": "fix(tools): unwrap markdown fences when writing structured-data deliv…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-22T01:47:07Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "5e0dfdebf6ab94c826790e11c638133c5d3f440b",
"body": null,
"is_bot": false,
"headline": "docs: update badge version to v0.14 in Astro config",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-22T01:32:45Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "66dc6857a84e4099622123254e344ba5bd7735ee",
"body": "Verified each remaining 'deferred debt' item against code (the register's\nrecurring over-count problem — Nth instance):\n\n- success+empty-output edge: RESOLVED, not open. The completed⟹non-empty\n invariant is enforced at the SHARED boundary (sense/step-utils.ts:84\n forces empty→failed, HS-106/M7); \n[…]\nays honest at 2 and still catches new sites.\n\nNo code changed — the honest finding is these items are stale/closed or\nlow-value ceremony, so forcing them would add indirection or theater, not\nquality.",
"is_bot": false,
"headline": "docs(debt): register truth-pass on the deferred harness-hardening items",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-22T01:19:17Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "f947aa33a2e245471f93c8671142911baa6efb02",
"body": "…echeck-gap fix + lesson",
"is_bot": false,
"headline": "docs(agents): memory sync — v0.14.0 RELEASED (npm live) + release-typ…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-22T00:48:45Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "5f0ade4189fd67042a438d7f32d2e14d582d7cec",
"body": null,
"is_bot": true,
"headline": "chore(release): sync VERSION/CHANGELOG/changesets → 0.14.0 [skip ci]",
"author_name": "github-actions[bot]",
"author_login": "github-actions[bot]",
"committed_at": "2026-07-22T00:46:57Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "4cb2da3e78731e8e08bc23dcdce9e2ee9d42e025",
"body": "…ocker)\n\nThe v0.14.0 tag's publish workflow failed at its Typecheck step — the\nrelease runs strict per-package `tsc --noEmit` (`bun run typecheck`),\nwhich the PR CI never did (its Typecheck job runs only `bun run build`,\nthe lenient tsup DTS emit). So 5 type errors rode green through PR CI and\nfirst\n[…]\nd — same strict check the release gates on — so this class fails a PR\ninstead of a tag. Verified: fresh `turbo run build --force` then\n`turbo run typecheck --force` = 67/67 tasks green; suite 8,294/0.",
"is_bot": false,
"headline": "fix(ci): close strict-typecheck rot + gate it on every PR (release bl…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-22T00:34:54Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "947b32e61b4c66cb02d700d67a476492edd8634e",
"body": "… CI daemon)\n\nThe all-providers test built createAgent({ provider: 'ollama' }), whose\nbuild runs a live-server pre-flight (validateProviderConnection →\nlocalhost:11434, builder.ts:2325). CI has no Ollama daemon, so build()\nthrew 'Cannot connect to Ollama' and the test failed — it passed locally\nonly\n[…]\ne for a\n provider-union claim.\n\nRed-on-cut reverified: re-inlining the 6-member union fails both the\ndecode and build assertions. Suite 8,294/0 (net +1 from the split);\nmetrics cache + README synced.",
"is_bot": false,
"headline": "fix(ci): createAgent provider test must not build an Ollama agent (no…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-22T00:09:14Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "6d634d76d725de35c65089177039a50c4cf7b21d",
"body": "…staged, dry-run green)",
"is_bot": false,
"headline": "docs(agents): memory sync — v0.14.0 release prep complete (changeset …",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-21T23:52:14Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "41306cf6c8fc6933fd5deb78ffce695f129c1ca4",
"body": "…] notes\n\nrelease.ts always prepends a generated '## [<version>] — <date>' header and\naggregates .changeset/*.md bodies into it; with no changeset it writes\n'_No notable changes._'. The v0.14 notes were hand-curated under a\n'## [Unreleased]' heading, which the generator does not consume — so a tag\nt\n[…]\nprose) and drop the [Unreleased]\nsection from CHANGELOG.md. At tag time release.ts now renders a correct\n'## [0.14.0]' section and consumes the changeset. No hand-edited release\nnotes in CHANGELOG.md.",
"is_bot": false,
"headline": "chore(release): stage v0.14.0 changeset — migrate curated [Unreleased…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-21T23:49:08Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "fbb6808bc93b9ff1ab6884ad2d2488ad953dc49a",
"body": "…lmCalls, dead test acceptance keys)\n\nturbo run typecheck (not in the CI gate — CI typechecks via the tsup DTS\nbuild) surfaced 4 pre-existing errors, one in a SOURCE file:\n\n- ReActKernelResult was missing the llmCalls field that react-kernel.ts:271\n actually emits (state.llmCalls ?? 0) and plan-exe\n[…]\nableSpec field\n removed in the Wave 3 delete pass — dropped the 3 dead keys (the live\n RequirementSpec.acceptance on spec:{} is untouched).\n\nFull workspace typecheck now 0 errors; build 37/37 green.",
"is_bot": false,
"headline": "fix(reasoning): close pre-existing typecheck rot (ReActKernelResult.l…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-21T23:47:46Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "1c52477ede1ef5495c7a4b03f6e6b179454fdb59",
"body": "…work superseded\n\nPrune pass verified index claims against code:\n- _enableMemory line ref 113→147, withLeanHarness 227→1355 (facts true,\n line numbers drifted) — fixed in the personal index.\n- Current Status header refreshed 0.13.6/226-ahead/OVERDUE → v0.14\n release-ready + pushed.\n- The 2026-07-1\n[…]\nen closed work; kept the 226-commit process analysis + doctrine.\nConfirmed still-true (no change): kernel capabilities/loop layout,\nwithOutputSchema/streamObject/withApprovalPolicy live, 8 strategies.",
"is_bot": false,
"headline": "docs(agents): prune-memory — mark 2026-07-12 state-of-framework open-…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-21T23:13:02Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "e3ff2e8a797e5ecfa0e931daac9a179ab28ed375",
"body": "…ixes + doc/scaffolder repair)",
"is_bot": false,
"headline": "docs(agents): memory sync — v0.14 first-timer quality sweep (4 code f…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-21T22:25:45Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d88ec81fe1b0f4c617fd17bbb9bb037426b7ddf3",
"body": "…uality-sweep tests",
"is_bot": false,
"headline": "chore(metrics): refresh snapshot to 8,293 tests / 1,061 files after q…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-21T22:24:37Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "a132a7aaae1bb93128e1373b5380f1f2447d892f",
"body": "… v0.14\n\nAudit of bunx create-reactive-agent + rax init/create found the emitted\nprojects broken in ways a first-time user hits immediately. Fixed and\nverified (4 templates generated + typechecked against v0.14 worktree types):\n\n- BLOCKER: version pin ^0.11.0 resolved to 0.11.2, which lacks\n withOu\n[…]\nproject-local path' claim contradicted runtime-construction.ts:449).\n\nScaffolder + cli suites green (140 pass); minimal/streaming/\nstructured-output/with-memory scaffolds typecheck clean against 0.14.",
"is_bot": false,
"headline": "fix(scaffold): first-touch scaffolder templates current + correct for…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-21T22:21:46Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "5ad31ba78bb7a70a8a4c2865d8a8d283e7dbf592",
"body": "…ath, funnel order\n\n14-finding onboarding audit applied to the Get Started trail (all\nverified against code):\n\n- BLOCKER: quickstart's first command 'bunx rax init' resolves to\n Alibaba's unrelated rax package in a fresh directory — now\n 'bunx reactive-agents init' (our package ships both bin alia\n[…]\nachine, all\n opt-outs incl. the new DO_NOT_TRACK / REACTIVE_AGENTS_TELEMETRY env\n switches) + sidebar entry.\n\ndocs:examples:check 355/0; SKIP_CEILING ratcheted 250 → 249 (one more\nblock un-skipped).",
"is_bot": false,
"headline": "docs: first-timer onboarding fixes — broken first command, zero-key p…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-21T18:26:25Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "3fc986a813a7747fec04d5d0ef9e503a31398213",
"body": "…, counts reconciled\n\n15-finding first-time-user audit applied (all verified against code):\n\n- API-key setup now sits directly above the first runnable example (was\n 750 lines later, unlinked) + Environment Variables table completed for\n all 8 providers (GROQ/XAI/LITELLM/OLLAMA vars were undocumen\n[…]\n- Three jargon-wall bullets rewritten outcome-first (entropy sensor,\n adaptive harness — still clearly experimental/opt-in, evidence ledger).\n\nGates: docs:examples:check 352/0; metrics:check in sync.",
"is_bot": false,
"headline": "docs(readme): first-timer audit fixes — key setup, complete env table…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-21T18:25:37Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "464e1e74425027b1b419cec2824569507868b577",
"body": "… env opt-out\n\nRI telemetry could only be disabled in code\n(.withReactiveIntelligence({ telemetry: false })). Industry convention\nand CI environments expect an environment-level kill switch:\n\n- telemetryOptedOut(): DO_NOT_TRACK set-and-not-'0' (console DNT\n convention) or REACTIVE_AGENTS_TELEMETRY=\n[…]\nes (first-run notice + report emit), so the notice never\n claims telemetry the environment has killed.\n- Red-on-cut suite: opted-out sends make zero sink attempts; control pins\n the default-on path.",
"is_bot": false,
"headline": "feat(reactive-intelligence): DO_NOT_TRACK / REACTIVE_AGENTS_TELEMETRY…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-21T18:25:27Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "564fce3e3a8cc76a3318520f20242c3ca23a599e",
"body": "A first run with no API key surfaced the raw SDK text ('Could not resolve\nauthentication method. Expected either apiKey or authToken to be set.')\n— which never names ANTHROPIC_API_KEY, leaving a new user to search for\nthe variable. mapProviderError now maps 401/403/credential-phrased\nfailures to one\n[…]\nlus the provider's\noriginal reason. Keyless providers (ollama) and bring-your-own-layer\nproviders never get an invented env var. Auth errors stay permanent\n(never retried). TDD: 5 new cases red first.",
"is_bot": false,
"headline": "fix(llm-provider): credential failures name the env var to set",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-21T18:25:27Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "86bf665444cf6b8136a5a3c886b75edc40f925d1",
"body": "…n from the canonical source\n\nThe declarative front door (the README quickstart API) rejected two of the\neight shipped providers: agent-config.ts carried a stale 6-member inline\ncopy of the provider union, so createAgent({ provider: 'groq' }) failed\nschema decode while the fluent builder accepted it\n[…]\ns, collapses union mismatches to one\n expected-one-of line, and links the public docs reference instead of a\n repo-relative path.\n- Generated config-field-reference block regenerated (provider row).",
"is_bot": false,
"headline": "fix(runtime): createAgent accepts groq/xai — derive the provider unio…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-21T18:25:15Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "2dc278020efb282703dcdd830d4f1258a534bcda",
"body": ".agents/MEMORY.md: doc-sync entry (all surfaces truthful for 0.14; verified\nfact sheet + 3 parallel writers; orchestration dir = untracked build residue;\nadapter hooks = 4 live + parseToolCalls). Personal Claude memory index\ncompacted 20.5KB→16.8KB in parallel (burndown detail collapsed to a pointer;\ntopic file holds the waves).",
"is_bot": false,
"headline": "docs(agents): memory sync — v0.14 full doc sync complete",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-21T17:34:35Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "6379e94a3d14274648681f68aeaab8925bf30a50",
"body": "Full doc sweep for the v0.14 release across every user-facing surface,\nevery claim verified against code (three parallel sweeps + spot checks).\n\nwhats-new.mdx: new v0.14 section — trust receipt (result.receipt),\nprocess model (inspect/fork/rax ps/attach), enforcement-caught-up-to-docs\n(tool policy o\n[…]\n to v0.14 release-ready state.\n\nVerified: docs:examples:check 352/0, metrics:check in sync. No published\nbenchmark numbers introduced; opt-in harness flags kept out of the\nrecommended/default framing.",
"is_bot": false,
"headline": "docs: sync all documentation to v0.14.0",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-21T17:32:15Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "8158c757d33564340d4bbb53d52e628c5112d751",
"body": "…ischarged, P0-21 drift-skips gone\n\n- P0-4/B1: code-action residual CLOSED (d22e784f) — sandbox handlers gate\n through the shared evaluateToolPolicy; red-on-cut.\n- P0-21: all 6 drift-hiding skips discharged; SKIP_CEILING 283→250;\n corrected the register's own over-count (session persist/id are real +\n test-pinned; the true rot was context key / table name / end()\n semantics / dead persistOnEnd).\n- .agents/MEMORY.md: release-readiness entry (gates green, owner-gated\n tag remains).",
"is_bot": false,
"headline": "docs(debt): register + memory — release-readiness sweep; P0-4 fully d…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-21T17:06:43Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "11c1e99980402cd709524eb0ad89706595525ca4",
"body": "…ate.test.ts, solution.ts)\n\nLive bench agents wrote deliverables to the worktree root during the\n2026-07-21 cross-tier campaign; a git add -A swept them into the metrics\ncommit. Neither is repo code.",
"is_bot": false,
"headline": "chore: remove stray bench-run artifacts committed by accident (parseD…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-21T17:04:50Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "6c5c2530b8543f392b85f6594cc4b73a2dd0458c",
"body": "…grand-total sync pattern\n\nThe metrics cache still pinned the 2026-07-19 count (8,253/1045); the\nresilience fixes, policy-gate suite, and doc-example un-skips moved it to\n8,276 tests across 1,060 files (0 fail). Also removed the sync script's\n'grand-total header' pattern — its README target line was deleted in the\nWave 1 claims takedown, so it warned on every run against nothing.",
"is_bot": false,
"headline": "chore(metrics): refresh test snapshot to 8,276/1060 + drop the stale …",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-21T17:04:32Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "ae5825cf67ec45628e46e7816abb79803ce374ea",
"body": "…lBuilder flow\n\nRegister P0-21's six drift-hiding skips, discharged with the docs now\nmatching verified code (positive scratch snippets compile under strict\ntsc; negative reproductions confirmed each fabrication before the fix):\n\n- agent.session(): the register's own claim ('persist/id fabricated') \n[…]\nied at\n registration; defineTool for typed handlers).\n\ndocs:examples:check: 348 blocks, 0 failed; 6 previously-skipped broken\nblocks now compile and are un-skipped — SKIP_CEILING ratcheted 256 → 250.",
"is_bot": false,
"headline": "docs: fix fabricated API options — session(), withContextProfile, Too…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-21T17:00:21Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "848f5aed9a12f7fc62514d10235228f781d0de51",
"body": "26 verified live-drift sites across 13 files still taught APIs removed in\nv0.14 (register P0-21 residue). A visitor following these docs on day one\nof the release would hit compile errors or silently-missing tools.\n\n- .withTelemetry / .withoutTracing → folded into .withObservability\n ({ telemetry, \n[…]\neractionManager); runs green (exit 0);\n interaction READMEs updated to match.\n\nVerification: docs:examples:check 342/342 blocks typecheck; zero\nremaining live-drift mentions across all touched files.",
"is_bot": false,
"headline": "docs: purge drift — remove v0.14-removed APIs from live documentation",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-21T16:50:57Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "c19d20ebe4d3cdba05ebae5842b569b561cfdec6",
"body": "…fix + policy-gate test files",
"is_bot": false,
"headline": "fix(ci): re-sync README test-file count (1057→1060) after resilience-…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-21T16:47:09Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "f870e5394ce64152bd6dd1f3404dc854491b7409",
"body": "…enforcement, run integrity\n\nThe Wave-1 rewrite predated the spine (Wave 2), the delete wave (Wave 3),\nand the resilience fixes; the section was missing three breaking removals\n(orchestration + scenarios packages, .withCacheTimeout) and every\nuser-visible behavior change since (tool-policy enforceme\n[…]\nhase stream events, requirement lifecycle, kernel-path memory extraction,\ntransient-error retry, critique graceful degrade). A v0.14 cut without\nthese entries would ship breaking changes undocumented.",
"is_bot": false,
"headline": "docs(changelog): cover Waves 2-5 in [Unreleased] — package removals, …",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-21T16:45:53Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "d22e784fa4e23ac112930189b503b7a313bb9397",
"body": "…P0-4 residual)\n\ncode-action executes tools inside the sandbox Worker via bridged handler\nclosures, not through the kernel act phase — so the Wave 2 B1 boundary\n(evaluateToolPolicy inside executeToolAndObserve) never covered it. The\nclosures called toolSvc.execute() with zero policy checks: LLM-gene\n[…]\nen, contract-seeded, whitelist); controls pin unchanged\n behavior with no policy.\n- Fixed the stale plan-execute.ts header comment still describing the\n pre-B1 direct toolService.execute() dispatch.",
"is_bot": false,
"headline": "fix(reasoning): enforce tool policy on code-action sandbox handlers (…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-21T16:43:42Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "2099aa077987cd9562e9a857a2fb8267b51a9d8d",
"body": "…ce fixes",
"is_bot": false,
"headline": "docs(agents): memory sync — cross-tier diagnosis + 2 harness resilien…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-21T13:50:31Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "0a26b21266990585de158e8ae2dc885272c9ce56",
"body": "Root cause (Wave 5 cross-tier diagnosis): mapProviderError routed status 429 to\nLLMRateLimitError (which retry.ts retries) but let EVERY other failure —\nincluding 5xx, Anthropic/Groq 529 overloaded, and network faults (ECONNRESET,\nsocket hang up, fetch failed) — fall through to the catch-all LLMErro\n[…]\nest.ts asserts 5xx/529/network → retryable\nand 4xx → not (red before, green after). Updated the JSON-dedup test to use 400\n(the 5xx it used is now transient). Build green; 382 llm-provider tests pass.",
"is_bot": false,
"headline": "fix(llm-provider): retry transient 5xx/529/network errors, not just 429",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-21T13:47:31Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "761115898ef450ba33bb604fcfd58c0bb6759174",
"body": "…ing the run\n\nRoot cause (Wave 5 cross-tier diagnosis): runCritiquePass mapped ANY LLM error\nto a strategy-attributed ExecutionError that propagated fatally, so a single\ntransient provider blip (429 / 5xx overload / timeout) during the critique pass\nzeroed a reflexion or plan-execute run that had AL\n[…]\nicitly left\nuntested — 'defer to integration') asserting the Effect RESOLVES with a degraded\nresult rather than rejecting. Red before, green after. Build green; 871\nstrategy+verify tests pass, 0 fail.",
"is_bot": false,
"headline": "fix(reasoning): critique pass degrades on LLM failure instead of kill…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-21T13:41:54Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "a8e51043faa890c45c7258bc9d59801ba0429fcf",
"body": null,
"is_bot": false,
"headline": "docs(agents): memory sync — Wave 5 entry gate (bench P2) conversion done",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-21T00:50:34Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "917bdef023aed5196381beef6de88d75f67c995d",
"body": "…d, re-baseline owed",
"is_bot": false,
"headline": "docs(debt): register — Wave 5 P2 conversion done, sd framing correcte…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-21T00:49:38Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "86a8ef9a3b0b1833e9ca5f027362f0fd03906cc0",
"body": "The 2026-07-10 plan's '7 llm-judge tasks' was already down to 2 (rw-1..rw-9 were\nconverted in the 2026-07-11 keyword->graded wave). This finishes the entry gate:\n\n- rw-5 (zero-downtime migration): converted llm-judge -> deterministic\n partial-credit 'verifiable'. The prompt now pins the deliverable\n[…]\n passThreshold; no solvedThreshold (a judge verdict is deliberately never a\n pass^k solve).\n\n1 llm-judge success criterion remains (rw-10, graded, by design). Build green;\n398 benchmarks tests pass.",
"is_bot": false,
"headline": "test(bench): Wave 5 P2 — deterministic-grade the last 2 llm-judge tasks",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-21T00:48:58Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "96edce39428e784a0ee0cb0db40f7c02bde7aef9",
"body": null,
"is_bot": false,
"headline": "docs(agents): memory sync — Wave 4 complete (derive-from-impl gates)",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-20T22:12:20Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "c0935f61fccdeecb994d1ea04a219ee895c65398",
"body": null,
"is_bot": false,
"headline": "docs(debt): register — Wave 4 derive-from-impl gates shipped",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-20T22:11:25Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "3702fb853164ac927e07940c10ffbe40fa6e88c0",
"body": "…nds (Wave 4)\n\nThe derived LedgerEntryKind kills kind<->interface drift at compile time. This\nguard catches the residue types cannot: a kind interface that EXISTS but that\nnothing ever appends — an always-empty projection that reads as a silent lie.\n\nEvery declared ledger kind must have >=1 non-test\n[…]\ns at a throwaway tree: green on the real tree,\nred when a fixture kind loses its writer, red when a baselined kind gains one.\n\nenforcement-scripts.test.ts 10 pass; the guard is green on the real tree.",
"is_bot": false,
"headline": "feat(gate): check-orphans.sh — declaration-orphan guard for ledger ki…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-20T22:09:48Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "59861c8da70db942a14adaee45fcdfbb2806a299",
"body": "LedgerEntryKind was a hand-maintained union of 9 string literals kept in sync\nby hand with the LedgerEntry interface union — the exact drift class Wave 4\nretires. Derive it: 'type LedgerEntryKind = LedgerEntry[\"kind\"]'. A kind\nliteral no entry interface declares is now impossible, and a new entry\nin\n[…]\ndant 'kind'\nfield from LedgerEntryBase so the derivation is non-circular (every concrete\nentry already declares its own literal kind).\n\nBuild green (DTS typecheck authoritative); 45 ledger tests pass.",
"is_bot": false,
"headline": "refactor(ledger): derive LedgerEntryKind from the entry union (Wave 4)",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-20T22:05:06Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "12a11d95c467d3ba3447986c6be0fcaeb962b393",
"body": null,
"is_bot": false,
"headline": "docs(agents): memory sync — Wave 3 COMPLETE (remainder shipped)",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-20T21:57:44Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "e9595f7260f5e012218983afee7eff065cd291d2",
"body": null,
"is_bot": false,
"headline": "docs(debt): register — Wave 3 remainder ratchet note (withers 85->84)",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-20T21:56:01Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "044a9eab28a1c9afdc2e2f4d719fa3677167adf4",
"body": "…(T3.10)\n\nBoth were public exports of @reactive-agents/tools but NEVER registered as\ncallable in production — the live meta-tool registration in\ntool-capabilities.ts wires recall/writeResultToFile/find/checkpoint/\ndiscover-tools/brief/pulse/todo, not these. Only tests referenced them.\n\n- task-comple\n[…]\nument-retrieval FEATURE (.withDocuments()/ingest()) is unchanged and\nlive via find. Build 20/20; all 8 architectural-invariant scripts + capability\nmanifest green; 931 tool+runtime tests pass, 0 fail.",
"is_bot": false,
"headline": "fix(debt): Wave 3 §3b — delete dead task-complete + rag-search tools …",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-20T21:54:21Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "6c7f780bd9dca3875e7cfbc53507eb3b0728ca6d",
"body": "…ot definitions\n\nThe control-plane grandfather list had 4 entries, but 'Which control action\nfires this iteration' has only 2 real un-reconciled forcing sites. Two entries —\nstrategy-switch.ts and force-abstention.ts — were only on the list because the\nprimitive regex applyStrategySwitch\\( / decideF\n[…]\nesolveControlPlane is behavioral kernel work with a red-on-cut\ntest — the genuine one-per-PR ratchet, deferred to a dedicated kernel PR.\n\nGuard still green (exit 0); no test pins the grandfather list.",
"is_bot": false,
"headline": "fix(debt): Wave 3 §3b — tighten check-control-plane guard to calls, n…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-20T21:47:36Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "a1c6361cc2f57e0ba9ed778ac594308ef0be4a76",
"body": "…ve 1 landmine)\n\nWave 1 (P0-10) removed withProgressCheckpoint() from the builder and pinned its\nabsence, but missed the cortex consumer — build-cortex-agent.ts still called\nb.withProgressCheckpoint(params.progressCheckpoint), which throws\n'b.withProgressCheckpoint is not a function' at runtime when\n[…]\nnd 3 cortex tests. checkpointEvery/withDurableRuns (a separate,\nlive feature) untouched.\n\nCortex 'tsc --noEmit' now reports 0 errors (was 1); cortex build green (23/23);\n323 cortex tests pass, 0 fail.",
"is_bot": false,
"headline": "fix(debt): Wave 3 — remove dead cortex progressCheckpoint control (Wa…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-20T21:40:18Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "f046299f1c7276c926dbda28ca7d4c6766536516",
"body": "…BudgetChars\n\nThe DEBT-REGISTER premise 'recencyBudgetChars governs the compaction threshold'\nwas a documentation lie. compactHistoryStage truncates the whole thread at\nwindow*4 chars (a full-window safety valve) and never referenced\nrecencyBudgetChars. The field's real, live role is the generous pe\n[…]\ndead).\n\nProactive earlier compaction (firing below full window) is a behavioral change\nthat can strip recall context — deferred to the Wave 5 bench, not forced blind.\n\nAssembly suite green (136 pass).",
"is_bot": false,
"headline": "fix(debt): Wave 3 §3b — correct compaction doc lie + delete dead aged…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-20T21:39:30Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "d4ed0ea806793cdba164d39d78815ad8e5fb1d35",
"body": "…Timeout control\n\nwithCacheTimeout()/execution.cacheTimeoutMs was a confirmed no-op: the value\nthreaded builder → runtime-construction → runtime.ts, but ToolResultCacheLive()\nis always constructed with no args, so the tool-result cache always used its\ndefault 300s TTL. The knob never did anything.\n\n\n[…]\nrift gates and 4 cortex tests updated consistently.\n\nBuild green (37/37); all 8 architectural-invariant scripts, capability\nmanifest, and North Star gate green; 1360 runtime+cortex tests pass, 0 fail.",
"is_bot": false,
"headline": "fix(debt): Wave 3 — remove dead withCacheTimeout no-op + cortex cache…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-20T21:34:47Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "526fa7255c2bf50e23e182cca1e6aa58c468f8e3",
"body": null,
"is_bot": false,
"headline": "docs(agents): memory sync — Wave 3 delete round 2 shipped",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-20T16:32:15Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "4517f5b3ad265536da1f447e64755defb44de998",
"body": "…narios, orphan fields\n\nRegister §4 deletions, each grep-verified for zero non-test readers first.\n\nLedger kinds (reasoning): checkpoint-marker, deliverable-commit, contract-amended\n+ amendContract()/ContractAmendment REMOVED (zero writers AND readers). Ledger\nsingle-writer invariant green. process-\n[…]\nparity suite has only the\npre-existing load/timing flakes (CLI process-spawn, perf-timing, 5-20s bench\ncells — all pass isolated, green in CI on fresh runners), zero new failures.\nRegister §4 flipped.",
"is_bot": false,
"headline": "fix(debt): Wave 3 (round 2) — dead ledger kinds, dead vocabulary, sce…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-20T16:24:31Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "f8e1226542c3f1ef094aef538c87f401448fec58",
"body": null,
"is_bot": false,
"headline": "docs(agents): memory sync — Wave 3 delete round 1 shipped",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-20T15:22:28Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "10e63d5cee8dc22f104daf345235283a745de7a4",
"body": "…gate)\n\nThe orchestration deletion removed apps/examples/09-orchestration.ts; the\nexamples guide still linked to it on GitHub (404). Removed the row; the\nDocs Link Check gate is the only thing that caught it (Test/Typecheck/docs-gates\nwere already green).",
"is_bot": false,
"headline": "fix(docs): drop the deleted 09-orchestration example link (dead link …",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-20T15:16:38Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d13fa3c2233620176d5376ad388310b818a62014",
"body": "… flags\n\nRegister §4 deletions (LOC goes down; wire-or-delete):\n\npackages/orchestration REMOVED (net -2833 LOC). OrchestrationService/WorkerPool/\nWorkflowEngine had zero live consumers (worker-pool.spawn() built a struct in a\nRef, nothing ran). Removed the whole package, the published\n`reactive-agen\n[…]\neen at ceiling 256. Full-suite run showed only load/timing flakes\n(CLI process-spawn, perf-<500ms, 20s bench cells) that pass isolated, plus the\nAGENTS.md drift now fixed. Register §4 + P0-12 flipped.",
"is_bot": false,
"headline": "fix(debt): Wave 3 (round 1) — delete orchestration package + dead RA_…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-20T15:08:58Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "8809adeb251af4c3a21c9a9f350bfc58c2186f4a",
"body": null,
"is_bot": false,
"headline": "docs(agents): memory sync — Wave 2 spine COMPLETE (all 7 boundaries)",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-20T14:16:58Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "1a2d9c16152b0abc5381e136a3e42b368378ed9c",
"body": "B8 part 2 (T4 fork/cancellation, T3b depth correlation, T5 nesting) landed in\nc889ca7d/b0431110/cb19cda9. Flip register B8 to RESOLVED; re-sync README for the\n3 new subagent tests (cancellation, depth-correlation, nesting-depth).\n\nVerified: full CI-parity suite 0 fail / 8300 tests; no-cascade gate green; the\nabort-signal 'mid-stream abort' timing test is a pre-existing full-suite flake\n(passes isolated + in an independent full runtime run) — not a fork regression.",
"is_bot": false,
"headline": "docs(debt): Wave 2 B8 COMPLETE — register + README",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-20T14:16:10Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "cb19cda9f9a4ec1b83c2bf5cc2c949cf3fa32d32",
"body": "Teams were structurally flat: depth was a literal 0 at every call site so the\ndepth>=max guard never fired, and children never got spawn tools so nesting was\nunreachable even with a live guard. The guard now reads RunContext.depth (the\nspawning agent's), and children are given their own spawn-agent/\n[…]\n; delegation refused past maxRecursionDepth 1 stays at depth 1 with no\nRangeError. Cutting child spawn registration drops depth 2 → 1 and fails.\nFull subagent suite + no-cascade gate green (66 tests).",
"is_bot": false,
"headline": "fix(debt): Wave 2 B8-T5 — nesting; the recursion cap is live (G7)",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-20T13:49:24Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "b0431110673fcb054c4622f1089c0ae5b227d2ac",
"body": "A delegated child's trace events shared no rootRunId/depth with the parent — an\nunlinked island. The child's RunContext (rootRunId/parentRunId/depth) now rides\non its task metadata; the execution engine stamps those fields onto the child's\nAgentStarted/AgentCompleted, and the trace normalizer copies\n[…]\ncut proven): child trace events have depth===1, rootRunId===parent\nrunId, runId!==parent runId; dropping runContext from the child metadata drops\ndepth 1 and fails the test. trace + core suites green.",
"is_bot": false,
"headline": "fix(debt): Wave 2 B8-T3b — correlate sub-agent trace events at depth 1",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-20T13:43:50Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "c889ca7d9cfed71b54c1467596531cbba89a191f",
"body": "…e (real cancellation)\n\nThe delegation boundary ran the child on a DETACHED root fiber\n(await Effect.runPromise(subEffect.pipe(Effect.provide(subRuntime)))), which\nFiber.interrupt on the parent could not reach — interrupting the parent orphaned\nin-flight children. buildSubAgentTask now returns an Ef\n[…]\n the fork, terminate() interrupts the\nin-flight child; reverting to runPromise lets the orphan complete → test fails.\nNo-cascade gate (m8-sub-agent-delegation) stayed GREEN. Full subagent suite green.",
"is_bot": false,
"headline": "fix(debt): Wave 2 B8-T4 — sub-agents fork into the parent's fiber tre…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-20T13:35:59Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "fea9ef8d8760e03eb94cb822751d2b929ed33fd1",
"body": "…+ G1 shared bus\n\nRATIFIED re-scoped B8 (owner sign-off): Tasks 1-5 of the subagents-and-logging\nplan. This lands the safe, non-regressing foundation (T1, T2, T3a); the\nconcurrency-sensitive fork rewrite (T3b/T4/T5) follows in part 2.\n\n- T1: packages/core/src/run-context.ts — the explicit RunContext\n[…]\nols 961 (no-cascade green),\ncore+trace 250 — all 0 fail; full CI-parity suite 0 fail / 8296 tests;\ncore/trace/runtime/tools build clean. Plan RATIFIED re-scoped; register B8\nPARTIAL; README re-synced.",
"is_bot": false,
"headline": "fix(debt): Wave 2 B8 (part 1) — RunContext spine + trace correlation …",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-20T12:56:03Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "52428cb578f1998b1dfdf91a7f3e015973abe295",
"body": "…ated",
"is_bot": false,
"headline": "docs(agents): memory sync — Wave 2 6/7 boundaries shipped, B8 owner-g…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-20T11:55:08Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "42e188ec3e7b26cc721fb19cebe4f1af8d2f15e8",
"body": "… sweep\n\nThe builder->runtime seam crosses every field via\n`self as unknown as BuilderRuntimeStateView`, a structural cast that won't\ncatch a renamed/removed field, and the wither tests asserted private `_*`\nfields, not behavior — so deleting a wiring line in runtime-construction.ts left\nthe suite g\n[…]\ne 1339 pass/0 fail; full CI-parity suite 0\nfail / 8289 tests; runtime build clean (strict, DTS); wither-discipline +\nwither-ratchet gates green. Register B3 + runtime-as-any flipped; README\nre-synced.",
"is_bot": false,
"headline": "fix(debt): Wave 2 B3 — builder-seam behavioral tests + runtime as-any…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-20T11:54:00Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "e304ac6fb0dc528816b06634fd6deeb60dbe1fed",
"body": "…linkage\n\nThe register's '19 orphaned KernelMeta fields' was an overcount conflating\nthree populations. Triaged each:\n- Already projected (healthy): the honesty markers + terminatedBy family cross\n via CompletionEnvelope / ReActKernelResult (envelopeFromKernelState,\n react-kernel.ts) and are consu\n[…]\ny 0 fail / 8282 tests; check-ledger-writes green;\nreasoning+runtime build clean. Register B4 + §5.3 + #44 flipped; §4 orphan\nrecount (3 dead retired, rest reclassified); README re-synced (1053->1055).",
"is_bot": false,
"headline": "fix(debt): Wave 2 B4 — kernel->strategy projection triage + verifier …",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-20T11:08:14Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "bb99ad8e72965c884c25c4d938508416eb21d80d",
"body": "… gate\n\nThe RunLedger \"requirement\" kind (declared->satisfied|blocked) had ZERO\nnon-test writers, so its two live readers (assess.ts:207, standing-frame.ts:193)\nalways saw [] — the meta-loop's requirement lifecycle was fiction; the Projector\nrendered no outstanding work and evidenceRefs were double-\n[…]\nages/reasoning 2401 pass/0 fail; check-ledger-writes.sh\ngreen; full CI-parity suite 0 fail / 8277 tests; reasoning build clean. Register\nB7 + §3b #39 flipped; README re-synced (1051->1053 test files).",
"is_bot": false,
"headline": "fix(debt): Wave 2 B7 — mint requirement ledger lifecycle at compile +…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-20T10:45:55Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "0adbcafaf3def730e4d0688fd2fe54509970063a",
"body": "PhaseStarted/PhaseCompleted were declared in AgentStreamEvent and advertised as\ndensity:\"full\" events (ui-core protocol + docs/features/streaming.md), but the\nEventBus->public-stream projection in execute-stream.ts subscribed only to\niteration/step/tool events — both phase events had ZERO stream wri\n[…]\nt density emits neither. Flipping the guard to\nif(false) drops the full-density chunks (red); restored.\n\nVerified: bun test packages/runtime 1330 pass/0 fail; runtime build clean.\nRegister B5 flipped.",
"is_bot": false,
"headline": "fix(debt): Wave 2 B5 — project phase events onto the public stream",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-20T10:45:31Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "7b257c4009c00930d19f0e47024cfbcbffc7a251",
"body": null,
"is_bot": false,
"headline": "docs(agents): memory sync — Wave 2 B1+B2 shipped, CI green",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-20T03:31:14Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "8cc595f0d8b45ae3ed7995ea79d70bb732271359",
"body": "…trategies\n\nOnly reactive forwarded terminatedBy + abstention across the strategy->engine\nresult boundary, so execution-engine.ts:1096 (terminatedBy ?? \"end_turn\")\nmislabeled every non-reactive run and projectAbstention never fired —\nreceipt.abstained was permanently false on 8 of 9 paths (P0-5).\n\nB\n[…]\ned the old end_turn default); full CI-parity\nsuite (keys stripped) 0 fail / 8267 tests; reasoning build clean; WS-5b cast\nceiling respected. Register P0-5 + B2 + §5.1 + §5.2 flipped; README re-synced.",
"is_bot": false,
"headline": "fix(debt): Wave 2 B2 — terminatedBy + abstention forward across all s…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-20T03:25:48Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "3038eb03ec0a10b9d00e4d837be823d89b205ff6",
"body": null,
"is_bot": false,
"headline": "fix(ci): re-sync README file count after B1 mutation test (1049→1050)",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-20T03:05:01Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d5dffadac4b7ae3afd3b5484a3cd6e30d6c10f12",
"body": "… point\n\nThe shared executeToolAndObserve primitive is the one path every hand-rolled\nstrategy (plan-execute, blueprint) routes tool calls through, yet it inherited\nno policy enforcement and minted no ledger — so a forbidden or hallucinated\ntool arriving via a planned step executed unchecked (P0-4, \n[…]\nkages/reasoning 2389 pass/0 fail; full CI-parity suite\n(keys stripped) 0 fail across 8263 tests; reasoning+runtime build clean;\nledger single-writer + WS-5 ceilings intact. Register P0-4 + B1 flipped.",
"is_bot": false,
"headline": "fix(debt): Wave 2 B1 — tool-policy gate + RunLedger mint at the choke…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-20T02:56:55Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "d1f4e2e5d7ca3fd85148b966c7fce3c4b9969317",
"body": "…l env\n\nThe replay-golden keystone recorded its run's trace into a dir chosen by the\nprocess-global REACTIVE_AGENTS_TRACE_DIR. Bun executes test FILES concurrently\nin one process, and two other suites (diagnose, meta-tools-default-surface)\nmutate that same env var, so the recorder's LLM exchanges co\n[…]\no concurrent env mutation. Same global-state-race\nclass as the Wave 0 mock.module leak fixes.\n\nVerified: the 3 env-racing files run green together keyless; full CI-parity\nsuite (keys stripped) 0 fail.",
"is_bot": false,
"headline": "fix(ci): replay-golden sets trace dir explicitly, not via raced globa…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-20T02:39:59Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "16b3038ea254e7ae161a9b5dc8785178e16cd533",
"body": "…8→1049)\n\nThe rebase onto main pulled in PR #196's packages/replay/src/e2e.test.ts,\nbumping the live test-file count by one after Wave 1's metrics sync. CI's\nmetrics:check counts test files from the tree, so README drifted. Re-synced.",
"is_bot": false,
"headline": "fix(ci): re-sync README test-file count after replay test landed (104…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-20T02:27:53Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "7c44226bc53a7d9bf19336d1a2df2cdda9269d51",
"body": null,
"is_bot": false,
"headline": "docs(agents): memory sync — debt burndown Wave 1 shipped",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-20T01:12:17Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "80337d2623ffd86d96a4b5e79195210de2e8bb4d",
"body": "Every shipped API that promised behavior it did not deliver is now removed,\nwired, or fixed; every false published claim is gone. v0.14 is already a\nbreaking release, so lying surfaces are removed outright rather than deprecated.\n\nPublic API (register P0-1,2,3,6,7,8,9,10,11):\n- REMOVED no-op options\n[…]\ne.\n\nVerified: bun test — Docs + provider + runtime + RI green; the only non-Docker\nsuite failure was a stray untracked orphan test (imported a deleted export),\nmoved aside. Both anti-rot gates exit 0.",
"is_bot": false,
"headline": "fix(debt): Wave 1 — stop the lies (public API + published claims)",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-20T01:10:58Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "9df97ceeda427cec8a41fd997c211b99ea8b7016",
"body": "Main goes green and the anti-rot gates become real:\n\n1. Fix the 3 environment-independent failures:\n - builder-with-budget: both regexes pin the real broadened message.\n - WS-5 silent-swallow ceiling: the new killSwitchAction site\n (reactive-agent.ts) typed to Effect<void> (KillSwitchService\n[…]\nics-cache.json refreshed.\n\nVerified: bun test twice — 8224 pass / 0 fail / 8253 tests / 1045 files.\nBoth gates exit 0. Register §1 ratchet + P0-15 (PROVEN) + P0-21 (gate\nPROVEN, skips remain) updated.",
"is_bot": false,
"headline": "fix(debt): Wave 0 — make the signal trustworthy",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-20T00:51:44Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "3bdf7388b817cb73d7d7c56c49c2aa9f201eebb4",
"body": "… 09 amended\n\nReview found the burndown plan sound in shape and order but failing its own\ndefinition of done: the register it defers to had holes, and the governance it\nprescribes (amend 09, never fork direction) it had not followed.\n\n1. Absorb-or-defer pass (register 3b): every open item from the t\n[…]\nmbers on the sd-0.50 instrument would repeat July with fresher branding.\n4. Register 5 latent bugs assigned to Wave 2 (ride B2/B4).\n5. Subagent disposition recorded: debt repair, not new architecture.",
"is_bot": false,
"headline": "docs(debt): close the five plan-review defects — register exhaustive,…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-20T00:51:44Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "5efa8a9a3bcaa0981574bf19a6f1c831063a3fa3",
"body": "Seven waves, ordered by dependency rather than severity. The plan deliberately\ncontains no item list: the Debt Register is the single source of truth, and this\ndocument holds only the order and the rules. Thirteen plans rotted in July\nbecause each re-listed its own items and then drifted.\n\nThe order\n[…]\nred; wire-or-delete with no third option;\nboundary-first; the ratchet only decreases; v0.14 is already breaking, so removing\na lying API is cheaper and more honest than implementing it under pressure.",
"is_bot": false,
"headline": "docs(plan): debt burndown — sequence only, register holds the items",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-20T00:51:44Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "886b5d0a581b548eea24f45fe755feb978f58101",
"body": "Fifth and final validation sweep. 23 published claims are FALSE, 6 unvalidated.\n\nVerified by running the suite: main is RED. 8,199 pass / 21 fail / 8,247 tests /\n1,045 files. Eighteen failures are Docker-daemon-dependent; three are\nenvironment-independent and gate CI (ci.yml:82 runs bare `bun test`)\n[…]\nnces drift by marking failing blocks as\nskipped. The claims did not rot randomly — the two mechanisms built to prevent\nrot were never connected to anything that could fail. Same disease, one level up.",
"is_bot": false,
"headline": "docs(debt): register — published-claims sweep; main is red",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-20T00:51:44Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "02fa631f2d830729bd445c895dd53e57b9b1433a",
"body": "Replaces the scattered findings across six audit-report directories with one\nledger. Nothing is \"known debt\" unless it has a row here; every row carries a\nverdict, primary evidence, and the gate that keeps it fixed.\n\nMethod: five parallel read-only sweeps (builder withers, strategy x mechanism\nmatri\n[…]\ntention and goalAchieved across eight.\n\nRatchet: the counts may only go down. Definition of done is now declaration +\nwriter + reader + a mutation that goes red — prose findings do not discharge debt.",
"is_bot": false,
"headline": "docs(debt): canonical Debt Register — 5-sweep validation, ratcheted",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-20T00:51:44Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "9c9e1f63647946cda563c431314da7e1884bd69f",
"body": "Co-authored-by: Zain Dana Harper <zain@aurora-framework.dev>",
"is_bot": false,
"headline": "test(replay): add deterministic end-to-end replay coverage (#196)",
"author_name": "ZentropyLabs.ai",
"author_login": "HarperZ9",
"committed_at": "2026-07-19T23:49:25Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "e0a7a2b274f164bb920bf5d021a617ed2feddc7d",
"body": "… one open-work list\n\nComprehensive map + health audit of the July harness fortnight (226 unpushed\ncommits), synthesized from four parallel read-only audits: program completion\nvs git, built-never-wired code sweep, docs/authority accuracy, and churn\nanalysis.\n\nDeliverable: wiki/Research/Audit-Report\n[…]\nbefore the probe fleet gave it a regression\ngate. Corrective doctrine recorded in §4b: boundary-first fixing, probes as the\ngate, a sole-caller grep before deletion, measurement freeze, sync-per-wave.",
"is_bot": false,
"headline": "docs(audit): state-of-the-framework 2026-07-12 — one authority chain,…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-12T23:02:03Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "68bcb046db04da239bc866abf01853c58e0a61ce",
"body": "…h, without .withKillSwitch()\n\nAll four are documented public methods on ReactiveAgent, and all four requested\nKillSwitchService by its raw Context tag. That service is only in the layer when\n.withKillSwitch() was called — Layer.empty otherwise, which is the DEFAULT\n(builder.ts: _enableKillSwitch = \n[…]\nnd .withKillSwitch(), never leaks the Effect defect text, and that the\nopted-in path still terminates — so the guard cannot be satisfied by breaking\nthe feature.\n\nVerified: runtime 1013 pass / 0 fail.",
"is_bot": false,
"headline": "fix(runtime): pause/resume/stop/terminate must fail clearly, not cras…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-12T15:28:01Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "1c4c670f854c9976be4d828e6ec72463321c0b91",
"body": "…, ToT guard reachability",
"is_bot": false,
"headline": "docs(agents): memory sync — stream tool events, unhandled-fiber noise…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-12T14:14:45Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "e41006e918e30b14155c1879858e2f05eca37bf4",
"body": "… become reachable\n\nTwo findings from the probe fleet, both the same shape: a mechanism that exists,\nis documented, and cannot fire.\n\n1. Six of the nine action-step sites in act.ts minted their step without\n `metadata.toolUsed` — the allowedTools block, the meta-tool handler,\n final-answer accep\n[…]\n84\ntok / 117s -> 11 calls / 17,919 tok / 55s, still writing the correct sum, all\nchecks pass. Cost is measured; quality-neutrality at other tiers is NOT claimed\nhere and needs the cross-tier ablation.",
"is_bot": false,
"headline": "fix(kernel,tot): every started tool call completes; ToT's cost guards…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-12T14:10:11Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "61f05489452dd8caeb0d0822fc9fe1bb765f76d2",
"body": "… stop reporting as unhandled fibers\n\nProbe fleet rerun (12/12 graded checks passing) surfaced three defects that were\ninvisible to the checks and visible only in stderr. The instrument was the first\nbug: probe-harness graded the returned AgentResult and nothing else, so a run\ncould scream during ex\n[…]\n Live on ollama/gemma4:\np8 stream now shows ToolCallStarted x2 + ToolCallCompleted x2 with paired callIds\nand streamed tools exactly matching receipt.toolsUsed; p6 hygiene clean against a\nreal ENOENT.",
"is_bot": false,
"headline": "fix(stream,tools): tool events reach the public stream; failing tools…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-12T13:53:31Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "b03a1b73bbacb82dfe08ffa573605a7f0ed43983",
"body": "…100)",
"is_bot": false,
"headline": "docs(agents): memory sync — wave 9 full interventions coverage (23f34…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-12T13:41:29Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "23f341000c70d67565347e3e8e18313f37bb92ae",
"body": "…l actor named (#54)\n\nCompletes the receipt-as-debugging-spine (north-star spec §5b). W-J shipped\nthe slice (gate + grounding redirects); this annotates the remaining control\nactors at their EXISTING emission points, so a c4e964e8-class misfire is\ndiagnosable from result.receipt.interventions[] inst\n[…]\n entry absent → red). reasoning 2372 pass, core 186 pass; W-J\nauthority-exits + receipt-interventions kept green; tsc clean (excl. the\nparallel workstream's pre-existing step-executor llmCalls error).",
"is_bot": false,
"headline": "feat(reasoning): full receipt.interventions[] coverage — every contro…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-12T13:41:13Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "c7d5ddef8733da73d2ec3e42855f5e0f9f20382f",
"body": "…ed (ee9a1471)",
"is_bot": false,
"headline": "docs(agents): memory sync — wave 8 docs gate honest + error-lies kill…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-12T12:45:35Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "ee9a147186f8b16b2e58e20f7a89b1302d5fb267",
"body": "…gestion lies (#58)\n\nThe docs examples gate was green because ~35 real-drift blocks were marked\ndocs-skip-typecheck instead of fixed (a false green — the metric-gaming the\ngate exists to prevent). Fixed each to the real API and UNMARKED it, so the\ngreen now means \"docs are correct,\" not \"failures hi\n[…]\nthe test).\n\ndocs:examples:check green (349 checked); docs:gen:api clean; docs:build 92\npages; runtime tsc clean (excl. the parallel logging workstream's pre-existing\neffect-log-capture.test.ts break).",
"is_bot": false,
"headline": "fix(docs,runtime): make the anti-rot gate honest + kill the error-sug…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-12T12:45:11Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "70d87a0cef43d1ea41474d2823116d57e28bda42",
"body": null,
"is_bot": false,
"headline": "docs(agents): memory sync — result-boundary verification (b6745426)",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-12T12:25:17Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "b6745426455f4396645b78673799db247950468c",
"body": "…es every run\n\nEmpirical: the terminal verifier ran ONLY inside the react kernel. Strategy\npaths (blueprint / plan-execute / tree-of-thought / reflexion / code-action)\nand the engine's inline loop shipped their answers UNVERIFIED — `rax:diagnose`\nreported \"0 verifier verdicts\" on every strategy trac\n[…]\nict events; p9 matrix\n+ p1 ALL CHECKS PASS. A pre-existing test comment (\"no verifier pass is\nforwarded to the receipt sites … bump if that plumbing lands\") is now the\nassertion — the plumbing landed.",
"is_bot": false,
"headline": "feat(runtime,core): result-boundary verification — the verifier reach…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-12T12:24:40Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "31933c9e51a4fabb830ce7076afb1aeaea7057cb",
"body": "…f8f0ef2)",
"is_bot": false,
"headline": "docs(agents): memory sync — wave 7 doc propagation + anti-rot gate (2…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-12T02:05:13Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "2f8f0ef28d210f59f92aae01fccc5156716def42",
"body": "… (#57)\n\nPublic-facing surfaces reframed to the shipped createAgent(config) front door,\nper the ratified dual-API spec (declarative front door -> fluent builder ->\ncompose). Additive: no builder docs deleted, the hierarchy is reframed.\n\n- Anti-rot gate (durable): scripts/check-doc-examples.ts, `docs\n[…]\norts) — pre-existing doc bugs the gate surfaced. The green means \"no\nUNMARKED block fails,\" not \"all docs correct.\" #58 fixes them so the green is\nhonest; the gate catches all FUTURE drift regardless.",
"is_bot": false,
"headline": "docs: propagate createAgent dual API + examples-compile anti-rot gate…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-12T02:04:34Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "5cc9cafdee3da4838adcac45108ed49f7b01ce11",
"body": null,
"is_bot": false,
"headline": "docs(agents): memory sync — probe-fleet wave 2 (12d86630)",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-12T02:03:26Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "12d8663009a2bce2d31d4c7a864999df1fb45da2",
"body": "…ce policy parity\n\nFleet rerun after wave 1 went 12/12 clean; this wave takes the ranked backlog.\nThree coordinated fixes on the ENGINE's inline path plus the regressions the\nfleet itself caught while fixing them.\n\n1. Empty-output success invariant (M7's engine mirror). Deterministic repro:\n tool-\n[…]\net drift\nfails); reasoning 2370, llm-provider 381, benchmarks 398 all 0 fail; bench:t0\ndeterministic gate green; live fleet spot-checks p2/p6/p10 ALL PASS and p4\nhonest-failure as above; builds clean.",
"is_bot": false,
"headline": "fix(runtime,reasoning,llm-provider): inline-path honesty + tool-surfa…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-12T02:02:39Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "61fcdfe9ad1e189c40bde047307c93b3295a37aa",
"body": null,
"is_bot": false,
"headline": "docs(agents): memory sync + debrief — probe-fleet QA wave (4 fixes)",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-12T00:38:51Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "f65722f6d31fe331839705b2ca1b38285dbd1b4e",
"body": "…d receipt-vs-disk cross-checks\n\nPermanent QA tooling for the harness-improvement loop: build agents the way\nusers would (public builder API, live model), run realistic tasks, grade with\ndeterministic checks including receipt-claims-vs-disk-truth cross-checks.\nArchetypes: research-writer, multi-file\n[…]\neep (2026-07-11, gemma4) surfaced 8 findings; 4 fixed same-day\n(309a5c3a inline ledger, ed5caa07 code-action, d4623073 llmCalls,\nb1755ff4 goalAchieved). Reports committed as the before/after evidence.",
"is_bot": false,
"headline": "feat(probes): real-world agent probe fleet — 10 archetypes with grade…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-12T00:37:02Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "b1755ff40512b8623652c0b87511d7e700fc282f",
"body": "…urn's \"maybe\" answered deterministically\n\nEmpirical: probe p5 (gemma4, .withLongHorizon()) — success:true, file\nproduced, goalAchieved:null. Every end_turn run stayed null forever while the\ndeterministic answer (RunContract × step-ledger deliverable scan) sat one\nfield away on receipt.deliverables.\n[…]\nse on a run whose\nfile genuinely didn't land (receipt agrees with disk) — the null is gone in\nboth directions. runtime 1246 tests, same 2 pre-existing withBudget fails\n(parallel session); build clean.",
"is_bot": false,
"headline": "fix(runtime): goalAchieved resolves from deliverable evidence — end_t…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-12T00:36:45Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "d4623073b907a47b9a1d2611695d894b7d0e9902",
"body": "…mCalls (was 0)\n\nEmpirical: probe p9 (gemma4, same hermetic file task through all three\nstrategies) — every run reported metadata.llmCalls:0. The kernel counts its\nown calls (state.llmCalls, think.ts) and blueprint was fixed in 02e5d12b; the\nsiblings never read the counter or shipped a count.\n\nWirin\n[…]\nrategy; reasoning 2370 tests 0 fail; build clean.\n\nPerf note (unfixed, tracked): ToT burned 19 calls / 32k tokens / ~2min adding\nthree numbers — strategy cost on trivial tasks is its own backlog item.",
"is_bot": false,
"headline": "fix(reasoning): reflexion/plan-execute/tree-of-thought report real ll…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-12T00:30:41Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "ed5caa07007f69271ecc2b278f25796881812789",
"body": "…ools — five defects, one probe\n\nEmpirical: probe p7 (gemma4, \"sum of squares 1..250 → write file\"). Before:\nrun FAILED with \"Unexpected token '-'\" and reported tokensUsed:0 / llmCalls:0\nbeside a real plan call in the trace. After: exact answer 5239625 on disk,\nproduced:true, tokensUsed/llmCalls exa\n[…]\n examples.\n\nVerification: sandbox/tool-binding/ledger pins RED→GREEN (36+40 tests);\nreasoning package 2370 pass 0 fail; live p7 rerun ALL CHECKS PASS;\nturbo build --force (reasoning, tools) clean.",
"is_bot": false,
"headline": "fix(reasoning,tools): code-action was structurally broken with real t…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-12T00:22:33Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "309a5c3ada14296755f03960c5d9558c315ab947",
"body": "…ault-path receipts stop lying\n\nEmpirical: real-world probe fleet (2026-07-11, gemma4) — EVERY default-strategy\nrun reported receipt.deliverables[].produced:false with the file on disk\n(probes p1/p2/p4/p5/p10), and the new deliverable verdict cap (e247e6b8) then\ndowngraded those honest runs to parti\n[…]\nom\n the parallel session); reasoning 2368 pass 0 fail.\n\nSurfaced, not fixed here: p10 second run shipped success:true with empty\noutput (inline-path output ownership); tracked in the probe backlog.",
"is_bot": false,
"headline": "fix(runtime): inline agent loop mints the canonical tool ledger — def…",
"author_name": "Tyler Buell",
"author_login": "tylerjrbuell",
"committed_at": "2026-07-12T00:13:33Z",
"body_truncated": true,
"is_coding_agent": false
}
],
"releases_count": 35,
"commits_last_year": 3410,
"latest_release_at": "2026-07-22T00:47:00Z",
"latest_release_tag": "v0.14.0",
"releases_from_tags": false,
"days_since_last_push": 7,
"active_weeks_last_year": 21,
"days_since_latest_release": 8,
"mean_days_between_releases": 8.6
},
"community": {
"has_readme": true,
"has_license": true,
"has_description": true,
"has_contributing": true,
"health_percentage": 85,
"has_issue_template": false,
"has_code_of_conduct": false,
"has_pull_request_template": true
},
"ecosystem": {
"packages": [
{
"name": "@reactive-agents/cli",
"exists": true,
"license": "MIT",
"keywords": [
"ai",
"agents",
"cli",
"typescript",
"llm",
"reactive-agents",
"mcp",
"agent-cli",
"developer-tools"
],
"ecosystem": "npm",
"matches_repo": true,
"registry_url": "https://www.npmjs.com/package/@reactive-agents/cli",
"is_deprecated": false,
"latest_version": "0.14.0",
"repository_url": "https://github.com/tylerjrbuell/reactive-agents-ts",
"versions_count": 42,
"total_downloads": null,
"dependents_count": null,
"deprecation_note": null,
"maintainers_count": 1,
"monthly_downloads": 1071,
"first_published_at": "2026-02-20T17:14:08.787000Z",
"latest_published_at": "2026-07-22T00:46:54.944000Z",
"latest_version_yanked": null,
"days_since_latest_publish": 8
},
{
"name": "@reactive-agents/cortex",
"exists": true,
"license": "MIT",
"keywords": [
"reactive-agents",
"cortex",
"agent-studio",
"agent-ui",
"agent-observability",
"ai-agents",
"elysia"
],
"ecosystem": "npm",
"matches_repo": true,
"registry_url": "https://www.npmjs.com/package/@reactive-agents/cortex",
"is_deprecated": false,
"latest_version": "0.14.0",
"repository_url": "https://github.com/tylerjrbuell/reactive-agents-ts",
"versions_count": 11,
"total_downloads": null,
"dependents_count": null,
"deprecation_note": null,
"maintainers_count": 1,
"monthly_downloads": 1678,
"first_published_at": "2026-05-05T17:36:49.186000Z",
"latest_published_at": "2026-07-22T00:46:53.401000Z",
"latest_version_yanked": null,
"days_since_latest_publish": 8
},
{
"name": "@reactive-agents/a2a",
"exists": true,
"license": "MIT",
"keywords": [
"ai",
"agents",
"ai-agents",
"llm",
"effect-ts",
"typescript",
"a2a",
"agent-to-agent",
"agent-protocol",
"json-rpc",
"agent-card",
"multi-agent",
"sse"
],
"ecosystem": "npm",
"matches_repo": true,
"registry_url": "https://www.npmjs.com/package/@reactive-agents/a2a",
"is_deprecated": false,
"latest_version": "0.14.0",
"repository_url": "https://github.com/tylerjrbuell/reactive-agents-ts",
"versions_count": 26,
"total_downloads": null,
"dependents_count": null,
"deprecation_note": null,
"maintainers_count": 1,
"monthly_downloads": 1145,
"first_published_at": "2026-02-25T01:34:52.143000Z",
"latest_published_at": "2026-07-22T00:46:28.843000Z",
"latest_version_yanked": null,
"days_since_latest_publish": 8
},
{
"name": "@reactive-agents/core",
"exists": true,
"license": "MIT",
"keywords": [
"ai",
"agents",
"ai-agents",
"llm",
"effect-ts",
"typescript",
"eventbus",
"pubsub",
"agent-lifecycle",
"state-machine",
"core"
],
"ecosystem": "npm",
"matches_repo": true,
"registry_url": "https://www.npmjs.com/package/@reactive-agents/core",
"is_deprecated": false,
"latest_version": "0.14.0",
"repository_url": "https://github.com/tylerjrbuell/reactive-agents-ts",
"versions_count": 27,
"total_downloads": null,
"dependents_count": null,
"deprecation_note": null,
"maintainers_count": 1,
"monthly_downloads": 2202,
"first_published_at": "2026-02-20T17:13:25.532000Z",
"latest_published_at": "2026-07-22T00:46:06.042000Z",
"latest_version_yanked": null,
"days_since_latest_publish": 8
},
{
"name": "@reactive-agents/cost",
"exists": true,
"license": "MIT",
"keywords": [
"ai",
"agents",
"ai-agents",
"llm",
"effect-ts",
"typescript",
"cost-tracking",
"budget",
"model-routing",
"complexity-routing",
"token-cost",
"llm-cost"
],
"ecosystem": "npm",
"matches_repo": true,
"registry_url": "https://www.npmjs.com/package/@reactive-agents/cost",
"is_deprecated": false,
"latest_version": "0.14.0",
"repository_url": "https://github.com/tylerjrbuell/reactive-agents-ts",
"versions_count": 27,
"total_downloads": null,
"dependents_count": null,
"deprecation_note": null,
"maintainers_count": 1,
"monthly_downloads": 1201,
"first_published_at": "2026-02-20T17:13:56.840000Z",
"latest_published_at": "2026-07-22T00:46:32.134000Z",
"latest_version_yanked": null,
"days_since_latest_publish": 8
},
{
"name": "@reactive-agents/eval",
"exists": true,
"license": "MIT",
"keywords": [
"ai",
"agents",
"ai-agents",
"llm",
"effect-ts",
"typescript",
"evaluation",
"llm-as-judge",
"benchmark",
"regression-testing",
"scoring",
"eval"
],
"ecosystem": "npm",
"matches_repo": true,
"registry_url": "https://www.npmjs.com/package/@reactive-agents/eval",
"is_deprecated": false,
"latest_version": "0.14.0",
"repository_url": "https://github.com/tylerjrbuell/reactive-agents-ts",
"versions_count": 26,
"total_downloads": null,
"dependents_count": null,
"deprecation_note": null,
"maintainers_count": 1,
"monthly_downloads": 946,
"first_published_at": "2026-02-21T01:32:58.329000Z",
"latest_published_at": "2026-07-22T00:46:33.646000Z",
"latest_version_yanked": null,
"days_since_latest_publish": 8
},
{
"name": "@reactive-agents/health",
"exists": true,
"license": "MIT",
"keywords": [
"ai",
"agents",
"ai-agents",
"llm",
"effect-ts",
"typescript",
"health-check",
"readiness",
"liveness",
"probe",
"production"
],
"ecosystem": "npm",
"matches_repo": true,
"registry_url": "https://www.npmjs.com/package/@reactive-agents/health",
"is_deprecated": false,
"latest_version": "0.14.0",
"repository_url": "https://github.com/tylerjrbuell/reactive-agents-ts",
"versions_count": 15,
"total_downloads": null,
"dependents_count": null,
"deprecation_note": null,
"maintainers_count": 1,
"monthly_downloads": 1057,
"first_published_at": "2026-03-12T14:16:44.001000Z",
"latest_published_at": "2026-07-22T00:46:12.740000Z",
"latest_version_yanked": null,
"days_since_latest_publish": 8
},
{
"name": "@reactive-agents/memory",
"exists": true,
"license": "MIT",
"keywords": [
"ai",
"agents",
"ai-agents",
"llm",
"effect-ts",
"typescript",
"memory",
"sqlite",
"vector-search",
"embeddings",
"fts5",
"rag",
"semantic-memory",
"agent-memory"
],
"ecosystem": "npm",
"matches_repo": true,
"registry_url": "https://www.npmjs.com/package/@reactive-agents/memory",
"is_deprecated": false,
"latest_version": "0.14.0",
"repository_url": "https://github.com/tylerjrbuell/reactive-agents-ts",
"versions_count": 26,
"total_downloads": null,
"dependents_count": null,
"deprecation_note": null,
"maintainers_count": 1,
"monthly_downloads": 1705,
"first_published_at": "2026-02-20T17:13:48.885000Z",
"latest_published_at": "2026-07-22T00:46:19.525000Z",
"latest_version_yanked": null,
"days_since_latest_publish": 8
}
]
},
"popularity": {
"forks": 4,
"stars": 19,
"watchers": 0,
"fork_history": {
"days": [
{
"date": "2026-03-12",
"count": 1
},
{
"date": "2026-04-17",
"count": 1
},
{
"date": "2026-05-17",
"count": 1
},
{
"date": "2026-07-19",
"count": 1
}
],
"complete": true,
"collected": 4,
"total_forks": 4
},
"star_history": null,
"open_issues_and_prs": 32
},
"ai_readiness": {
"has_nix": false,
"example_dirs": [
"cookbook",
"demos",
"examples"
],
"has_llms_txt": false,
"has_dockerfile": true,
"has_mcp_signal": true,
"bootstrap_files": [],
"api_schema_files": [],
"has_devcontainer": true,
"typecheck_configs": [
"apps/advocate/tsconfig.json",
"apps/cli/tsconfig.json",
"apps/cortex/tsconfig.json",
"apps/cortex/ui/tsconfig.json",
"apps/docs/tsconfig.json",
"apps/examples/tsconfig.json",
"apps/stackblitz/01-hello-agent/tsconfig.json",
"apps/stackblitz/02-tool-integration/tsconfig.json",
"apps/stackblitz/03-strategy-demo/tsconfig.json",
"docker/signal-mcp/server/tsconfig.json",
"packages/a2a/tsconfig.json",
"packages/benchmarks/tsconfig.json",
"packages/channels/tsconfig.json",
"packages/compose/tsconfig.json",
"packages/core/tsconfig.json",
"packages/cost/tsconfig.json",
"packages/create-reactive-agent/tsconfig.json",
"packages/diagnose/tsconfig.json",
"packages/eval/tsconfig.json",
"packages/gateway/tsconfig.json",
"packages/guardrails/tsconfig.json",
"packages/health/tsconfig.json",
"packages/identity/tsconfig.json",
"packages/interaction/tsconfig.json",
"packages/judge-server/tsconfig.json",
"packages/llm-provider/tsconfig.json",
"packages/memory/tsconfig.json",
"packages/observability/tsconfig.json",
"packages/observe/tsconfig.json",
"packages/prompts/tsconfig.json",
"packages/react/tsconfig.json",
"packages/reactive-agents/tsconfig.json",
"packages/reactive-intelligence/tsconfig.json",
"packages/reasoning/tsconfig.json",
"packages/replay/tsconfig.json",
"packages/runtime-shim/tsconfig.json",
"packages/runtime/tsconfig.json",
"packages/svelte/tsconfig.json",
"packages/testing/tsconfig.json",
"packages/tools/tsconfig.json",
"packages/trace/tsconfig.json",
"packages/ui-core/tsconfig.json",
"packages/verification/tsconfig.json",
"packages/vue/tsconfig.json",
"tsconfig.json"
],
"toolchain_manifests": [],
"largest_source_bytes": 117970,
"source_files_sampled": 2346,
"oversized_source_files": 11,
"agent_instruction_files": [
".github/copilot-instructions.md",
"AGENTS.md",
"CLAUDE.md",
"apps/cortex/AGENTS.md"
],
"agent_instruction_max_bytes": 65593
},
"dependencies": {
"manifests": [
"package.json"
],
"advisories": {
"error": null,
"scope": "published_package",
"source": "osv",
"findings": [
{
"name": "@opentelemetry/core",
"direct": false,
"version": "2.6.0",
"severity": "moderate",
"ecosystem": "npm",
"cvss_score": 5.3,
"advisory_ids": [
"GHSA-8988-4f7v-96qf"
],
"fixed_version": "2.8.0",
"advisory_count": 1,
"oldest_advisory_days": 45
}
],
"collected": true,
"malicious": [],
"truncated": false,
"by_severity": {
"moderate": 1
},
"advisory_count": 1,
"affected_count": 1,
"assessed_count": 233,
"malicious_count": 0,
"assessed_package": "npm:@reactive-agents/cli@0.14.0",
"unassessed_count": 0,
"direct_affected_count": 0
},
"ecosystems": [
"npm"
],
"dependencies": [
{
"name": "reactive-agents",
"manifest": "apps/advocate/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "@reactive-agents/compose",
"manifest": "apps/advocate/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "@reactive-agents/health",
"manifest": "apps/advocate/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "effect",
"manifest": "apps/advocate/package.json",
"ecosystem": "npm",
"version_constraint": "^3.10.0"
},
{
"name": "effect",
"manifest": "apps/cli/package.json",
"ecosystem": "npm",
"version_constraint": "^3.10.0"
},
{
"name": "@reactive-agents/core",
"manifest": "apps/cli/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "@reactive-agents/runtime",
"manifest": "apps/cli/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "@reactive-agents/runtime-shim",
"manifest": "apps/cli/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "@reactive-agents/eval",
"manifest": "apps/cli/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "@reactive-agents/llm-provider",
"manifest": "apps/cli/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "@reactive-agents/a2a",
"manifest": "apps/cli/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "@reactive-agents/trace",
"manifest": "apps/cli/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "@reactive-agents/tools",
"manifest": "apps/cli/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "@reactive-agents/memory",
"manifest": "apps/cli/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "@reactive-agents/diagnose",
"manifest": "apps/cli/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "chalk",
"manifest": "apps/cli/package.json",
"ecosystem": "npm",
"version_constraint": "^5.4.0"
},
{
"name": "ora",
"manifest": "apps/cli/package.json",
"ecosystem": "npm",
"version_constraint": "^8.2.0"
},
{
"name": "boxen",
"manifest": "apps/cli/package.json",
"ecosystem": "npm",
"version_constraint": "^8.0.1"
},
{
"name": "elysia",
"manifest": "apps/cortex/package.json",
"ecosystem": "npm",
"version_constraint": "^1.1.0"
},
{
"name": "effect",
"manifest": "apps/cortex/package.json",
"ecosystem": "npm",
"version_constraint": "^3.10.0"
},
{
"name": "@reactive-agents/core",
"manifest": "apps/cortex/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "@reactive-agents/memory",
"manifest": "apps/cortex/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "@reactive-agents/runtime",
"manifest": "apps/cortex/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "@reactive-agents/observability",
"manifest": "apps/cortex/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "@reactive-agents/gateway",
"manifest": "apps/cortex/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "@reactive-agents/llm-provider",
"manifest": "apps/cortex/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "@reactive-agents/tools",
"manifest": "apps/cortex/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "@reactive-agents/reactive-intelligence",
"manifest": "apps/cortex/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "@reactive-agents/core",
"manifest": "packages/a2a/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "@reactive-agents/runtime-shim",
"manifest": "packages/a2a/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "@reactive-agents/core",
"manifest": "packages/channels/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "@reactive-agents/gateway",
"manifest": "packages/channels/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "effect",
"manifest": "packages/channels/package.json",
"ecosystem": "npm",
"version_constraint": "^3.10.0"
},
{
"name": "@reactive-agents/core",
"manifest": "packages/compose/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "effect",
"manifest": "packages/core/package.json",
"ecosystem": "npm",
"version_constraint": "^3.10.0"
},
{
"name": "ulid",
"manifest": "packages/core/package.json",
"ecosystem": "npm",
"version_constraint": "^2.3.0"
},
{
"name": "@reactive-agents/core",
"manifest": "packages/cost/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "@reactive-agents/llm-provider",
"manifest": "packages/cost/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "@reactive-agents/memory",
"manifest": "packages/cost/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "@reactive-agents/runtime-shim",
"manifest": "packages/cost/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "@reactive-agents/trace",
"manifest": "packages/diagnose/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "@reactive-agents/replay",
"manifest": "packages/diagnose/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "@reactive-agents/core",
"manifest": "packages/eval/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "@reactive-agents/llm-provider",
"manifest": "packages/eval/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "@reactive-agents/runtime-shim",
"manifest": "packages/eval/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "@reactive-agents/core",
"manifest": "packages/gateway/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "@reactive-agents/core",
"manifest": "packages/guardrails/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "@reactive-agents/llm-provider",
"manifest": "packages/guardrails/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "@reactive-agents/runtime-shim",
"manifest": "packages/health/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "@reactive-agents/core",
"manifest": "packages/identity/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "@noble/ed25519",
"manifest": "packages/identity/package.json",
"ecosystem": "npm",
"version_constraint": "^2.0.0"
},
{
"name": "@reactive-agents/core",
"manifest": "packages/interaction/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "@reactive-agents/reasoning",
"manifest": "packages/interaction/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "@reactive-agents/observability",
"manifest": "packages/interaction/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "ulid",
"manifest": "packages/interaction/package.json",
"ecosystem": "npm",
"version_constraint": "^2.3.0"
},
{
"name": "@reactive-agents/core",
"manifest": "packages/judge-server/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "@reactive-agents/eval",
"manifest": "packages/judge-server/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "@reactive-agents/llm-provider",
"manifest": "packages/judge-server/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "@reactive-agents/runtime-shim",
"manifest": "packages/judge-server/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "effect",
"manifest": "packages/judge-server/package.json",
"ecosystem": "npm",
"version_constraint": "*"
},
{
"name": "@reactive-agents/core",
"manifest": "packages/llm-provider/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "@reactive-agents/memory",
"manifest": "packages/llm-provider/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "@reactive-agents/runtime-shim",
"manifest": "packages/llm-provider/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "@reactive-agents/core",
"manifest": "packages/memory/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "@reactive-agents/runtime-shim",
"manifest": "packages/memory/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "@opentelemetry/api",
"manifest": "packages/observability/package.json",
"ecosystem": "npm",
"version_constraint": "^1.9.0"
},
{
"name": "@opentelemetry/exporter-metrics-otlp-http",
"manifest": "packages/observability/package.json",
"ecosystem": "npm",
"version_constraint": "^0.213.0"
},
{
"name": "@opentelemetry/exporter-trace-otlp-http",
"manifest": "packages/observability/package.json",
"ecosystem": "npm",
"version_constraint": "^0.213.0"
},
{
"name": "@opentelemetry/resources",
"manifest": "packages/observability/package.json",
"ecosystem": "npm",
"version_constraint": "^2.6.0"
},
{
"name": "@opentelemetry/sdk-metrics",
"manifest": "packages/observability/package.json",
"ecosystem": "npm",
"version_constraint": "^2.6.0"
},
{
"name": "@opentelemetry/sdk-trace-base",
"manifest": "packages/observability/package.json",
"ecosystem": "npm",
"version_constraint": "^2.6.0"
},
{
"name": "@opentelemetry/semantic-conventions",
"manifest": "packages/observability/package.json",
"ecosystem": "npm",
"version_constraint": "^1.40.0"
},
{
"name": "@reactive-agents/core",
"manifest": "packages/observability/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "chalk",
"manifest": "packages/observability/package.json",
"ecosystem": "npm",
"version_constraint": "^5.4.0"
},
{
"name": "boxen",
"manifest": "packages/observability/package.json",
"ecosystem": "npm",
"version_constraint": "^8.0.1"
}
],
"all_dependencies": {
"error": "GitHub dependency-graph SBOM unavailable (404); the dependency graph may be disabled for this repository",
"source": null,
"packages": [],
"collected": false,
"truncated": false,
"total_count": null,
"direct_count": null,
"indirect_count": null
}
},
"maintainership": {
"issues": {
"open_prs": 0,
"merged_prs": 55,
"open_issues": 32,
"closed_ratio": 0.717,
"closed_issues": 81,
"closed_unmerged_prs": 26
},
"bus_factor": 1,
"bot_contributors": 1,
"top_contributors": [
{
"type": "User",
"login": "tylerjrbuell",
"commits": 3394,
"avatar_url": "https://avatars.githubusercontent.com/u/89788783?v=4"
},
{
"type": "User",
"login": "HarperZ9",
"commits": 2,
"avatar_url": "https://avatars.githubusercontent.com/u/17142659?v=4"
}
],
"contributors_sampled": 2,
"top_contributor_share": 0.999
},
"quality_signals": {
"has_ci": true,
"has_tests": true,
"ci_workflows": [
"backfill-releases.yml",
"ci.yml",
"docs.yml",
"eval.yml",
"publish.yml",
"regression-gate.yml"
],
"has_docs_dir": true,
"linter_configs": [
"eslint.config.mjs"
],
"has_editorconfig": false,
"has_linter_config": true,
"has_precommit_config": false
},
"security_signals": {
"lockfiles": [],
"scorecard": {
"checks": [
{
"name": "Binary-Artifacts",
"score": 10,
"reason": "no binaries found in the repo",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#binary-artifacts"
},
{
"name": "Branch-Protection",
"score": 3,
"reason": "branch protection is not maximal on development and all release branches",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#branch-protection"
},
{
"name": "CI-Tests",
"score": 10,
"reason": "1 out of 1 merged PRs checked by a CI test -- score normalized to 10",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#ci-tests"
},
{
"name": "CII-Best-Practices",
"score": 0,
"reason": "no effort to earn an OpenSSF best practices badge detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#cii-best-practices"
},
{
"name": "Code-Review",
"score": 0,
"reason": "Found 1/30 approved changesets -- score normalized to 0",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#code-review"
},
{
"name": "Contributors",
"score": 3,
"reason": "project has 1 contributing companies or organizations -- score normalized to 3",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#contributors"
},
{
"name": "Dangerous-Workflow",
"score": 10,
"reason": "no dangerous workflow patterns detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#dangerous-workflow"
},
{
"name": "Dependency-Update-Tool",
"score": 0,
"reason": "no update tool detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#dependency-update-tool"
},
{
"name": "Fuzzing",
"score": 10,
"reason": "project is fuzzed",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#fuzzing"
},
{
"name": "License",
"score": 10,
"reason": "license file detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#license"
},
{
"name": "Maintained",
"score": 10,
"reason": "30 commit(s) and 30 issue activity found in the last 90 days -- score normalized to 10",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#maintained"
},
{
"name": "Packaging",
"score": null,
"reason": "packaging workflow not detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#packaging"
},
{
"name": "Pinned-Dependencies",
"score": 0,
"reason": "dependency not pinned by hash detected -- score normalized to 0",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#pinned-dependencies"
},
{
"name": "SAST",
"score": 0,
"reason": "SAST tool is not run on all commits -- score normalized to 0",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#sast"
},
{
"name": "Security-Policy",
"score": 10,
"reason": "security policy file detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#security-policy"
},
{
"name": "Signed-Releases",
"score": null,
"reason": "no releases found",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#signed-releases"
},
{
"name": "Token-Permissions",
"score": 0,
"reason": "detected GitHub workflow tokens with excessive permissions",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#token-permissions"
},
{
"name": "Vulnerabilities",
"score": 0,
"reason": "162 existing vulnerabilities detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#vulnerabilities"
}
],
"commit": "45cbacdb3acf81c05c706b2cefa5f732b1584175",
"ran_at": "2026-07-30T20:59:33Z",
"aggregate_score": 4.6,
"scorecard_version": "v5.5.0"
},
"has_codeql_workflow": false,
"has_security_policy": true,
"has_dependabot_config": false
},
"contribution_flow": {
"collected": true,
"ci_last_run_at": "2026-07-22T22:11:00Z",
"oldest_open_prs": [],
"last_merged_pr_at": "2026-07-22T22:06:34Z",
"ci_last_conclusion": "SUCCESS",
"oldest_open_issues": [
{
"number": 30,
"created_at": "2026-05-15T01:57:42Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 31,
"created_at": "2026-05-15T01:57:44Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 32,
"created_at": "2026-05-15T01:57:45Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 33,
"created_at": "2026-05-15T01:57:46Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 34,
"created_at": "2026-05-15T01:57:47Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 35,
"created_at": "2026-05-15T01:57:48Z",
"last_comment_at": "2026-06-16T17:57:16Z",
"last_comment_author": "tylerjrbuell"
},
{
"number": 36,
"created_at": "2026-05-15T01:57:50Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 37,
"created_at": "2026-05-15T01:57:51Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 38,
"created_at": "2026-05-15T01:57:52Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 42,
"created_at": "2026-05-15T01:57:57Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 43,
"created_at": "2026-05-15T01:57:58Z",
"last_comment_at": "2026-06-16T17:57:16Z",
"last_comment_author": "tylerjrbuell"
},
{
"number": 44,
"created_at": "2026-05-15T01:58:00Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 45,
"created_at": "2026-05-15T01:58:01Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 47,
"created_at": "2026-05-15T01:58:03Z",
"last_comment_at": "2026-06-16T17:57:15Z",
"last_comment_author": "tylerjrbuell"
},
{
"number": 48,
"created_at": "2026-05-15T01:58:04Z",
"last_comment_at": "2026-06-11T00:45:23Z",
"last_comment_author": "tylerjrbuell"
},
{
"number": 49,
"created_at": "2026-05-15T01:58:05Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 50,
"created_at": "2026-05-15T01:58:06Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 51,
"created_at": "2026-05-15T01:58:08Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 52,
"created_at": "2026-05-15T01:58:10Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 53,
"created_at": "2026-05-15T01:58:11Z",
"last_comment_at": null,
"last_comment_author": null
}
]
}
},
"config": {
"disabled_metrics": [],
"disabled_categories": [],
"disabled_components": {}
},
"source": {
"url": "https://github.com/tylerjrbuell/reactive-agents-ts",
"host": "github.com",
"name": "reactive-agents-ts",
"owner": "tylerjrbuell"
},
"metrics": {
"overall": {
"key": "overall",
"band": "good",
"name": "Overall health",
"note": "The weighted overall 67 is calibrated to 78 on the published index scale (record calibration 2026-08-02).",
"notes": [
{
"code": "overall_calibration",
"params": {
"raw": 67,
"calibrated": 78,
"calibration": "2026-08-02"
}
}
],
"value": 78,
"inputs": {
"security": 55,
"vitality": 87,
"community": 53,
"governance": 49,
"calibration": "2026-08-02",
"engineering": 86,
"ai_readiness": 71,
"weighted_overall_raw": 67
},
"components": []
},
"categories": [
{
"key": "vitality",
"band": "excellent",
"name": "Vitality",
"value": 87,
"weight": 0.21,
"metrics": [
{
"key": "development_activity",
"band": "good",
"name": "Development activity",
"note": null,
"notes": [],
"value": 78,
"inputs": {
"commits_last_year": 3410,
"human_commit_share": 0.99,
"days_since_last_push": 7,
"active_weeks_last_year": 21
},
"components": [
{
"key": "push_recency",
"name": "Push recency",
"detail": "last push 7 days ago",
"points": 36,
"status": "met",
"details": [
{
"code": "push_recency",
"params": {
"days": 7
}
}
],
"max_points": 36
},
{
"key": "commit_cadence",
"name": "Commit cadence",
"detail": "21/52 weeks with commits",
"points": 14.5,
"status": "partial",
"details": [
{
"code": "commit_cadence_weeks",
"params": {
"weeks": 21
}
}
],
"max_points": 36
},
{
"key": "commit_volume",
"name": "Commit volume",
"detail": "3410 commits in the last year",
"points": 18,
"status": "met",
"details": [
{
"code": "commits_last_year",
"params": {
"count": 3410
}
}
],
"max_points": 18
},
{
"key": "openssf_scorecard_maintained",
"name": "OpenSSF Scorecard: Maintained",
"detail": "30 commit(s) and 30 issue activity found in the last 90 days -- score normalized to 10",
"points": 10,
"status": "met",
"details": [],
"max_points": 10
}
]
},
{
"key": "release_discipline",
"band": "exceptional",
"name": "Release discipline",
"note": "Excluded from scoring (no data or not applicable): OpenSSF Scorecard: Signed-Releases. Remaining weights renormalized.",
"notes": [
{
"code": "excluded_no_data",
"params": {
"components": [
"openssf_scorecard_signed_releases"
]
}
},
{
"code": "weights_renormalized",
"params": {}
}
],
"value": 100,
"inputs": {
"releases_count": 35,
"latest_release_tag": "v0.14.0",
"releases_from_tags": false,
"days_since_latest_release": 8,
"mean_days_between_releases": 8.6
},
"components": [
{
"key": "ships_releases",
"name": "Ships releases",
"detail": "35 releases published",
"points": 27,
"status": "met",
"details": [
{
"code": "releases_published",
"params": {
"count": 35
}
}
],
"max_points": 27
},
{
"key": "release_recency",
"name": "Release recency",
"detail": "latest release 8 days ago",
"points": 36,
"status": "met",
"details": [
{
"code": "release_recency",
"params": {
"days": 8
}
}
],
"max_points": 36
},
{
"key": "release_cadence",
"name": "Release cadence",
"detail": "a release every ~8.6 days",
"points": 27,
"status": "met",
"details": [
{
"code": "release_cadence",
"params": {
"gap": 8.6
}
}
],
"max_points": 27
},
{
"key": "openssf_scorecard_signed_releases",
"name": "OpenSSF Scorecard: Signed-Releases",
"detail": "no releases found",
"points": 0,
"status": "excluded",
"details": [
{
"code": "no_data",
"params": {}
}
],
"max_points": 10
}
]
},
{
"key": "abandonment",
"band": "exceptional",
"name": "Abandonment",
"note": null,
"notes": [],
"value": 100,
"inputs": {
"cap": null,
"state": "unverified",
"guards": [],
"signals": [],
"red_flag": false,
"multiplier_pct": 100,
"declared_reason": null,
"unverified_reason": "repository_too_young",
"unanswered_open_prs": null,
"unanswered_open_issues": null,
"days_since_last_merged_pr": null,
"days_since_last_human_commit": null,
"days_since_last_human_commit_is_floor": false
},
"components": [
{
"key": "project_is_still_maintained",
"name": "Project is still maintained",
"detail": "maintenance record not established from the collected data",
"points": 100,
"status": "met",
"details": [
{
"code": "abandonment_unverified",
"params": {}
}
],
"max_points": 100
}
]
}
],
"description": "Is the project alive — is code being written and are releases shipping?"
},
{
"key": "community",
"band": "moderate",
"name": "Community & Adoption",
"value": 53,
"weight": 0.17,
"metrics": [
{
"key": "popularity",
"band": "at_risk",
"name": "Popularity & adoption",
"note": null,
"notes": [],
"value": 24,
"inputs": {
"forks": 4,
"stars": 19,
"watchers": 0,
"growth_state": "unverified",
"growth_factor_pct": 100,
"growth_unverified_reason": "no_history"
},
"components": [
{
"key": "stars",
"name": "Stars",
"detail": "19 stars",
"points": 20.4,
"status": "partial",
"details": [
{
"code": "stars",
"params": {
"count": 19
}
}
],
"max_points": 60
},
{
"key": "forks",
"name": "Forks",
"detail": "4 forks",
"points": 4,
"status": "partial",
"details": [
{
"code": "forks",
"params": {
"count": 4
}
}
],
"max_points": 25
},
{
"key": "watchers",
"name": "Watchers",
"detail": "0 watchers",
"points": 0,
"status": "missed",
"details": [
{
"code": "watchers",
"params": {
"count": 0
}
}
],
"max_points": 15
}
]
},
{
"key": "community_health",
"band": "good",
"name": "Community health",
"note": null,
"notes": [],
"value": 77,
"inputs": {
"has_readme": true,
"has_license": true,
"readme_badges": null,
"has_contributing": true,
"has_issue_template": false,
"has_code_of_conduct": false,
"readme_badge_services": [],
"has_pull_request_template": true
},
"components": [
{
"key": "readme",
"name": "README",
"detail": null,
"points": 22.5,
"status": "met",
"details": [],
"max_points": 22.5
},
{
"key": "license",
"name": "License",
"detail": "recognized license (MIT)",
"points": 22.5,
"status": "met",
"details": [
{
"code": "license_standard",
"params": {}
},
{
"code": "license_spdx",
"params": {
"spdx": "MIT"
}
}
],
"max_points": 22.5
},
{
"key": "contributing_guide",
"name": "CONTRIBUTING guide",
"detail": null,
"points": 18,
"status": "met",
"details": [],
"max_points": 18
},
{
"key": "code_of_conduct",
"name": "Code of conduct",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 13.5
},
{
"key": "issue_template",
"name": "Issue template",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.2
},
{
"key": "pr_template",
"name": "PR template",
"detail": null,
"points": 6.3,
"status": "met",
"details": [],
"max_points": 6.3
}
]
},
{
"key": "ecosystem_adoption",
"band": "good",
"name": "Ecosystem adoption (downloads)",
"note": "Excluded from scoring (no data or not applicable): Registry dependents. Remaining weights renormalized.",
"notes": [
{
"code": "excluded_no_data",
"params": {
"components": [
"registry_dependents"
]
}
},
{
"code": "weights_renormalized",
"params": {}
}
],
"value": 67,
"inputs": {
"packages": [
"@reactive-agents/cli",
"@reactive-agents/cortex",
"@reactive-agents/a2a",
"@reactive-agents/core",
"@reactive-agents/cost",
"@reactive-agents/eval",
"@reactive-agents/health",
"@reactive-agents/memory"
],
"dependents": null,
"ecosystems": "npm",
"total_downloads": null,
"monthly_downloads": 11005
},
"components": [
{
"key": "monthly_downloads",
"name": "Monthly downloads",
"detail": "11,005 downloads/month across npm",
"points": 53.9,
"status": "partial",
"details": [
{
"code": "downloads_monthly",
"params": {
"count": 11005,
"ecosystems": "npm"
}
}
],
"max_points": 80
},
{
"key": "registry_dependents",
"name": "Registry dependents",
"detail": "not reported by this ecosystem",
"points": 0,
"status": "excluded",
"details": [
{
"code": "not_reported_by_this_ecosystem",
"params": {}
}
],
"max_points": 20
}
]
}
],
"description": "Does the project have users, downloads, attention, and a welcoming setup for contributors?"
},
{
"key": "governance",
"band": "weak",
"name": "Sustainability & Governance",
"value": 49,
"weight": 0.23,
"metrics": [
{
"key": "maintainer_resilience",
"band": "critical",
"name": "Maintainer resilience (bus factor)",
"note": null,
"notes": [],
"value": 15,
"inputs": {
"bus_factor": 1,
"contributors_sampled": 2,
"top_contributor_share": 0.999
},
"components": [
{
"key": "bus_factor",
"name": "Bus factor",
"detail": "1 contributor(s) cover half of all commits",
"points": 9,
"status": "partial",
"details": [
{
"code": "bus_factor",
"params": {
"count": 1
}
}
],
"max_points": 54
},
{
"key": "commit_distribution",
"name": "Commit distribution",
"detail": "top contributor authored 100% of commits",
"points": 0,
"status": "partial",
"details": [
{
"code": "top_contributor_share",
"params": {
"share": 100
}
}
],
"max_points": 22.5
},
{
"key": "contributor_breadth",
"name": "Contributor breadth",
"detail": "2 contributors",
"points": 2.7,
"status": "partial",
"details": [
{
"code": "contributors_sampled",
"params": {
"count": 2
}
}
],
"max_points": 13.5
},
{
"key": "openssf_scorecard_contributors",
"name": "OpenSSF Scorecard: Contributors",
"detail": "project has 1 contributing companies or organizations -- score normalized to 3",
"points": 3,
"status": "partial",
"details": [],
"max_points": 10
}
]
},
{
"key": "responsiveness",
"band": "moderate",
"name": "Issue & PR responsiveness",
"note": "Excluded from scoring (no data or not applicable): Newcomer PR acceptance. Remaining weights renormalized.",
"notes": [
{
"code": "excluded_no_data",
"params": {
"components": [
"newcomer_pr_acceptance"
]
}
},
{
"code": "weights_renormalized",
"params": {}
}
],
"value": 58,
"inputs": {
"merged_prs": 55,
"open_issues": 32,
"closed_issues": 81,
"prs_merged_7d": null,
"prs_decided_7d": null,
"prs_merged_30d": null,
"prs_decided_30d": null,
"issue_closed_ratio": 0.717,
"closed_unmerged_prs": 26,
"first_time_authors_30d": null,
"first_time_prs_merged_30d": null,
"first_time_prs_decided_30d": null
},
"components": [
{
"key": "issue_resolution",
"name": "Issue resolution",
"detail": "72% of issues closed",
"points": 30.1,
"status": "partial",
"details": [
{
"code": "issues_closed_share",
"params": {
"share": 72
}
}
],
"max_points": 42
},
{
"key": "pr_acceptance",
"name": "PR acceptance",
"detail": "55/81 decided PRs merged",
"points": 20.4,
"status": "partial",
"details": [
{
"code": "decided_prs_merged",
"params": {
"merged": 55,
"decided": 81
}
}
],
"max_points": 30
},
{
"key": "newcomer_pr_acceptance",
"name": "Newcomer PR acceptance",
"detail": "no first-time contributor's PR decided in 30d",
"points": 0,
"status": "excluded",
"details": [
{
"code": "no_newcomer_prs",
"params": {
"days": 30
}
}
],
"max_points": 13
},
{
"key": "openssf_scorecard_code_review",
"name": "OpenSSF Scorecard: Code-Review",
"detail": "Found 1/30 approved changesets -- score normalized to 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 15
}
]
},
{
"key": "stewardship",
"band": "weak",
"name": "Ownership & stewardship",
"note": "Excluded from scoring (no data or not applicable): Verified domain. Remaining weights renormalized.",
"notes": [
{
"code": "excluded_no_data",
"params": {
"components": [
"verified_domain"
]
}
},
{
"code": "weights_renormalized",
"params": {}
}
],
"value": 40,
"inputs": {
"followers": 3,
"owner_type": "User",
"is_verified": null,
"owner_login": "tylerjrbuell",
"public_repos": 12,
"account_age_days": 1795
},
"components": [
{
"key": "ownership_backing",
"name": "Ownership backing",
"detail": "personal (user) account",
"points": 10,
"status": "partial",
"details": [
{
"code": "owner_personal",
"params": {}
}
],
"max_points": 30
},
{
"key": "verified_domain",
"name": "Verified domain",
"detail": "not applicable to user accounts",
"points": 0,
"status": "excluded",
"details": [
{
"code": "not_applicable_to_user_accounts",
"params": {}
}
],
"max_points": 20
},
{
"key": "owner_reach",
"name": "Owner reach",
"detail": "3 followers of tylerjrbuell",
"points": 4.3,
"status": "partial",
"details": [
{
"code": "owner_followers",
"params": {
"count": 3,
"login": "tylerjrbuell"
}
}
],
"max_points": 25
},
{
"key": "track_record",
"name": "Track record",
"detail": "12 public repos, account ~4 yr old",
"points": 17.9,
"status": "partial",
"details": [
{
"code": "public_repos",
"params": {
"count": 12
}
},
{
"code": "account_age_years",
"params": {
"years": 4
}
}
],
"max_points": 25
}
]
},
{
"key": "package_maintenance",
"band": "exceptional",
"name": "Package maintenance",
"note": null,
"notes": [],
"value": 100,
"inputs": {
"packages": [
"@reactive-agents/cli",
"@reactive-agents/cortex",
"@reactive-agents/a2a",
"@reactive-agents/core",
"@reactive-agents/cost",
"@reactive-agents/eval",
"@reactive-agents/health",
"@reactive-agents/memory"
],
"ecosystems": "npm",
"any_deprecated": false,
"min_days_since_publish": 8
},
"components": [
{
"key": "published_resolvable",
"name": "Published & resolvable",
"detail": "8 package(s) on npm",
"points": 25,
"status": "met",
"details": [
{
"code": "packages_published",
"params": {
"count": 8,
"ecosystems": "npm"
}
}
],
"max_points": 25
},
{
"key": "publish_recency",
"name": "Publish recency",
"detail": "latest publish 8 days ago",
"points": 35,
"status": "met",
"details": [
{
"code": "publish_recency",
"params": {
"days": 8
}
}
],
"max_points": 35
},
{
"key": "version_history",
"name": "Version history",
"detail": "42 published versions",
"points": 20,
"status": "met",
"details": [
{
"code": "published_versions",
"params": {
"count": 42
}
}
],
"max_points": 20
},
{
"key": "not_deprecated",
"name": "Not deprecated",
"detail": "active, not deprecated or yanked",
"points": 20,
"status": "met",
"details": [
{
"code": "package_not_deprecated",
"params": {}
}
],
"max_points": 20
}
]
}
],
"description": "Will the project survive its people — bus factor, responsiveness, who backs it, and package upkeep?"
},
{
"key": "engineering",
"band": "excellent",
"name": "Engineering Quality",
"value": 86,
"weight": 0.19,
"metrics": [
{
"key": "engineering_practices",
"band": "excellent",
"name": "Engineering practices",
"note": null,
"notes": [],
"value": 84,
"inputs": {
"has_ci": true,
"has_tests": true,
"has_editorconfig": false,
"has_linter_config": true,
"has_precommit_config": false
},
"components": [
{
"key": "ci_workflows",
"name": "CI workflows",
"detail": "6 workflow(s)",
"points": 24,
"status": "met",
"details": [
{
"code": "ci_workflows",
"params": {
"count": 6
}
}
],
"max_points": 24
},
{
"key": "tests_present",
"name": "Tests present",
"detail": null,
"points": 24,
"status": "met",
"details": [],
"max_points": 24
},
{
"key": "linter_config",
"name": "Linter config",
"detail": "eslint.config.mjs",
"points": 16,
"status": "met",
"details": [
{
"code": "file_list",
"params": {
"files": "eslint.config.mjs"
}
}
],
"max_points": 16
},
{
"key": "pre_commit_hooks",
"name": "Pre-commit hooks",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 9.6
},
{
"key": "editorconfig",
"name": ".editorconfig",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 6.4
},
{
"key": "openssf_scorecard_ci_tests",
"name": "OpenSSF Scorecard: CI-Tests",
"detail": "1 out of 1 merged PRs checked by a CI test -- score normalized to 10",
"points": 20,
"status": "met",
"details": [],
"max_points": 20
}
]
},
{
"key": "documentation",
"band": "excellent",
"name": "Documentation",
"note": null,
"notes": [],
"value": 90,
"inputs": {
"topics": [
"agent-framework",
"agent-observability",
"agent-orchestration",
"agentic-ai",
"anthropic",
"bun",
"composable",
"effect-ts",
"google-ai",
"llm",
"multi-agent",
"ollama",
"openai",
"type-safe",
"typescript",
"automation",
"ai-agents",
"gateway",
"mcp",
"streaming"
],
"has_wiki": false,
"homepage": "https://docs.reactiveagents.dev",
"has_readme": true,
"has_docs_dir": true,
"has_description": true
},
"components": [
{
"key": "readme",
"name": "README",
"detail": null,
"points": 30,
"status": "met",
"details": [],
"max_points": 30
},
{
"key": "documentation_directory",
"name": "Documentation directory",
"detail": null,
"points": 25,
"status": "met",
"details": [],
"max_points": 25
},
{
"key": "documentation_homepage_site",
"name": "Documentation / homepage site",
"detail": "https://docs.reactiveagents.dev",
"points": 15,
"status": "met",
"details": [],
"max_points": 15
},
{
"key": "repository_description",
"name": "Repository description",
"detail": null,
"points": 10,
"status": "met",
"details": [],
"max_points": 10
},
{
"key": "topics",
"name": "Topics",
"detail": "20 topics",
"points": 10,
"status": "met",
"details": [
{
"code": "topics_count",
"params": {
"count": 20
}
}
],
"max_points": 10
},
{
"key": "wiki",
"name": "Wiki",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 10
}
]
}
],
"description": "Are baseline engineering and documentation practices in place?"
},
{
"key": "security",
"band": "moderate",
"name": "Security",
"value": 55,
"weight": 0.16,
"metrics": [
{
"key": "security_posture",
"band": "weak",
"name": "Security posture",
"note": "Excluded from scoring (no data or not applicable): Packaging, Signed-Releases. Remaining weights renormalized.",
"notes": [
{
"code": "excluded_no_data",
"params": {
"components": [
"packaging",
"signed_releases"
]
}
},
{
"code": "weights_renormalized",
"params": {}
}
],
"value": 46,
"inputs": {
"source": "openssf_scorecard",
"checks_evaluated": 16,
"scorecard_version": "v5.5.0",
"checks_inconclusive": 2,
"scorecard_aggregate": 4.6
},
"components": [
{
"key": "binary_artifacts",
"name": "Binary-Artifacts",
"detail": "no binaries found in the repo",
"points": 7.5,
"status": "met",
"details": [],
"max_points": 7.5
},
{
"key": "branch_protection",
"name": "Branch-Protection",
"detail": "branch protection is not maximal on development and all release branches",
"points": 2.2,
"status": "partial",
"details": [],
"max_points": 7.5
},
{
"key": "ci_tests",
"name": "CI-Tests",
"detail": "1 out of 1 merged PRs checked by a CI test -- score normalized to 10",
"points": 2.5,
"status": "met",
"details": [],
"max_points": 2.5
},
{
"key": "cii_best_practices",
"name": "CII-Best-Practices",
"detail": "no effort to earn an OpenSSF best practices badge detected",
"points": 0,
"status": "missed",
"details": [],
"max_points": 2.5
},
{
"key": "code_review",
"name": "Code-Review",
"detail": "Found 1/30 approved changesets -- score normalized to 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.5
},
{
"key": "contributors",
"name": "Contributors",
"detail": "project has 1 contributing companies or organizations -- score normalized to 3",
"points": 0.8,
"status": "partial",
"details": [],
"max_points": 2.5
},
{
"key": "dangerous_workflow",
"name": "Dangerous-Workflow",
"detail": "no dangerous workflow patterns detected",
"points": 10,
"status": "met",
"details": [],
"max_points": 10
},
{
"key": "dependency_update_tool",
"name": "Dependency-Update-Tool",
"detail": "no update tool detected",
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.5
},
{
"key": "fuzzing",
"name": "Fuzzing",
"detail": "project is fuzzed",
"points": 5,
"status": "met",
"details": [],
"max_points": 5
},
{
"key": "license",
"name": "License",
"detail": "license file detected",
"points": 2.5,
"status": "met",
"details": [],
"max_points": 2.5
},
{
"key": "maintained",
"name": "Maintained",
"detail": "30 commit(s) and 30 issue activity found in the last 90 days -- score normalized to 10",
"points": 7.5,
"status": "met",
"details": [],
"max_points": 7.5
},
{
"key": "packaging",
"name": "Packaging",
"detail": "packaging workflow not detected",
"points": 0,
"status": "excluded",
"details": [
{
"code": "no_data",
"params": {}
}
],
"max_points": 5
},
{
"key": "pinned_dependencies",
"name": "Pinned-Dependencies",
"detail": "dependency not pinned by hash detected -- score normalized to 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 5
},
{
"key": "sast",
"name": "SAST",
"detail": "SAST tool is not run on all commits -- score normalized to 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 5
},
{
"key": "security_policy",
"name": "Security-Policy",
"detail": "security policy file detected",
"points": 5,
"status": "met",
"details": [],
"max_points": 5
},
{
"key": "signed_releases",
"name": "Signed-Releases",
"detail": "no releases found",
"points": 0,
"status": "excluded",
"details": [
{
"code": "no_data",
"params": {}
}
],
"max_points": 7.5
},
{
"key": "token_permissions",
"name": "Token-Permissions",
"detail": "detected GitHub workflow tokens with excessive permissions",
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.5
},
{
"key": "vulnerabilities",
"name": "Vulnerabilities",
"detail": "162 existing vulnerabilities detected",
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.5
}
]
},
{
"key": "dependency_advisories",
"band": "excellent",
"name": "Dependency advisories",
"note": "Matched the npm:@reactive-agents/cli@0.14.0 runtime dependency closure — what installing the published package pulls in — 233 packages. Reachability is not analyzed.",
"notes": [
{
"code": "advisories_scope_published",
"params": {
"package": "npm:@reactive-agents/cli@0.14.0",
"assessed": 233
}
},
{
"code": "advisories_reachability",
"params": {}
}
],
"value": 89,
"inputs": {
"source": "osv",
"advisories": 1,
"affected_packages": 1,
"assessed_packages": 233,
"unassessed_packages": 0,
"affected_by_severity": "moderate 1",
"direct_affected_packages": 0
},
"components": [
{
"key": "direct_dependencies_free_of_known_advisories",
"name": "Direct dependencies free of known advisories",
"detail": "no direct dependency carries a known advisory",
"points": 35,
"status": "met",
"details": [
{
"code": "no_direct_advisories",
"params": {}
}
],
"max_points": 35
},
{
"key": "indirect_dependencies_free_of_known_advisories",
"name": "Indirect dependencies free of known advisories",
"detail": "1 affected: @opentelemetry/core 2.6.0 (moderate 5.3)",
"points": 14.4,
"status": "partial",
"details": [
{
"code": "advisories_affected",
"params": {
"count": 1,
"packages": "@opentelemetry/core 2.6.0 (moderate 5.3)"
}
}
],
"max_points": 25
},
{
"key": "no_advisories_left_outstanding",
"name": "No advisories left outstanding",
"detail": "no advisory has been public longer than 90 days",
"points": 40,
"status": "met",
"details": [
{
"code": "advisories_none_stale",
"params": {
"days": 90
}
}
],
"max_points": 40
}
]
},
{
"key": "malicious_dependencies",
"band": "exceptional",
"name": "Malicious dependencies",
"note": null,
"notes": [],
"value": 100,
"inputs": {
"source": "osv",
"meaning": "reported as a malicious package by the OpenSSF corpus; the remedy is removal or moving off the compromised name, never an upgrade of the same artifact. Versions the registry has since pulled are listed but not scored",
"packages": [],
"red_flag": false,
"assessed_packages": 233,
"malicious_packages": 0,
"direct_malicious_packages": 0,
"withdrawn_malicious_packages": 0,
"installable_malicious_packages": 0
},
"components": [
{
"key": "no_dependency_reported_as_a_malicious_package",
"name": "No dependency reported as a malicious package",
"detail": "no dependency is reported as a malicious package",
"points": 100,
"status": "met",
"details": [
{
"code": "no_malicious_dependencies",
"params": {}
}
],
"max_points": 100
}
]
},
{
"key": "high_risk_jurisdiction_exposure",
"band": "exceptional",
"name": "High-Risk Jurisdiction Exposure",
"note": "Only high-confidence self-published location evidence affects this multiplier. Ambiguous matches are review-only; country evidence is not proof of nationality, citizenship, legal registration, malicious intent, or sanctions status.",
"notes": [
{
"code": "jurisdiction_evidence_limits",
"params": {}
}
],
"value": 100,
"inputs": {
"meaning": "self-published location evidence; not nationality or citizenship",
"red_flag": false,
"exposures": [],
"policy_countries": [
"Russia",
"Iran",
"North Korea"
],
"commit_weight_rule": {
"min_commits": 50,
"min_commit_share": 0.1
},
"review_only_matches": 0,
"below_threshold_exposures": [],
"assessed_self_published_locations": 3
},
"components": [
{
"key": "policy_exposure_multiplier",
"name": "Policy exposure multiplier",
"detail": "no confirmed policy-scope location match",
"points": 100,
"status": "met",
"details": [
{
"code": "jurisdiction_no_match",
"params": {}
}
],
"max_points": 100
}
]
}
],
"description": "Are visible security and supply-chain practices strong, with no malicious dependency and no unresolved high-risk jurisdiction exposure?"
},
{
"key": "ai_readiness",
"band": "good",
"name": "AI Readiness",
"value": 71,
"weight": 0.04,
"metrics": [
{
"key": "ai_agent_context",
"band": "excellent",
"name": "Agent context & guidance",
"note": null,
"notes": [],
"value": 85,
"inputs": {
"has_llms_txt": false,
"legible_history_share": 1,
"agent_instruction_files": [
".github/copilot-instructions.md",
"AGENTS.md",
"CLAUDE.md",
"apps/cortex/AGENTS.md"
],
"agent_instruction_max_bytes": 65593
},
"components": [
{
"key": "agent_instructions",
"name": "Agent instructions",
"detail": ".github/copilot-instructions.md, AGENTS.md, CLAUDE.md, apps/cortex/AGENTS.md",
"points": 45,
"status": "met",
"details": [
{
"code": "file_list",
"params": {
"files": ".github/copilot-instructions.md, AGENTS.md, CLAUDE.md, apps/cortex/AGENTS.md"
}
}
],
"max_points": 45
},
{
"key": "machine_readable_docs_llms_txt",
"name": "Machine-readable docs (llms.txt)",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 15
},
{
"key": "legible_commit_history",
"name": "Legible commit history",
"detail": "99 of 99 human commits state their intent (structured subject or explanatory body)",
"points": 40,
"status": "met",
"details": [
{
"code": "legible_history",
"params": {
"legible": 99,
"sampled": 99
}
}
],
"max_points": 40
}
]
},
{
"key": "ai_verify_loop",
"band": "moderate",
"name": "Verify loop (build / test / typecheck)",
"note": null,
"notes": [],
"value": 54,
"inputs": {
"has_nix": false,
"has_tests": true,
"lockfiles": [],
"has_dockerfile": true,
"typed_language": true,
"bootstrap_files": [],
"has_devcontainer": true,
"has_linter_config": true,
"typecheck_configs": [
"apps/advocate/tsconfig.json",
"apps/cli/tsconfig.json",
"apps/cortex/tsconfig.json",
"apps/cortex/ui/tsconfig.json",
"apps/docs/tsconfig.json",
"apps/examples/tsconfig.json",
"apps/stackblitz/01-hello-agent/tsconfig.json",
"apps/stackblitz/02-tool-integration/tsconfig.json",
"apps/stackblitz/03-strategy-demo/tsconfig.json",
"docker/signal-mcp/server/tsconfig.json",
"packages/a2a/tsconfig.json",
"packages/benchmarks/tsconfig.json",
"packages/channels/tsconfig.json",
"packages/compose/tsconfig.json",
"packages/core/tsconfig.json",
"packages/cost/tsconfig.json",
"packages/create-reactive-agent/tsconfig.json",
"packages/diagnose/tsconfig.json",
"packages/eval/tsconfig.json",
"packages/gateway/tsconfig.json",
"packages/guardrails/tsconfig.json",
"packages/health/tsconfig.json",
"packages/identity/tsconfig.json",
"packages/interaction/tsconfig.json",
"packages/judge-server/tsconfig.json",
"packages/llm-provider/tsconfig.json",
"packages/memory/tsconfig.json",
"packages/observability/tsconfig.json",
"packages/observe/tsconfig.json",
"packages/prompts/tsconfig.json",
"packages/react/tsconfig.json",
"packages/reactive-agents/tsconfig.json",
"packages/reactive-intelligence/tsconfig.json",
"packages/reasoning/tsconfig.json",
"packages/replay/tsconfig.json",
"packages/runtime-shim/tsconfig.json",
"packages/runtime/tsconfig.json",
"packages/svelte/tsconfig.json",
"packages/testing/tsconfig.json",
"packages/tools/tsconfig.json",
"packages/trace/tsconfig.json",
"packages/ui-core/tsconfig.json",
"packages/verification/tsconfig.json",
"packages/vue/tsconfig.json",
"tsconfig.json"
],
"agent_commit_share": 0,
"toolchain_manifests": [],
"dependency_bot_commit_share": 0
},
"components": [
{
"key": "one_command_bootstrap",
"name": "One-command bootstrap",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 18
},
{
"key": "automated_tests",
"name": "Automated tests",
"detail": null,
"points": 22,
"status": "met",
"details": [],
"max_points": 22
},
{
"key": "lint_format_config",
"name": "Lint / format config",
"detail": "eslint.config.mjs",
"points": 11,
"status": "met",
"details": [
{
"code": "file_list",
"params": {
"files": "eslint.config.mjs"
}
}
],
"max_points": 11
},
{
"key": "static_type_checking",
"name": "Static type checking",
"detail": "apps/advocate/tsconfig.json, apps/cli/tsconfig.json, apps/cortex/tsconfig.json, apps/cortex/ui/tsconfig.json, apps/docs/tsconfig.json, apps/examples/tsconfig.json, apps/stackblitz/01-hello-agent/tsconfig.json, apps/stackblitz/02-tool-integration/tsconfig.json, apps/stackblitz/03-strategy-demo/tsconfig.json, docker/signal-mcp/server/tsconfig.json, packages/a2a/tsconfig.json, packages/benchmarks/tsconfig.json, packages/channels/tsconfig.json, packages/compose/tsconfig.json, packages/core/tsconfig.json, packages/cost/tsconfig.json, packages/create-reactive-agent/tsconfig.json, packages/diagnose/tsconfig.json, packages/eval/tsconfig.json, packages/gateway/tsconfig.json, packages/guardrails/tsconfig.json, packages/health/tsconfig.json, packages/identity/tsconfig.json, packages/interaction/tsconfig.json, packages/judge-server/tsconfig.json, packages/llm-provider/tsconfig.json, packages/memory/tsconfig.json, packages/observability/tsconfig.json, packages/observe/tsconfig.json, packages/prompts/tsconfig.json, packages/react/tsconfig.json, packages/reactive-agents/tsconfig.json, packages/reactive-intelligence/tsconfig.json, packages/reasoning/tsconfig.json, packages/replay/tsconfig.json, packages/runtime-shim/tsconfig.json, packages/runtime/tsconfig.json, packages/svelte/tsconfig.json, packages/testing/tsconfig.json, packages/tools/tsconfig.json, packages/trace/tsconfig.json, packages/ui-core/tsconfig.json, packages/verification/tsconfig.json, packages/vue/tsconfig.json, tsconfig.json",
"points": 11,
"status": "met",
"details": [
{
"code": "file_list",
"params": {
"files": "apps/advocate/tsconfig.json, apps/cli/tsconfig.json, apps/cortex/tsconfig.json, apps/cortex/ui/tsconfig.json, apps/docs/tsconfig.json, apps/examples/tsconfig.json, apps/stackblitz/01-hello-agent/tsconfig.json, apps/stackblitz/02-tool-integration/tsconfig.json, apps/stackblitz/03-strategy-demo/tsconfig.json, docker/signal-mcp/server/tsconfig.json, packages/a2a/tsconfig.json, packages/benchmarks/tsconfig.json, packages/channels/tsconfig.json, packages/compose/tsconfig.json, packages/core/tsconfig.json, packages/cost/tsconfig.json, packages/create-reactive-agent/tsconfig.json, packages/diagnose/tsconfig.json, packages/eval/tsconfig.json, packages/gateway/tsconfig.json, packages/guardrails/tsconfig.json, packages/health/tsconfig.json, packages/identity/tsconfig.json, packages/interaction/tsconfig.json, packages/judge-server/tsconfig.json, packages/llm-provider/tsconfig.json, packages/memory/tsconfig.json, packages/observability/tsconfig.json, packages/observe/tsconfig.json, packages/prompts/tsconfig.json, packages/react/tsconfig.json, packages/reactive-agents/tsconfig.json, packages/reactive-intelligence/tsconfig.json, packages/reasoning/tsconfig.json, packages/replay/tsconfig.json, packages/runtime-shim/tsconfig.json, packages/runtime/tsconfig.json, packages/svelte/tsconfig.json, packages/testing/tsconfig.json, packages/tools/tsconfig.json, packages/trace/tsconfig.json, packages/ui-core/tsconfig.json, packages/verification/tsconfig.json, packages/vue/tsconfig.json, tsconfig.json"
}
}
],
"max_points": 11
},
{
"key": "reproducible_environment",
"name": "Reproducible environment",
"detail": "devcontainer, Dockerfile",
"points": 10,
"status": "met",
"details": [
{
"code": "file_list",
"params": {
"files": "devcontainer, Dockerfile"
}
}
],
"max_points": 10
},
{
"key": "demonstrated_agent_practice",
"name": "Demonstrated agent practice",
"detail": "no agent-authored commits among the last 100",
"points": 0,
"status": "missed",
"details": [
{
"code": "no_agent_authored_commits",
"params": {
"sampled": 100
}
}
],
"max_points": 10
},
{
"key": "automated_maintenance",
"name": "Automated maintenance",
"detail": "no automated dependency updates observed",
"points": 0,
"status": "missed",
"details": [
{
"code": "no_dependency_automation",
"params": {}
}
],
"max_points": 8
},
{
"key": "openssf_scorecard_pinned_dependencies",
"name": "OpenSSF Scorecard: Pinned-Dependencies",
"detail": "dependency not pinned by hash detected -- score normalized to 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 10
}
]
},
{
"key": "ai_code_legibility",
"band": "exceptional",
"name": "Code legibility for models",
"note": null,
"notes": [],
"value": 100,
"inputs": {
"primary_language": "TypeScript",
"largest_source_bytes": 117970,
"source_files_sampled": 2346,
"oversized_source_files": 11
},
"components": [
{
"key": "type_checkable_code",
"name": "Type-checkable code",
"detail": "TypeScript (statically typed)",
"points": 45,
"status": "met",
"details": [
{
"code": "statically_typed_language",
"params": {
"language": "TypeScript"
}
}
],
"max_points": 45
},
{
"key": "manageable_file_sizes",
"name": "Manageable file sizes",
"detail": "11/2346 source files over 60KB",
"points": 54.7,
"status": "partial",
"details": [
{
"code": "oversized_source_files",
"params": {
"kb": 60,
"sampled": 2346,
"oversized": 11
}
}
],
"max_points": 55
}
]
},
{
"key": "ai_interfaces",
"band": "moderate",
"name": "Machine-readable interfaces",
"note": null,
"notes": [],
"value": 60,
"inputs": {
"example_dirs": [
"cookbook",
"demos",
"examples"
],
"has_mcp_signal": true,
"api_schema_files": []
},
"components": [
{
"key": "api_schema_openapi_graphql_proto",
"name": "API schema (OpenAPI/GraphQL/proto)",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 40
},
{
"key": "mcp_server",
"name": "MCP server",
"detail": null,
"points": 20,
"status": "met",
"details": [],
"max_points": 20
},
{
"key": "runnable_examples",
"name": "Runnable examples",
"detail": "cookbook, demos, examples",
"points": 40,
"status": "met",
"details": [
{
"code": "file_list",
"params": {
"files": "cookbook, demos, examples"
}
}
],
"max_points": 40
}
]
}
],
"description": "How well is the repo equipped to be developed and maintained with AI coding agents? Carries a deliberately small weight: agent tooling is a real maintenance signal, but its absence must never gate the top of the scale (calibration saturates at raw 91, so 100/100 remains reachable with AI Readiness at zero)."
}
],
"classification": {
"labels": [
"library",
"framework"
],
"scores": {
"cli": 2,
"library": 6,
"framework": 4,
"mcp-server": 3
},
"primary": "library",
"evidence": [
{
"tier": "distribution",
"label": "library",
"source": "registry:npm",
"weight": 6
},
{
"tier": "structure",
"label": "mcp-server",
"source": "mcp_signal",
"weight": 3
},
{
"tier": "tags",
"label": "cli",
"source": "tag:cli",
"weight": 2
},
{
"tier": "description",
"label": "framework",
"source": "description:framework",
"weight": 2
},
{
"tier": "tags",
"label": "framework",
"source": "tag:agent-framework",
"weight": 2
}
],
"artifacts": [],
"confidence": "medium",
"host_extension": false,
"runs_as_process": false,
"consumed_by_code": true
},
"metrics_version": "2.3.1"
},
"warnings": [
"Star history unavailable: GitHub GraphQL error: Resource not accessible by personal access token",
"GitHub dependency-graph SBOM unavailable (404); the dependency graph may be disabled for this repository"
],
"report_type": "repository",
"generated_at": "2026-07-30T20:59:44.195726Z",
"schema_version": "0.27.0",
"badge_url": "https://raw.githubusercontent.com/inspect-software/badges/main/v1/t/tylerjrbuell/reactive-agents-ts.svg",
"full_name": "tylerjrbuell/reactive-agents-ts",
"license_state": "standard",
"license_spdx": "MIT"
}
Пов’язані записи
Перевірені репозиторії, що мають спільні каталожні теги або екосистеми з tylerjrbuell/reactive-agents-ts. Читати поруч →
Оцінки — це сигнали, а не гарантії. Вони відображають публічно видимі практики на GitHub — це не аудит коду й не гарантія безпеки.
Відсутні дані виключаються, а ваги перенормовуються — нуль за відсутність ніколи не ставиться. Методологія версіонована й відкрита: метрики v2.3.1, схема v0.27.0 — повна методологія · вікі метрик.
