meridianlabs-ai/inspect_swe holds a health index of 80 out of 100, placing it in the Excellent band. It scores highest on Vitality (96/100) and lowest on Security (42/100). It was last updated today. A single contributor accounts for most of its recent work.
80
overall / 100
Excellent
Software health index
Metrics are grouped into weighted categories on one standardized 1–100 scale. Overall starts as their weighted mean, calibrated against the distribution of the public record so bands carry percentile meaning; when public evidence triggers the High-Risk Jurisdiction Policy, the rating is adjusted and receives an At Risk ceiling of 34.
80
Exceptional93-100The record's top tier (≈ top 5%); essentially all checked criteria met
Excellent80-92Strong across the board; minor gaps
Good65-79Healthy; gaps are limited and manageable
Moderate50-64Acceptable with notable gaps; review recommended
Weak35-49Material weaknesses across several areas
At Risk20-34Significant weaknesses; adoption warrants caution
Critical1-19Severe problems (abandoned, single-maintainer, no hygiene)
Score profile
Each axis is a category. The shape matters more than the average — a healthy subject fills the whole shape, while a spike-and-crater profile means strength in one dimension is masking risk in another.
The weighted overall 68 is calibrated to 80 on the published index scale (record calibration 2026-08-02).
How well is the repo equipped to be developed and maintained with AI coding agents? Carries a deliberately small weight (4%): agent tooling is a real maintenance signal, but a repository with none can still reach 100/100.
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
deps.dev does not index pypi:inspect_swe@0.2.67; advisories assessed against the repository dependency graph instead
More detail
Star and fork history 0 ★ / 36 ⇿
0Stars
36Forks
When each star and fork was added, collected from GitHub and bucketed by day. Cumulative growth sits directly above the daily additions it is made of, so the two read against each other: steady organic accretion looks nothing like an abrupt, short-lived burst. Where that difference is measurable, it is reported as growth authenticity.
OpenSSF Scorecard 4.2 / 10
4.2aggregate
Independent, tool-agnostic security assessment from the open-source OpenSSF Scorecard. Each check rewards a security practice, not a specific vendor's tool. Checks Scorecard could not determine are marked n/a and excluded from the security score (never counted as zero).Scorecard v5.5.0 · 2026-07-29 15:25 UTC
The resolved dependency set could not be collected for this report: GitHub dependency-graph SBOM unavailable (404); the dependency graph may be disabled for this repository
Raw JSON report machine-readable
{
"data": {
"repo": {
"topics": [],
"is_fork": false,
"size_kb": 2555,
"has_wiki": true,
"homepage": "https://meridianlabs-ai.github.io/inspect_swe/",
"languages": {
"Python": 526023,
"Makefile": 182
},
"pushed_at": "2026-07-29T15:20:32Z",
"created_at": "2025-08-29T23:59:08Z",
"owner_type": "Organization",
"updated_at": "2026-07-29T15:22:36Z",
"description": "Software Engineering Agents for Inspect AI",
"is_archived": false,
"is_disabled": false,
"license_spdx": "MIT",
"default_branch": "main",
"license_spdx_raw": "MIT",
"primary_language": "Python",
"significant_languages": [
"Python"
]
},
"owner": {
"blog": "https://www.meridianlabs.ai",
"name": "Meridian Labs",
"type": "Organization",
"login": "meridianlabs-ai",
"company": null,
"location": "United States of America",
"followers": 87,
"avatar_url": "https://avatars.githubusercontent.com/u/196480008?v=4",
"created_at": "2025-01-25T20:45:22Z",
"is_verified": null,
"public_repos": 22,
"account_age_days": 549
},
"license": {
"state": "standard",
"spdx_id": "MIT",
"raw_spdx": "MIT",
"file_present": true,
"scorecard_found": true,
"profile_has_license": true
},
"activity": {
"releases": [
{
"tag": "0.2.67",
"kind": "patch",
"published_at": "2026-07-29T15:20:32Z"
},
{
"tag": "0.2.66",
"kind": "patch",
"published_at": "2026-07-14T19:37:22Z"
},
{
"tag": "0.2.65",
"kind": "patch",
"published_at": "2026-07-14T19:05:48Z"
}
],
"recent_commits": [
{
"oid": "3492cd6fdfd6e9ec304ad14b3d70b6c7c6701b38",
"body": ":robot: I have created a release *beep* *boop*\n---\n\n\n##\n[0.2.67](https://github.com/meridianlabs-ai/inspect_swe/compare/0.2.66...0.2.67)\n(2026-07-29)\n\n\n### Features\n\n* **claude_code:** add `permission_mode` option (deprecates `auto_mode`)\n([5cc9e6d](https://github.com/meridianlabs-ai/inspect_swe/com\n[…]\nase-please). See\n[documentation](https://github.com/googleapis/release-please#release-please).\n\nCo-authored-by: meridian-release-bot[bot] <301467749+meridian-release-bot[bot]@users.noreply.github.com>",
"is_bot": true,
"headline": "chore(main): release 0.2.67 (#92)",
"author_name": "meridian-release-bot[bot]",
"author_login": "meridian-release-bot[bot]",
"committed_at": "2026-07-29T15:20:15Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "cc854fd00f6939f40d2004eb6e7d077283d8af18",
"body": "… (#102)\n\nAdds an `auto_review` option to `codex_cli()` and\n`interactive_codex_cli()` enabling Codex CLI's automated approval review\n(guardian): Codex runs with its own `workspace-write` sandbox and\n`on-request` approvals, with escalation requests (network access, writes\noutside the workspace, MCP t\n[…]\nored-by: Claude Fable 5 <noreply@anthropic.com>\nCo-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com>\nCo-authored-by: Charles Teague <261654+dragonstyle@users.noreply.github.com>",
"is_bot": false,
"headline": "feat(codex_cli): add auto_review option for automated approval review…",
"author_name": "Charles Teague",
"author_login": "dragonstyle",
"committed_at": "2026-07-29T15:14:52Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "5cc9e6d9a92ed71efc9d72d075528c598b4498d4",
"body": "## Summary\n- Add `allowlist_mcp_tools` for static caller-provided MCP servers.\n- Preserve the released `auto_mode` API through the established\ndeprecated-argument shim while exposing the complete typed Claude Code\npermission-mode set.\n- Correct the MCP wildcard syntax to `mcp__<name>__*` and cover t\n[…]\ne): add `permission_mode` option (deprecates `auto_mode`)\n\nfix(claude_code): correct \"all\" tools MCP allowlist wildcard to\n`mcp__<name>__*`\n\nCo-authored-by: Peter McIntyre <peter.mcintyre01@gmail.com>",
"is_bot": false,
"headline": "feat(claude_code): control static MCP allowlisting (#91)",
"author_name": "Sami Jawhar",
"author_login": "sjawhar",
"committed_at": "2026-07-28T15:44:48Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "596be229bb3efb47adaab0edbb2997b7ae3c7d68",
"body": "…latest (#95)\n\nHi, I am Claude acting on Sami Jawhar (sjawhar)'s behalf.\n\nThis refreshes the bundled Codex fallback catalog from `openai/codex`\n`rust-v0.145.0` (July 2026), including the current `gpt-5.6-sol` latest\nentry and its live priorities. It keeps the fallback aligned when the\nversion-matche\n[…]\ned model can therefore hard-fail CI until the\nsnapshot is refreshed. I can send a separate follow-up if maintainers\nwould like that gate implemented; this PR intentionally only refreshes\nthe snapshot.",
"is_bot": false,
"headline": "fix(codex_cli): refresh bundled model catalog snapshot to track live …",
"author_name": "Sami Jawhar",
"author_login": "sjawhar",
"committed_at": "2026-07-27T09:27:58Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "939d5162618271e36f4db0eb47e6d09fbf1d38cd",
"body": "Adds workflow stubs from\n[meridianlabs-ai/agents](https://github.com/meridianlabs-ai/agents):\nclaude.yml,claude-review.yml.\n\nOnce merged:\n- **Dev agent** — mention `@claude` in an issue or PR comment, or add\nthe `claude` label to an issue.\n- **Reviewer** — auto-reviews PRs on open; or comment `@review` on a PR.",
"is_bot": false,
"headline": "chore: enable Meridian agents (#93)",
"author_name": "Charles Teague",
"author_login": "dragonstyle",
"committed_at": "2026-07-23T00:39:48Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "7fca27f4481a02e39122efd0fd98b306274251bb",
"body": "…s, and Centaur support (#73)\n\n## Summary\n\nAdds a `kimi_code()` agent for Moonshot AI's [Kimi\nCode](https://github.com/MoonshotAI/kimi-code) CLI, running headless in\na sandbox with Inspect model bridging — the same shape as the existing\n`opencode()` / `claude_code()` agents. Closes #72.\n\nKimi's mode\n[…]\n builds keyed by arch only (no musl variants),\nso musl sandbox platforms are collapsed onto the plain `linux-x64` /\n`linux-arm64` keys.\n\n---------\n\nCo-authored-by: Craig Walton <craig@meridianlabs.ai>",
"is_bot": false,
"headline": "feat(kimi): add `kimi_code()` agent with Inspect bridging, MCP, skill…",
"author_name": "jannes-apollo",
"author_login": "jannes-apollo",
"committed_at": "2026-07-22T11:47:53Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "cef56453bdd3cea0d659e5963d277cc1ded59cfc",
"body": "…#86)\n\nUpdates the Commit messages and releases section to match the live\nRelease Please config: perf/revert appear in the release notes while\ndocs/refactor/chore stay hidden, feat and fix both bump the patch\nversion pre-1.0, and publish waits on deployment approval after the\nrelease PR merges. Mirrors the review fix from flow#754.\n\n🤖 Generated with [Claude Code](https://claude.com/claude-code)\n\nCo-authored-by: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "docs: correct release-notes visibility and publish-approval wording (…",
"author_name": "Charles Teague",
"author_login": "dragonstyle",
"committed_at": "2026-07-15T13:59:11Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "6d1bd78345c732d06c4ddabba54dbbd7e280e441",
"body": "Coding agents read AGENTS.md/CLAUDE.md automatically but not\nCONTRIBUTING.md, so this inlines the release-driving PR-title rules\nwhere they'll actually be seen, with CLAUDE.md as a relative symlink to\nAGENTS.md per the org pattern. Mirrors inspect_scout#533.\n\n🤖 Generated with [Claude Code](https://claude.com/claude-code)\n\nCo-authored-by: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "docs: add minimal AGENTS.md with PR-title and release guidance (#87)",
"author_name": "Charles Teague",
"author_login": "dragonstyle",
"committed_at": "2026-07-15T13:55:48Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "614db6c77447f9a47e80de6da14a935bf96dadbd",
"body": "…he top (#84)\n\nPermanent fix for the changelog mis-ordering quirk (new release sections\nlanding *below* the previous one).\n\nRoot cause, verified in release-please's source: the changelog updater\ninserts the new section before the first version header **preceded by a\nnewline** (`\\n###? v?[0-9[]`). A \n[…]\nis open, this merge regenerates it — with the\nnew section correctly at the top.\n\n🤖 Generated with [Claude Code](https://claude.com/claude-code)\n\nCo-authored-by: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "docs: add Changelog title so release-please inserts new sections at t…",
"author_name": "Charles Teague",
"author_login": "dragonstyle",
"committed_at": "2026-07-15T02:10:46Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "709340fb498e1f0d587fdc587f075e72860e9631",
"body": ":robot: I have created a release *beep* *boop*\n---\n\n\n##\n[0.2.66](https://github.com/meridianlabs-ai/inspect_swe/compare/0.2.65...0.2.66)\n(2026-07-14)\n\n\n### Bug Fixes\n\n* update ACP client for agent-client-protocol 0.11.0 compatibility\n([#76](https://github.com/meridianlabs-ai/inspect_swe/issues/76))\n\n[…]\n-by: meridian-release-bot[bot] <301467749+meridian-release-bot[bot]@users.noreply.github.com>\nCo-authored-by: Charles Teague <cteague@gmail.com>\nCo-authored-by: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": true,
"headline": "chore(main): release 0.2.66 (#83)",
"author_name": "meridian-release-bot[bot]",
"author_login": "meridian-release-bot[bot]",
"committed_at": "2026-07-14T19:37:08Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "22328dc0082e0ed49f751d0f905ee249f640db70",
"body": "… (#76) (#82)\n\nCatch-up release credit for **#76** (ACP 0.11.0 compatibility — revised\n`Client` interface signatures, new elicitation methods, requires\n`agent-client-protocol>=0.11.0`), which merged after the `0.2.65` tag\nbut with a non-conventional squash title, so Release Please can't\nsurface it.\n\n[…]\n16).\n\nCode change is docs-only; the actual fix already lives on `main` via\n#76.\n\n🤖 Generated with [Claude Code](https://claude.com/claude-code)\n\nCo-authored-by: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix: update ACP client for agent-client-protocol 0.11.0 compatibility…",
"author_name": "Charles Teague",
"author_login": "dragonstyle",
"committed_at": "2026-07-14T19:21:20Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "780e846c4498ab12829472087758b0e235225807",
"body": "CI ran `mypy src` but the Makefile ran `mypy src tests`, so test-only\ntype errors could merge unnoticed.\n\n- Move the target list into `[tool.mypy]` (`files = [\"src\", \"tests\"]`)\nas the single source of truth\n- CI and Makefile now just run `mypy` (no hardcoded paths)\n- Fix the pre-existing annotation \n[…]\nng them across CI and local.\n\n🤖 Generated with [Claude Code](https://claude.com/claude-code)\n\nCo-authored-by: Claude Opus 4.8 <noreply@anthropic.com>\nCo-authored-by: Charles Teague <cteague@gmail.com>",
"is_bot": false,
"headline": "chore: make mypy consistent between CI and local (#77)",
"author_name": "Craig Walton",
"author_login": "craig-meridian",
"committed_at": "2026-07-14T19:02:48Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "3f15255ce7f09be7b35456312438ecda965dc551",
"body": "…x) (#81)\n\nThe reusable workflow now derives `target-branch` from the dispatched\nbranch (`github.ref_name`), so this caller input is redundant and its\n`default: main` would override the new behavior. Removing it makes the\n\"Use workflow from\" branch selector the sole control (mirrors\nmeridianlabs-ai/actions#66). Normal push-to-main releases are unchanged.\n\n🤖 Generated with [Claude Code](https://claude.com/claude-code)\n\nCo-authored-by: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "ci: drop redundant target-branch dispatch input (single-control hotfi…",
"author_name": "Charles Teague",
"author_login": "dragonstyle",
"committed_at": "2026-07-14T18:52:57Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "ac67cc39835774ad1be1d2ff5403471606b56f8c",
"body": "…chore/refactor) (#80)\n\nRegenerates the committed release-please config from the fixed\ngenerator.\n\n- Removes the invalid \\`release-notes-config\\` key (unsupported; was a\nno-op / config error).\n- Hides \\`docs\\`, \\`chore\\`, and \\`refactor\\` changelog sections so\nrelease notes surface \\`feat\\`/\\`fix\\`/\n[…]\nat (bare /\ninclude-v-in-tag=false), or versioning (patch-pre-major bump flags).\n\n🤖 Generated with [Claude Code](https://claude.com/claude-code)\n\nCo-authored-by: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "chore: regenerate release-please config (drop invalid key, hide docs/…",
"author_name": "Charles Teague",
"author_login": "dragonstyle",
"committed_at": "2026-07-14T18:52:28Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "2d502e6d055037317c54c44e820f77474e64d8a1",
"body": "Adds a `CONTRIBUTING.md` covering development setup, checks and tests,\nthe org-standard Conventional Commits / Release Please guidance, and how\nto report issues. Commands are derived from the `Makefile`, `README.md`,\nand CI.\n\n🤖 Generated with [Claude Code](https://claude.com/claude-code)\n\nCo-authored-by: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "docs: add contributing guide (#78)",
"author_name": "Charles Teague",
"author_login": "dragonstyle",
"committed_at": "2026-07-13T21:06:38Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "44dbf1148571094e7a8e71ffaebed4b73b790f11",
"body": "Migrates `inspect_swe` from manual dispatch to Release Please (shared\nautomation), same pattern as `inspect_viz`.\n\n- **release.yaml** (new): release-please via\n`release-please-python.yml@v1` (App token); `approval-ping: false`.\n- **publish.yml**: `+on: release` (keep manual break-glass); publish\ngat\n[…]\neset + code-owner\nreview, squash-only + squash message.\n\n🤖 Generated with [Claude Code](https://claude.com/claude-code)\n\n---------\n\nCo-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "chore: migrate release to Release Please (App auth) (#75)",
"author_name": "Charles Teague",
"author_login": "dragonstyle",
"committed_at": "2026-07-13T21:05:50Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "3db8dca1ba37dd0de684187d5c2e18d9560ec1b2",
"body": "## Summary\nUpdates the ACP client implementation to be compatible with\n`agent-client-protocol` 0.11.0, which includes revised `Client`\ninterface signatures and new elicitation functionality.\n\n## Key Changes\n- **Updated method signatures** to match the revised `Client` interface:\n- `request_permissio\n[…]\n`_unsupported_capability_request()` errors to indicate they are not\nimplemented by this client.\n\nhttps://claude.ai/code/session_014cUZQ5vFCUnXjGDfgFtPtk\n\nCo-authored-by: Claude <noreply@anthropic.com>",
"is_bot": false,
"headline": "Update ACP client for agent-client-protocol 0.11.0 compatibility (#76)",
"author_name": "Charles Teague",
"author_login": "dragonstyle",
"committed_at": "2026-07-13T20:20:37Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "e0b83497f3c7f8126652e06c50069b5d756c5f6f",
"body": null,
"is_bot": false,
"headline": "update changelog for release",
"author_name": "J.J. Allaire",
"author_login": "jjallaire",
"committed_at": "2026-07-05T15:44:06Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "3fc3a848ad9eb76aca8b0d1fdd41f6e5faa51859",
"body": null,
"is_bot": false,
"headline": "update insepct dependency",
"author_name": "J.J. Allaire",
"author_login": "jjallaire",
"committed_at": "2026-07-05T15:43:50Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "9fae8ac2c755bd394415eb08a792ea329560f3ed",
"body": null,
"is_bot": false,
"headline": "update changelog for release",
"author_name": "J.J. Allaire",
"author_login": "jjallaire",
"committed_at": "2026-07-05T15:39:03Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "319f34b56f2d7fa61185d2a0b8e94756e62d89ee",
"body": "Handle claude_code refusals gracefully",
"is_bot": false,
"headline": "Merge pull request #71 from meridianlabs-ai/brandly/claude-refusals",
"author_name": "Charles Teague",
"author_login": "dragonstyle",
"committed_at": "2026-06-30T00:51:09Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "7c52458035d7fdee808e8ef6436ad483d908ab1f",
"body": "Addresses review feedback: rather than re-parsing raw JSONL in the runner\nloop to recover the terminal stop reason, track it on LiveConsumer, which\nalready receives every ModelEvent from the bridge as a structured object.\n\n- LiveConsumer.on_complete records event.output.stop_reason (guarded for\n em\n[…]\npletes (status=success, 0 sample errors) and the refusing sample is\nscored incorrect, matching the react and direct-model solvers.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "claude_code: source refusal stop reason from LiveConsumer",
"author_name": "Matt Brandly",
"author_login": "brandly",
"committed_at": "2026-06-30T00:33:40Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "c4156881204e0212a9f91abedbc5b3d018059c10",
"body": "Claude Code exits with code 1 (and empty stderr) after an Anthropic\nrefusal response, even though the refusal has already been recorded in\nbridge.state and can be scored. Previously this propagated as a\nRuntimeError that interrupted the entire eval, diverging from native\nInspect solvers which score \n[…]\npletes (status=success, 0 sample errors) and the refusing sample\nis scored incorrect, matching the react and direct-model solvers.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "claude_code: treat Anthropic refusal exits as scoreable, not fatal",
"author_name": "Matt Brandly",
"author_login": "brandly",
"committed_at": "2026-06-29T19:58:12Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "858507e4358b765a407a459c04e0a74149f80111",
"body": null,
"is_bot": false,
"headline": "Handle claude_code refusals gracefully",
"author_name": "Matt Brandly",
"author_login": "brandly",
"committed_at": "2026-06-29T19:49:10Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "f86c55101cf51704e2d860dd6fb0ff5df7418d08",
"body": "Fix Gemini CLI ACP bridge tools",
"is_bot": false,
"headline": "Merge pull request #70 from rguan72/richard/fix-gemini-acp-bridged-tools",
"author_name": "Kai Fronsdal",
"author_login": "kaifronsdal",
"committed_at": "2026-06-25T14:16:07Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "7ee151118967d46426f640220a4f480244b80682",
"body": null,
"is_bot": false,
"headline": "Fix Gemini CLI ACP bridge tools",
"author_name": "Richard Guan",
"author_login": "rguan72",
"committed_at": "2026-06-24T23:46:03Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "364504adff18a5812ada630f1d140655f9e3582d",
"body": "…bridge\n\nCheckpointer support for Codex CLI & Claude Code; run agents in home dir when sandbox default workdir is /",
"is_bot": false,
"headline": "Merge pull request #68 from meridianlabs-ai/feature/checkpoint-agent-…",
"author_name": "Eric Patey",
"author_login": "epatey",
"committed_at": "2026-06-18T14:44:00Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "4439db511533c29350eebb4f2dc8801e33cf23c9",
"body": null,
"is_bot": false,
"headline": "Pin inspect_ai to github main for checkpointer bridge support",
"author_name": "Eric Patey",
"author_login": "epatey",
"committed_at": "2026-06-18T13:55:27Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "02ab118d72cab34c5899d05492fd575893338ff7",
"body": null,
"is_bot": false,
"headline": "Add CHANGELOG entry for checkpoint support",
"author_name": "Eric Patey",
"author_login": "epatey",
"committed_at": "2026-06-18T13:48:01Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "b0879c286843fcf15da4fea5c269fbadf2375a97",
"body": "LiveConsumer/CodexConsumer froze outer_span_id at construction (before\ncheckpointer() entry), pinning main-agent model events and sub-agent\nspan parents to the pre-checkpoint agent span. Resolve via\ncurrent_span_id() at emission instead so attribution tracks the\nrotating checkpoint span (inspect_ai SpanRotationScope; see\ndesign/plans/checkpoint-span-cell.md there).",
"is_bot": false,
"headline": "Resolve consumer outer span lazily at emission time",
"author_name": "Eric Patey",
"author_login": "epatey",
"committed_at": "2026-06-11T18:06:02Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "e56efcf5dd1690a6788373010cc63c32b8a6284f",
"body": null,
"is_bot": false,
"headline": "Add Claude Code checkpoint support",
"author_name": "Eric Patey",
"author_login": "epatey",
"committed_at": "2026-06-11T12:40:59Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "cc34bcc9362bc62d1c32c32c6374887bdf0f0f0c",
"body": null,
"is_bot": false,
"headline": "All agents: fall back to home dir when sandbox default working dir is /",
"author_name": "Eric Patey",
"author_login": "epatey",
"committed_at": "2026-06-10T19:28:52Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "b1a5b07e76573659507f8818b799e086aceedff5",
"body": "…ent-bridge",
"is_bot": false,
"headline": "Merge remote-tracking branch 'origin/main' into feature/checkpoint-ag…",
"author_name": "Eric Patey",
"author_login": "epatey",
"committed_at": "2026-06-10T17:42:04Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "49a7c3004a872b87f9c22fc53036b397b660716f",
"body": null,
"is_bot": false,
"headline": "update changelog for release",
"author_name": "J.J. Allaire",
"author_login": "jjallaire",
"committed_at": "2026-06-10T17:35:15Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "83a9bd06b02d7ccd58ce448bed4023977055314c",
"body": "… (#67)",
"is_bot": false,
"headline": "Codex CLI: use releases/latest endpoint to avoid 504s on full listing…",
"author_name": "Eric Patey",
"author_login": "epatey",
"committed_at": "2026-06-10T17:32:56Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "6183054dac19d7c152a4be2a57716de002c38fd9",
"body": null,
"is_bot": false,
"headline": "mypy",
"author_name": "J.J. Allaire",
"author_login": "jjallaire",
"committed_at": "2026-06-09T20:27:04Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "36d583ef710cfccbf3a055bce00de815b41542f6",
"body": null,
"is_bot": false,
"headline": "use checkpointer in codex",
"author_name": "J.J. Allaire",
"author_login": "jjallaire",
"committed_at": "2026-06-09T20:26:58Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "959d916f3cfc18ded85e6d5781ec41bd6b499715",
"body": null,
"is_bot": false,
"headline": "Remove ACP patch for connection initialization order issue",
"author_name": "J.J. Allaire",
"author_login": "jjallaire",
"committed_at": "2026-06-07T13:54:06Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "2b57b8f68cc5fca8958d2dad05ede9f6ddf65a2f",
"body": null,
"is_bot": false,
"headline": "update changelog for release",
"author_name": "J.J. Allaire",
"author_login": "jjallaire",
"committed_at": "2026-06-05T11:05:47Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "03c44dc75470a198841ca4229cb47ecc8b3dfdff",
"body": null,
"is_bot": false,
"headline": "Tracing: Only trace full session output when `debug` option is passed",
"author_name": "J.J. Allaire",
"author_login": "jjallaire",
"committed_at": "2026-06-05T11:05:22Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "289973e490ce63dff6330bd86799e20ce78159af",
"body": "…#63)\n\n* claude_code: report real served model instead of inspect sentinel\n\nThe bridge sentinel ('inspect'/'inspect/<model>') was used as Claude Code's displayed model, so its system prompt read 'You are powered by the model inspect'. Present the real served model name instead (new presented_model o\n[…]\no-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>\n\n---------\n\nCo-authored-by: J.J. Allaire <jj.allaire@gmail.com>\nCo-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "claude_code: report real served model instead of `inspect` sentinel (…",
"author_name": "alexlloyd-apollo",
"author_login": "alexlloyd-apollo",
"committed_at": "2026-06-04T17:18:30Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "bbea71645fb51065b85bd952c4fec0ac6e0ab65d",
"body": null,
"is_bot": false,
"headline": "update changelog for release",
"author_name": "J.J. Allaire",
"author_login": "jjallaire",
"committed_at": "2026-06-03T23:19:36Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "71733d907665b039d0e859a5f64a2d7c122512b6",
"body": null,
"is_bot": false,
"headline": "codex model name improvements",
"author_name": "J.J. Allaire",
"author_login": "jjallaire",
"committed_at": "2026-06-03T23:19:16Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "8f874c078d282d167a2f428b8206a0e4e3f0a905",
"body": "The sandbox bridge captures Claude Code's own system prompt back into\nstate.messages as a ChatMessageSystem. On resumed turns claude_code\nre-passed it via --append-system-prompt while --resume had already\nrestored it, concatenating the system prompt onto itself (2x turn 2,\n3x turn 3, ...). Send the system prompt only when creating the session;\nnever on resume, where the session already contains it.",
"is_bot": false,
"headline": "fix claude code system prompt duplicated on resumed turns (#64)",
"author_name": "alexlloyd-apollo",
"author_login": "alexlloyd-apollo",
"committed_at": "2026-06-03T17:37:22Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "6fe6fa19034418b73404bc357fc2a949b19104ce",
"body": null,
"is_bot": false,
"headline": "update inspect dependency to 0.3.234",
"author_name": "J.J. Allaire",
"author_login": "jjallaire",
"committed_at": "2026-06-02T20:04:20Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "f5a8e8b11ef15cc2abed916a9c59979005e3f6f2",
"body": null,
"is_bot": false,
"headline": "uddate changelog",
"author_name": "J.J. Allaire",
"author_login": "jjallaire",
"committed_at": "2026-06-01T01:17:21Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "8ddb712502c4e2b6023ef0e4520a583cc8dc52ae",
"body": null,
"is_bot": false,
"headline": "use hatchling < 1.30",
"author_name": "J.J. Allaire",
"author_login": "jjallaire",
"committed_at": "2026-06-01T01:16:58Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "ef2ba9efbc257f5384f7f088e43b2cc578a65bcd",
"body": null,
"is_bot": false,
"headline": "update changelog",
"author_name": "J.J. Allaire",
"author_login": "jjallaire",
"committed_at": "2026-06-01T01:09:12Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "5a9e15eb8f629d93b751fe46fd262ea80da8a87b",
"body": null,
"is_bot": false,
"headline": "update inspect dependency",
"author_name": "J.J. Allaire",
"author_login": "jjallaire",
"committed_at": "2026-05-31T19:43:04Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "a7fd68931067cd2eed57fdef9ae4bbfbe7b40c1d",
"body": null,
"is_bot": false,
"headline": "codex cli agents: code review feedback",
"author_name": "J.J. Allaire",
"author_login": "jjallaire",
"committed_at": "2026-05-31T19:42:52Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "678138c62074a9b6d92b4be16182573b498e29db",
"body": "…t stream",
"is_bot": false,
"headline": "Codex CLI: Detect and apply agent spans automatically from Codex even…",
"author_name": "J.J. Allaire",
"author_login": "jjallaire",
"committed_at": "2026-05-31T17:01:14Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "622de674ac2c2e880aa776fd88ecce304611a9d2",
"body": null,
"is_bot": false,
"headline": "update changelog for release",
"author_name": "J.J. Allaire",
"author_login": "jjallaire",
"committed_at": "2026-05-30T22:50:30Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "7f83c5f2df56012c6e3abf0dd582e09bc41e31d4",
"body": null,
"is_bot": false,
"headline": "Gemini CLI: Explicity set auth type to \"gemini-api-key\"",
"author_name": "J.J. Allaire",
"author_login": "jjallaire",
"committed_at": "2026-05-30T22:49:59Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "66b9245fffdecdb346e30fefcc88a2da8b1d5d95",
"body": null,
"is_bot": false,
"headline": "update required inspect-ai version",
"author_name": "J.J. Allaire",
"author_login": "jjallaire",
"committed_at": "2026-05-30T17:05:45Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "8a1e4fa4960d8b12332e563cbe713b66b2238265",
"body": "… model",
"is_bot": false,
"headline": "Codex CLI: Align the system prompt and tool set with the real bridged…",
"author_name": "J.J. Allaire",
"author_login": "jjallaire",
"committed_at": "2026-05-30T16:50:19Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "ac66a0e370d5632527c9db1863bda3f22acbb383",
"body": "…` tools (both default to enabled).",
"is_bot": false,
"headline": "Codex CLI: Add options for enabling/disabling `web_search` and `goals…",
"author_name": "J.J. Allaire",
"author_login": "jjallaire",
"committed_at": "2026-05-30T15:57:44Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "bc37fced59397a5c65c9255b56aaec9944b805c8",
"body": null,
"is_bot": false,
"headline": "update changelog for release",
"author_name": "J.J. Allaire",
"author_login": "jjallaire",
"committed_at": "2026-05-25T14:16:30Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "648aaf9670c44ac6c3bc37c4b6b3519adfdf23bd",
"body": "* support new claude code jsonl format\n\n* reformat",
"is_bot": false,
"headline": "support new claude code jsonl format (#60)",
"author_name": "jjallaire",
"author_login": "jjallaire",
"committed_at": "2026-05-25T14:14:58Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "be5910dcda8b347726d3729d10c20db3d74d0b90",
"body": "…n of spans into transcript) (#59)\n\n* live event/agent tracking\n\n* Claude Code: Improved live event capture (no longer requires injection of spans into transcript)",
"is_bot": false,
"headline": "Claude Code: Improved live event capture (no longer requires injectio…",
"author_name": "jjallaire",
"author_login": "jjallaire",
"committed_at": "2026-05-25T13:38:50Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "807bc35af0bb212a67014a84bb9c5ef00aa4fc90",
"body": null,
"is_bot": false,
"headline": "Update changelog for unreleased changes",
"author_name": "jjallaire",
"author_login": "jjallaire",
"committed_at": "2026-05-25T13:21:09Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "8843effbc67ee4e45b64a84e82d058eb87c3474c",
"body": null,
"is_bot": false,
"headline": "update inspect-docs",
"author_name": "J.J. Allaire",
"author_login": "jjallaire",
"committed_at": "2026-05-23T17:22:03Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "67784366deba5d73a1096b07c43eee658e3f1251",
"body": null,
"is_bot": false,
"headline": "migrate to inspect-docs",
"author_name": "J.J. Allaire",
"author_login": "jjallaire",
"committed_at": "2026-05-23T17:16:57Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "b02b4a98d14b5dc4697ebd03dc6e9bd4068b3fa3",
"body": null,
"is_bot": false,
"headline": "Merge branch 'alex-treebeard-feat/auto-mode-flag'",
"author_name": "J.J. Allaire",
"author_login": "jjallaire",
"committed_at": "2026-05-22T17:56:33Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "c40e211bcef799087c422b78c26a5ba01de561a7",
"body": null,
"is_bot": false,
"headline": "parameter order + docs for auto_mode",
"author_name": "J.J. Allaire",
"author_login": "jjallaire",
"committed_at": "2026-05-22T17:53:53Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d3f72cefe36968f1317448e25fd757f618c9530e",
"body": "Adds --permission-mode auto as an alternative to --dangerously-skip-permissions,\nenabling the auto-mode monitor (two-stage classifier) for eval red-teaming.\n\nCo-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "Add auto_mode flag to claude_code() agent",
"author_name": "Alex Remedios",
"author_login": "alex-remedios",
"committed_at": "2026-05-22T11:00:47Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "2ca9581766e37f0934a4ab785a3c79ea43c35bc0",
"body": null,
"is_bot": false,
"headline": "Update CHANGELOG.md",
"author_name": "jjallaire",
"author_login": "jjallaire",
"committed_at": "2026-05-19T22:13:16Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "462dd1ee282bd8740034aeaf90844ffe4f19b568",
"body": null,
"is_bot": false,
"headline": "Fix deprecated claude-agent-acp package name (#56)",
"author_name": "kelvin",
"author_login": "kakugawa",
"committed_at": "2026-05-19T22:12:08Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "da0f4fc488a7b53c264190f14ebb942957041082",
"body": "* Fix opencode native skills (#53)\n\n* Fix OpenCode native skill loading\n\nOpenCode discovers global skills under HOME/.config/opencode/skills and uses its native skill tool to load them. The wrapper installed skills project-locally before setting HOME/OPENCODE_CONFIG, which made discovery depend on c\n[…]\n\n* Revert \"refactor: inline ripgrep into agentbinary\"\n\nThis reverts commit 8dd2b6c121d3b4c528c3ec443e24da08ef129dbd.\n\n* changelog and lint\n\n---------\n\nCo-authored-by: Toni Kukurin <tkukurin@gmail.com>",
"is_bot": false,
"headline": "opencode skills: install ripgrep (#54)",
"author_name": "jjallaire",
"author_login": "jjallaire",
"committed_at": "2026-05-17T12:26:22Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "241e7103d8b63ab2031e263eaf92924e21b5f1ff",
"body": null,
"is_bot": false,
"headline": "update changelog for release",
"author_name": "J.J. Allaire",
"author_login": "jjallaire",
"committed_at": "2026-05-16T14:39:56Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "ce29a588fe202775b4e7585dd19fbb5b32b740a7",
"body": null,
"is_bot": false,
"headline": "Workaround for `agent_client_protocol` v0.10.0 connection bug",
"author_name": "J.J. Allaire",
"author_login": "jjallaire",
"committed_at": "2026-05-16T14:37:15Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "f7ccc22b40f73f34d5132d5959ca62f8903775a9",
"body": null,
"is_bot": false,
"headline": "update changelog for release",
"author_name": "J.J. Allaire",
"author_login": "jjallaire",
"committed_at": "2026-05-13T20:05:45Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "6624c0161bcde7778eaaa839750c1e4fb1ec5476",
"body": null,
"is_bot": false,
"headline": "Update CHANGELOG.md",
"author_name": "jjallaire",
"author_login": "jjallaire",
"committed_at": "2026-05-13T20:03:11Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "169fa223e2669f5a3d4e65237b0a51b66b24a79a",
"body": "The non-ACP claude_code agent and the ACP codex_cli/gemini_cli agents\nall bump a per-sample store() counter and pass port= to\nsandbox_agent_bridge so that re-entering the agent in the same\nsandbox doesn't collide with a stale model_proxy still bound on the\ndefault 13131. The ACP claude_code agent wa\n[…]\n that runs the agent more than once per sample (e.g. petri-dish\non rollback/restart) hits EADDRINUSE if the previous proxy hasn't\nfully exited.\n\nCo-authored-by: Claude Opus 4.7 <noreply@anthropic.com>",
"is_bot": false,
"headline": "claude_code (ACP): allocate per-invocation bridge port (#51)",
"author_name": "Kai Fronsdal",
"author_login": "kaifronsdal",
"committed_at": "2026-05-13T20:02:14Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "6a5a374b431e72878940edf31f695312dd2518d5",
"body": "…tps://github.com/agentclientprotocol/python-sdk/issues/97) is fixed",
"is_bot": false,
"headline": "Pin `agent-client-protocol>=0.9.0,<0.10` until [init ordering bug](ht…",
"author_name": "J.J. Allaire",
"author_login": "jjallaire",
"committed_at": "2026-05-13T17:59:27Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "ced0f0e30698f164de9816a25c62f6269d324d8b",
"body": null,
"is_bot": false,
"headline": "update docs and changelog for release",
"author_name": "J.J. Allaire",
"author_login": "jjallaire",
"committed_at": "2026-05-09T13:59:58Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "296b61f18a36cc53a467da64f06eae314cea470f",
"body": null,
"is_bot": false,
"headline": "Merge branch 'marians-add-opencode-agent'",
"author_name": "J.J. Allaire",
"author_login": "jjallaire",
"committed_at": "2026-05-09T13:55:45Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "5c181623f7e89647e21bd81d3cb7733ff4d6e569",
"body": null,
"is_bot": false,
"headline": "ruff format",
"author_name": "J.J. Allaire",
"author_login": "jjallaire",
"committed_at": "2026-05-09T13:55:43Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "97fd3502b0f38ff7c9917b47c4547348d39ae7d3",
"body": null,
"is_bot": false,
"headline": "Merge branch 'main' into add-opencode-agent",
"author_name": "jjallaire",
"author_login": "jjallaire",
"committed_at": "2026-05-09T13:35:26Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "c998f7cc45cdb41210adef88dd2d7f21889716e7",
"body": "* Disable codex_cli and gemini_cli telemetry by default\n\nCo-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>\n\n* Update CHANGELOG.md\n\n* ruff format\n\nCo-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>\n\n---------\n\nCo-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>\nCo-authored-by: jjallaire <jj.allaire@gmail.com>",
"is_bot": false,
"headline": "Disable codex_cli and gemini_cli telemetry by default (#50)",
"author_name": "Eric Winsor",
"author_login": "ericwinsor-aisi",
"committed_at": "2026-05-07T20:38:57Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "eee63c4bdfebfa8616c8bd3d8b9d76b12fd7e830",
"body": null,
"is_bot": false,
"headline": "Update CHANGELOG for version 0.2.51 release",
"author_name": "jjallaire",
"author_login": "jjallaire",
"committed_at": "2026-05-07T15:27:57Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "883bd8da11f5537c7c0d62db12a05dc072f1a742",
"body": "gemini_cli: fix MCP registration via GEMINI_CLI_TRUST_WORKSPACE",
"is_bot": false,
"headline": "Merge pull request #49 from kaifronsdal/gemini-acp-fixes",
"author_name": "Kai Fronsdal",
"author_login": "kaifronsdal",
"committed_at": "2026-05-07T15:13:23Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "22065324846dd551dca7cdf70b9f46d0220081e0",
"body": "… list\n\nThe explicit GEMINI_UTILITY_MODEL_NAMES alias loop is redundant once a\nfallback is set: model_aliases is checked first, then any unmatched name\nfalls through to the bridge `model=` param. The previous fallback value\n`f\"inspect/{model.api.model_name}\"` was also subtly wrong — after\nremovepref\n[…]\n for the primary name, all five known utility\nnames, gemini-3.1-flash-lite-preview (new in 0.41.1), and an arbitrary\nunknown name.\n\nCo-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "gemini_cli (ACP): use bridge fallback model instead of explicit alias…",
"author_name": "Kai Fronsdal",
"author_login": "kaifronsdal",
"committed_at": "2026-05-06T20:18:38Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "f6a8f270f72d64204a678799975125093f65aa95",
"body": "gemini-cli's settings schema defaults security.folderTrust.enabled to\ntrue. With no trustedFolders.json entry for the sandbox cwd and no IDE\nworkspace trust signal, Config.isTrustedFolder() returns false, and\nMcpClientManager.startConfiguredMcpServers() returns immediately\nwithout connecting to any \n[…]\ncher redirects console.* away from stderr. Switch the debug\nparam to set GEMINI_DEBUG_LOG_FILE, which debugLogger honors directly.\n\nCo-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "gemini_cli: set GEMINI_CLI_TRUST_WORKSPACE so MCP servers register",
"author_name": "Kai Fronsdal",
"author_login": "kaifronsdal",
"committed_at": "2026-05-06T20:18:38Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "9d3205480b4c87dbb391a046ed96569ba351b50a",
"body": "Gemini CLI makes internal model calls under hardcoded names\n(gemini-3-flash-preview, gemini-2.5-flash, etc.) for loop-detection,\nweb-search/web-fetch, edit-fixer, next-speaker-checker, subagent\ndefinitions, summarizers, and compaction. There is no env var to\noverride them.\n\nPreviously the ACP wrappe\n[…]\nnot in the alias list still falls back to the target\n (mirrors the non-ACP gemini_cli wrapper).\n- Add a debug=False param that runs gemini-cli with --debug / DEBUG=1\n for MCP-connection diagnostics.",
"is_bot": false,
"headline": "gemini_cli (ACP): alias hardcoded utility-model names to target (#48)",
"author_name": "Kai Fronsdal",
"author_login": "kaifronsdal",
"committed_at": "2026-05-06T16:39:27Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "5d36c3776ed84201430061884be4cf7c49bcebee",
"body": null,
"is_bot": false,
"headline": "Adapt examples",
"author_name": "Marian Steinbach",
"author_login": "marians",
"committed_at": "2026-05-05T06:48:40Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "f626706f3c02263ba0cc33e26f3b533f0f071dd8",
"body": null,
"is_bot": false,
"headline": "Adapt tests",
"author_name": "Marian Steinbach",
"author_login": "marians",
"committed_at": "2026-05-05T06:48:05Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "079518c8874bc9d6353f26ec04596f482287d5ae",
"body": null,
"is_bot": false,
"headline": "Merge branch 'main' into add-opencode-agent",
"author_name": "jjallaire",
"author_login": "jjallaire",
"committed_at": "2026-05-04T20:15:34Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "bcc8dcd9b917177318ee876f97299b52954d7275",
"body": null,
"is_bot": false,
"headline": "Merge branch 'Scott-Simmons-fix/ensurepip-wheel-download'",
"author_name": "J.J. Allaire",
"author_login": "jjallaire",
"committed_at": "2026-05-04T20:12:51Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "e6f82d1695019c0b01600b5265591caa694c9a31",
"body": null,
"is_bot": false,
"headline": "ruff check",
"author_name": "J.J. Allaire",
"author_login": "jjallaire",
"committed_at": "2026-05-04T20:12:12Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "a6075f29e12bfda0cd2a1e4e27958df0d6f5fa51",
"body": "Added note about ensuring pip availability for installation.",
"is_bot": false,
"headline": "Update CHANGELOG with pip installation note",
"author_name": "jjallaire",
"author_login": "jjallaire",
"committed_at": "2026-05-04T20:07:56Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "a525d6f0e2ab4abb9c16820cb09c195579c4f55b",
"body": null,
"is_bot": false,
"headline": "Fix base URL",
"author_name": "Marian Steinbach",
"author_login": "marians",
"committed_at": "2026-04-30T14:13:15Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "cf6fa1a68765fe252dbb2496fca0b845e5889777",
"body": null,
"is_bot": false,
"headline": "Add support for OpenCode",
"author_name": "Marian Steinbach",
"author_login": "marians",
"committed_at": "2026-04-30T13:36:12Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "8467eff53e4cf6bb6f5129089f05b7a964e97f3e",
"body": null,
"is_bot": false,
"headline": "adjust pip download failure fixture",
"author_name": "Scott-Simmons",
"author_login": "Scott-Simmons",
"committed_at": "2026-04-30T04:54:33Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "2140bfff1c3aa58f57e070c57606ecce9e841ef1",
"body": null,
"is_bot": false,
"headline": "test pip bootstrap for wheel downloads",
"author_name": "Scott-Simmons",
"author_login": "Scott-Simmons",
"committed_at": "2026-04-30T04:52:16Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "be3e11818937c0439b5d3c05d7b8f746bed80abe",
"body": null,
"is_bot": false,
"headline": "bootstrap pip for wheel downloads",
"author_name": "Scott-Simmons",
"author_login": "Scott-Simmons",
"committed_at": "2026-04-30T04:35:45Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "5c3c62f1ef5cbf3b0aa8dcb2b81bbe9273b02e9d",
"body": null,
"is_bot": false,
"headline": "update changelog for release",
"author_name": "J.J. Allaire",
"author_login": "jjallaire",
"committed_at": "2026-04-29T22:15:32Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "3c0add4836e8aea75c170e1940e5f411b6955bcb",
"body": null,
"is_bot": false,
"headline": "richard/give-codex-acp-full-access (#45)",
"author_name": "Richard Guan",
"author_login": "rguan72",
"committed_at": "2026-04-29T22:14:34Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "040a3332c2b47233391d7abc259d00eeef1573ce",
"body": null,
"is_bot": false,
"headline": "remove hardcoded 'claude code' from agentbinary util (#44)",
"author_name": "Stephen Kyle",
"author_login": "rubzo",
"committed_at": "2026-04-29T22:13:28Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "f7667924fc1af2b7b293af8b07e30033d7a3229c",
"body": null,
"is_bot": false,
"headline": "bump to inspect_ai 0.3.214 to fix code cli mcp tool use",
"author_name": "J.J. Allaire",
"author_login": "jjallaire",
"committed_at": "2026-04-29T22:11:59Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "0e18e418a9f00c633ca589da15c48a6fa851e046",
"body": null,
"is_bot": false,
"headline": "update changelog",
"author_name": "J.J. Allaire",
"author_login": "jjallaire",
"committed_at": "2026-04-26T19:30:56Z",
"body_truncated": false,
"is_coding_agent": false
}
],
"releases_count": 3,
"commits_last_year": 378,
"latest_release_at": "2026-07-29T15:20:32Z",
"latest_release_tag": "0.2.67",
"releases_from_tags": false,
"days_since_last_push": 0,
"active_weeks_last_year": 43,
"days_since_latest_release": 0,
"mean_days_between_releases": 7.4
},
"community": {
"has_readme": true,
"has_license": true,
"has_description": true,
"has_contributing": true,
"health_percentage": 62,
"has_issue_template": false,
"has_code_of_conduct": false,
"has_pull_request_template": false
},
"ecosystem": {
"packages": [
{
"name": "inspect_swe",
"exists": true,
"license": "MIT License",
"keywords": [],
"ecosystem": "pypi",
"matches_repo": true,
"registry_url": "https://pypi.org/project/inspect_swe/",
"is_deprecated": false,
"latest_version": "0.2.67",
"repository_url": "https://github.com/meridianlabs-ai/inspect_swe",
"versions_count": 67,
"total_downloads": null,
"dependents_count": null,
"deprecation_note": null,
"maintainers_count": null,
"monthly_downloads": 282173,
"first_published_at": "2025-08-30T14:49:09.980006Z",
"latest_published_at": "2026-07-29T15:23:47.218964Z",
"latest_version_yanked": null,
"days_since_latest_publish": 0
}
]
},
"popularity": {
"forks": 36,
"stars": 23,
"watchers": 2,
"fork_history": {
"days": [
{
"date": "2025-09-02",
"count": 1
},
{
"date": "2025-09-17",
"count": 1
},
{
"date": "2025-10-03",
"count": 1
},
{
"date": "2025-10-12",
"count": 1
},
{
"date": "2025-10-29",
"count": 1
},
{
"date": "2025-11-17",
"count": 1
},
{
"date": "2025-12-08",
"count": 1
},
{
"date": "2026-01-02",
"count": 1
},
{
"date": "2026-01-15",
"count": 1
},
{
"date": "2026-02-11",
"count": 1
},
{
"date": "2026-02-13",
"count": 1
},
{
"date": "2026-02-18",
"count": 1
},
{
"date": "2026-02-25",
"count": 1
},
{
"date": "2026-03-05",
"count": 1
},
{
"date": "2026-03-24",
"count": 1
},
{
"date": "2026-03-31",
"count": 1
},
{
"date": "2026-04-21",
"count": 1
},
{
"date": "2026-04-27",
"count": 1
},
{
"date": "2026-04-29",
"count": 2
},
{
"date": "2026-04-30",
"count": 2
},
{
"date": "2026-05-07",
"count": 1
},
{
"date": "2026-05-08",
"count": 1
},
{
"date": "2026-05-09",
"count": 1
},
{
"date": "2026-05-13",
"count": 1
},
{
"date": "2026-05-16",
"count": 2
},
{
"date": "2026-05-19",
"count": 1
},
{
"date": "2026-05-22",
"count": 2
},
{
"date": "2026-06-11",
"count": 1
},
{
"date": "2026-07-01",
"count": 1
},
{
"date": "2026-07-14",
"count": 1
}
],
"complete": true,
"collected": 34,
"total_forks": 36
},
"star_history": null,
"open_issues_and_prs": 15
},
"ai_readiness": {
"has_nix": false,
"example_dirs": [
"examples"
],
"has_llms_txt": false,
"has_dockerfile": true,
"has_mcp_signal": true,
"bootstrap_files": [
"Makefile"
],
"api_schema_files": [],
"has_devcontainer": false,
"typecheck_configs": [
"src/inspect_swe/py.typed"
],
"toolchain_manifests": [],
"largest_source_bytes": 40132,
"source_files_sampled": 118,
"oversized_source_files": 0,
"agent_instruction_files": [
"AGENTS.md",
"CLAUDE.md"
],
"agent_instruction_max_bytes": 775
},
"dependencies": {
"manifests": [
"pyproject.toml"
],
"advisories": {
"error": null,
"scope": null,
"source": null,
"findings": [],
"collected": false,
"malicious": [],
"truncated": false,
"by_severity": {},
"advisory_count": 0,
"affected_count": 0,
"assessed_count": 0,
"malicious_count": 0,
"assessed_package": null,
"unassessed_count": 0,
"direct_affected_count": 0
},
"ecosystems": [
"pypi"
],
"dependencies": [
{
"name": "httpx",
"manifest": "pyproject.toml",
"ecosystem": "pypi",
"version_constraint": null
},
{
"name": "inspect_ai",
"manifest": "pyproject.toml",
"ecosystem": "pypi",
"version_constraint": ">=0.3.251"
},
{
"name": "nest_asyncio",
"manifest": "pyproject.toml",
"ecosystem": "pypi",
"version_constraint": null
},
{
"name": "platformdirs",
"manifest": "pyproject.toml",
"ecosystem": "pypi",
"version_constraint": null
},
{
"name": "pydantic",
"manifest": "pyproject.toml",
"ecosystem": "pypi",
"version_constraint": ">=2.13.0"
},
{
"name": "pyyaml",
"manifest": "pyproject.toml",
"ecosystem": "pypi",
"version_constraint": null
},
{
"name": "sniffio",
"manifest": "pyproject.toml",
"ecosystem": "pypi",
"version_constraint": null
},
{
"name": "anyio",
"manifest": "pyproject.toml",
"ecosystem": "pypi",
"version_constraint": null
},
{
"name": "typing_extensions",
"manifest": "pyproject.toml",
"ecosystem": "pypi",
"version_constraint": ">=4.9.0"
},
{
"name": "agent-client-protocol",
"manifest": "pyproject.toml",
"ecosystem": "pypi",
"version_constraint": ">=0.11.0"
}
],
"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": 8,
"merged_prs": 61,
"open_issues": 7,
"closed_ratio": 0.588,
"closed_issues": 10,
"closed_unmerged_prs": 16
},
"bus_factor": 1,
"bot_contributors": 1,
"top_contributors": [
{
"type": "User",
"login": "jjallaire",
"commits": 288,
"avatar_url": "https://avatars.githubusercontent.com/u/104391?v=4"
},
{
"type": "User",
"login": "anaoaktree",
"commits": 18,
"avatar_url": "https://avatars.githubusercontent.com/u/7874328?v=4"
},
{
"type": "User",
"login": "dragonstyle",
"commits": 12,
"avatar_url": "https://avatars.githubusercontent.com/u/261654?v=4"
},
{
"type": "User",
"login": "kaifronsdal",
"commits": 12,
"avatar_url": "https://avatars.githubusercontent.com/u/26915801?v=4"
},
{
"type": "User",
"login": "epatey",
"commits": 9,
"avatar_url": "https://avatars.githubusercontent.com/u/769548?v=4"
},
{
"type": "User",
"login": "alexlloyd-apollo",
"commits": 5,
"avatar_url": "https://avatars.githubusercontent.com/u/214490753?v=4"
},
{
"type": "User",
"login": "marians",
"commits": 4,
"avatar_url": "https://avatars.githubusercontent.com/u/273727?v=4"
},
{
"type": "User",
"login": "fastfedora",
"commits": 4,
"avatar_url": "https://avatars.githubusercontent.com/u/1173892?v=4"
},
{
"type": "User",
"login": "brandly",
"commits": 3,
"avatar_url": "https://avatars.githubusercontent.com/u/820696?v=4"
},
{
"type": "User",
"login": "Scott-Simmons",
"commits": 3,
"avatar_url": "https://avatars.githubusercontent.com/u/52365471?v=4"
}
],
"contributors_sampled": 25,
"top_contributor_share": 0.762
},
"quality_signals": {
"has_ci": true,
"has_tests": true,
"ci_workflows": [
"build.yaml",
"claude-review.yml",
"claude.yml",
"pr-title-lint.yml",
"publish.yml",
"release.yaml"
],
"has_docs_dir": true,
"linter_configs": [],
"has_editorconfig": false,
"has_linter_config": false,
"has_precommit_config": false
},
"security_signals": {
"lockfiles": [
"package-lock.json",
"uv.lock"
],
"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": "20 out of 20 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": 2,
"reason": "Found 6/21 approved changesets -- score normalized to 2",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#code-review"
},
{
"name": "Contributors",
"score": 10,
"reason": "project has 4 contributing companies or organizations",
"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": 0,
"reason": "project is not 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 3 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": 10,
"reason": "packaging workflow 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": 0,
"reason": "security policy file not 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": "130 existing vulnerabilities detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#vulnerabilities"
}
],
"commit": "3492cd6fdfd6e9ec304ad14b3d70b6c7c6701b38",
"ran_at": "2026-07-29T15:25:05Z",
"aggregate_score": 4.2,
"scorecard_version": "v5.5.0"
},
"has_codeql_workflow": false,
"has_security_policy": false,
"has_dependabot_config": false
},
"contribution_flow": {
"collected": true,
"ci_last_run_at": "2026-07-29T15:20:48Z",
"oldest_open_prs": [
{
"number": 69,
"created_at": "2026-06-15T12:00:22Z",
"last_comment_at": "2026-07-26T21:23:22Z",
"last_comment_author": "jannes-apollo"
},
{
"number": 88,
"created_at": "2026-07-20T15:59:32Z",
"last_comment_at": "2026-07-28T04:53:48Z",
"last_comment_author": "sjawhar"
},
{
"number": 89,
"created_at": "2026-07-20T15:59:35Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 94,
"created_at": "2026-07-24T02:22:14Z",
"last_comment_at": "2026-07-24T14:39:11Z",
"last_comment_author": "sjawhar"
},
{
"number": 98,
"created_at": "2026-07-27T11:49:07Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 99,
"created_at": "2026-07-27T21:32:54Z",
"last_comment_at": "2026-07-27T21:37:04Z",
"last_comment_author": "claude"
},
{
"number": 100,
"created_at": "2026-07-28T16:49:30Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 101,
"created_at": "2026-07-28T19:09:57Z",
"last_comment_at": "2026-07-28T20:08:42Z",
"last_comment_author": "sjawhar"
}
],
"last_merged_pr_at": "2026-07-29T15:20:16Z",
"ci_last_conclusion": "SKIPPED",
"oldest_open_issues": [
{
"number": 20,
"created_at": "2026-01-13T17:45:57Z",
"last_comment_at": "2026-01-14T13:18:57Z",
"last_comment_author": "jjallaire"
},
{
"number": 26,
"created_at": "2026-02-23T20:39:37Z",
"last_comment_at": "2026-03-05T19:23:56Z",
"last_comment_author": "anthonyduong9"
},
{
"number": 62,
"created_at": "2026-06-03T12:14:25Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 66,
"created_at": "2026-06-09T13:55:07Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 74,
"created_at": "2026-07-09T13:28:35Z",
"last_comment_at": "2026-07-14T03:16:31Z",
"last_comment_author": "gdjs2"
},
{
"number": 96,
"created_at": "2026-07-26T21:00:34Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 97,
"created_at": "2026-07-26T21:16:11Z",
"last_comment_at": null,
"last_comment_author": null
}
]
}
},
"config": {
"disabled_metrics": [],
"disabled_categories": [],
"disabled_components": {}
},
"source": {
"url": "https://github.com/meridianlabs-ai/inspect_swe",
"host": "github.com",
"name": "inspect_swe",
"owner": "meridianlabs-ai"
},
"metrics": {
"overall": {
"key": "overall",
"band": "excellent",
"name": "Overall health",
"note": "The weighted overall 68 is calibrated to 80 on the published index scale (record calibration 2026-08-02).",
"notes": [
{
"code": "overall_calibration",
"params": {
"raw": 68,
"calibrated": 80,
"calibration": "2026-08-02"
}
}
],
"value": 80,
"inputs": {
"security": 42,
"vitality": 96,
"community": 61,
"governance": 60,
"calibration": "2026-08-02",
"engineering": 77,
"ai_readiness": 69,
"weighted_overall_raw": 68
},
"components": []
},
"categories": [
{
"key": "vitality",
"band": "exceptional",
"name": "Vitality",
"value": 96,
"weight": 0.21,
"metrics": [
{
"key": "development_activity",
"band": "exceptional",
"name": "Development activity",
"note": null,
"notes": [],
"value": 94,
"inputs": {
"commits_last_year": 378,
"human_commit_share": 0.98,
"days_since_last_push": 0,
"active_weeks_last_year": 43
},
"components": [
{
"key": "push_recency",
"name": "Push recency",
"detail": "last push 0 days ago",
"points": 36,
"status": "met",
"details": [
{
"code": "push_recency",
"params": {
"days": 0
}
}
],
"max_points": 36
},
{
"key": "commit_cadence",
"name": "Commit cadence",
"detail": "43/52 weeks with commits",
"points": 29.8,
"status": "partial",
"details": [
{
"code": "commit_cadence_weeks",
"params": {
"weeks": 43
}
}
],
"max_points": 36
},
{
"key": "commit_volume",
"name": "Commit volume",
"detail": "378 commits in the last year",
"points": 18,
"status": "met",
"details": [
{
"code": "commits_last_year",
"params": {
"count": 378
}
}
],
"max_points": 18
},
{
"key": "openssf_scorecard_maintained",
"name": "OpenSSF Scorecard: Maintained",
"detail": "30 commit(s) and 3 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": 3,
"latest_release_tag": "0.2.67",
"releases_from_tags": false,
"days_since_latest_release": 0,
"mean_days_between_releases": 7.4
},
"components": [
{
"key": "ships_releases",
"name": "Ships releases",
"detail": "3 releases published",
"points": 27,
"status": "met",
"details": [
{
"code": "releases_published",
"params": {
"count": 3
}
}
],
"max_points": 27
},
{
"key": "release_recency",
"name": "Release recency",
"detail": "latest release 0 days ago",
"points": 36,
"status": "met",
"details": [
{
"code": "release_recency",
"params": {
"days": 0
}
}
],
"max_points": 36
},
{
"key": "release_cadence",
"name": "Release cadence",
"detail": "a release every ~7.4 days",
"points": 27,
"status": "met",
"details": [
{
"code": "release_cadence",
"params": {
"gap": 7.4
}
}
],
"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": "maintained",
"guards": [],
"signals": [],
"red_flag": false,
"multiplier_pct": 100,
"declared_reason": null,
"unverified_reason": null,
"unanswered_open_prs": null,
"unanswered_open_issues": null,
"days_since_last_merged_pr": null,
"days_since_last_human_commit": 4,
"days_since_last_human_commit_is_floor": false
},
"components": [
{
"key": "project_is_still_maintained",
"name": "Project is still maintained",
"detail": "last human commit 4 days ago",
"points": 100,
"status": "met",
"details": [
{
"code": "abandonment_maintained",
"params": {
"days": 4
}
}
],
"max_points": 100
}
]
}
],
"description": "Is the project alive — is code being written and are releases shipping?"
},
{
"key": "community",
"band": "moderate",
"name": "Community & Adoption",
"value": 61,
"weight": 0.17,
"metrics": [
{
"key": "popularity",
"band": "weak",
"name": "Popularity & adoption",
"note": null,
"notes": [],
"value": 35,
"inputs": {
"forks": 36,
"stars": 23,
"watchers": 2,
"growth_state": "unverified",
"growth_factor_pct": 100,
"growth_unverified_reason": "no_history"
},
"components": [
{
"key": "stars",
"name": "Stars",
"detail": "23 stars",
"points": 21.8,
"status": "partial",
"details": [
{
"code": "stars",
"params": {
"count": 23
}
}
],
"max_points": 60
},
{
"key": "forks",
"name": "Forks",
"detail": "36 forks",
"points": 12.9,
"status": "partial",
"details": [
{
"code": "forks",
"params": {
"count": 36
}
}
],
"max_points": 25
},
{
"key": "watchers",
"name": "Watchers",
"detail": "2 watchers",
"points": 0,
"status": "missed",
"details": [
{
"code": "watchers",
"params": {
"count": 2
}
}
],
"max_points": 15
}
]
},
{
"key": "community_health",
"band": "good",
"name": "Community health",
"note": null,
"notes": [],
"value": 70,
"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": false
},
"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": 0,
"status": "missed",
"details": [],
"max_points": 6.3
}
]
},
{
"key": "ecosystem_adoption",
"band": "excellent",
"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": 91,
"inputs": {
"packages": [
"inspect_swe"
],
"dependents": null,
"ecosystems": "pypi",
"total_downloads": null,
"monthly_downloads": 282173
},
"components": [
{
"key": "monthly_downloads",
"name": "Monthly downloads",
"detail": "282,173 downloads/month across pypi",
"points": 72.7,
"status": "partial",
"details": [
{
"code": "downloads_monthly",
"params": {
"count": 282173,
"ecosystems": "pypi"
}
}
],
"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": "moderate",
"name": "Sustainability & Governance",
"value": 60,
"weight": 0.23,
"metrics": [
{
"key": "maintainer_resilience",
"band": "weak",
"name": "Maintainer resilience (bus factor)",
"note": null,
"notes": [],
"value": 38,
"inputs": {
"bus_factor": 1,
"contributors_sampled": 25,
"top_contributor_share": 0.762
},
"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 76% of commits",
"points": 5.4,
"status": "partial",
"details": [
{
"code": "top_contributor_share",
"params": {
"share": 76
}
}
],
"max_points": 22.5
},
{
"key": "contributor_breadth",
"name": "Contributor breadth",
"detail": "25 contributors",
"points": 13.5,
"status": "met",
"details": [
{
"code": "contributors_sampled",
"params": {
"count": 25
}
}
],
"max_points": 13.5
},
{
"key": "openssf_scorecard_contributors",
"name": "OpenSSF Scorecard: Contributors",
"detail": "project has 4 contributing companies or organizations",
"points": 10,
"status": "met",
"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": 59,
"inputs": {
"merged_prs": 61,
"open_issues": 7,
"closed_issues": 10,
"prs_merged_7d": null,
"prs_decided_7d": null,
"prs_merged_30d": null,
"prs_decided_30d": null,
"issue_closed_ratio": 0.588,
"closed_unmerged_prs": 16,
"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": "59% of issues closed",
"points": 24.7,
"status": "partial",
"details": [
{
"code": "issues_closed_share",
"params": {
"share": 59
}
}
],
"max_points": 42
},
{
"key": "pr_acceptance",
"name": "PR acceptance",
"detail": "61/77 decided PRs merged",
"points": 23.8,
"status": "partial",
"details": [
{
"code": "decided_prs_merged",
"params": {
"merged": 61,
"decided": 77
}
}
],
"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 6/21 approved changesets -- score normalized to 2",
"points": 3,
"status": "partial",
"details": [],
"max_points": 15
}
]
},
{
"key": "stewardship",
"band": "moderate",
"name": "Ownership & stewardship",
"note": null,
"notes": [],
"value": 57,
"inputs": {
"followers": 87,
"owner_type": "Organization",
"is_verified": null,
"owner_login": "meridianlabs-ai",
"public_repos": 22,
"account_age_days": 549
},
"components": [
{
"key": "ownership_backing",
"name": "Ownership backing",
"detail": "organization-owned",
"points": 30,
"status": "met",
"details": [
{
"code": "owner_organization",
"params": {}
}
],
"max_points": 30
},
{
"key": "verified_domain",
"name": "Verified domain",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 20
},
{
"key": "owner_reach",
"name": "Owner reach",
"detail": "87 followers of meridianlabs-ai",
"points": 14,
"status": "partial",
"details": [
{
"code": "owner_followers",
"params": {
"count": 87,
"login": "meridianlabs-ai"
}
}
],
"max_points": 25
},
{
"key": "track_record",
"name": "Track record",
"detail": "22 public repos, account ~1 yr old",
"points": 12.9,
"status": "partial",
"details": [
{
"code": "public_repos",
"params": {
"count": 22
}
},
{
"code": "account_age_years",
"params": {
"years": 1
}
}
],
"max_points": 25
}
]
},
{
"key": "package_maintenance",
"band": "exceptional",
"name": "Package maintenance",
"note": null,
"notes": [],
"value": 100,
"inputs": {
"packages": [
"inspect_swe"
],
"ecosystems": "pypi",
"any_deprecated": false,
"min_days_since_publish": 0
},
"components": [
{
"key": "published_resolvable",
"name": "Published & resolvable",
"detail": "1 package(s) on pypi",
"points": 25,
"status": "met",
"details": [
{
"code": "packages_published",
"params": {
"count": 1,
"ecosystems": "pypi"
}
}
],
"max_points": 25
},
{
"key": "publish_recency",
"name": "Publish recency",
"detail": "latest publish 0 days ago",
"points": 35,
"status": "met",
"details": [
{
"code": "publish_recency",
"params": {
"days": 0
}
}
],
"max_points": 35
},
{
"key": "version_history",
"name": "Version history",
"detail": "67 published versions",
"points": 20,
"status": "met",
"details": [
{
"code": "published_versions",
"params": {
"count": 67
}
}
],
"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": "good",
"name": "Engineering Quality",
"value": 77,
"weight": 0.19,
"metrics": [
{
"key": "engineering_practices",
"band": "good",
"name": "Engineering practices",
"note": null,
"notes": [],
"value": 68,
"inputs": {
"has_ci": true,
"has_tests": true,
"has_editorconfig": false,
"has_linter_config": false,
"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": null,
"points": 0,
"status": "missed",
"details": [],
"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": "20 out of 20 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": [],
"has_wiki": true,
"homepage": "https://meridianlabs-ai.github.io/inspect_swe/",
"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://meridianlabs-ai.github.io/inspect_swe/",
"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": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 10
},
{
"key": "wiki",
"name": "Wiki",
"detail": null,
"points": 10,
"status": "met",
"details": [],
"max_points": 10
}
]
}
],
"description": "Are baseline engineering and documentation practices in place?"
},
{
"key": "security",
"band": "weak",
"name": "Security",
"value": 42,
"weight": 0.16,
"metrics": [
{
"key": "security_posture",
"band": "weak",
"name": "Security posture",
"note": "Excluded from scoring (no data or not applicable): Signed-Releases. Remaining weights renormalized.",
"notes": [
{
"code": "excluded_no_data",
"params": {
"components": [
"signed_releases"
]
}
},
{
"code": "weights_renormalized",
"params": {}
}
],
"value": 42,
"inputs": {
"source": "openssf_scorecard",
"checks_evaluated": 17,
"scorecard_version": "v5.5.0",
"checks_inconclusive": 1,
"scorecard_aggregate": 4.2
},
"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": "20 out of 20 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 6/21 approved changesets -- score normalized to 2",
"points": 1.5,
"status": "partial",
"details": [],
"max_points": 7.5
},
{
"key": "contributors",
"name": "Contributors",
"detail": "project has 4 contributing companies or organizations",
"points": 2.5,
"status": "met",
"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 not fuzzed",
"points": 0,
"status": "missed",
"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 3 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 detected",
"points": 5,
"status": "met",
"details": [],
"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 not detected",
"points": 0,
"status": "missed",
"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": "130 existing vulnerabilities detected",
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.5
}
]
},
{
"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": 15
},
"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": 69,
"weight": 0.04,
"metrics": [
{
"key": "ai_agent_context",
"band": "good",
"name": "Agent context & guidance",
"note": null,
"notes": [],
"value": 65,
"inputs": {
"has_llms_txt": false,
"legible_history_share": 0.367,
"agent_instruction_files": [
"AGENTS.md",
"CLAUDE.md"
],
"agent_instruction_max_bytes": 775
},
"components": [
{
"key": "agent_instructions",
"name": "Agent instructions",
"detail": "AGENTS.md, CLAUDE.md",
"points": 45,
"status": "met",
"details": [
{
"code": "file_list",
"params": {
"files": "AGENTS.md, CLAUDE.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": "36 of 98 human commits state their intent (structured subject or explanatory body)",
"points": 19.6,
"status": "partial",
"details": [
{
"code": "legible_history",
"params": {
"legible": 36,
"sampled": 98
}
}
],
"max_points": 40
}
]
},
{
"key": "ai_verify_loop",
"band": "good",
"name": "Verify loop (build / test / typecheck)",
"note": null,
"notes": [],
"value": 71,
"inputs": {
"has_nix": false,
"has_tests": true,
"lockfiles": [
"package-lock.json",
"uv.lock"
],
"has_dockerfile": true,
"typed_language": false,
"bootstrap_files": [
"Makefile"
],
"has_devcontainer": false,
"has_linter_config": false,
"typecheck_configs": [
"src/inspect_swe/py.typed"
],
"agent_commit_share": 0.2,
"toolchain_manifests": [],
"dependency_bot_commit_share": 0
},
"components": [
{
"key": "one_command_bootstrap",
"name": "One-command bootstrap",
"detail": "Makefile",
"points": 18,
"status": "met",
"details": [
{
"code": "file_list",
"params": {
"files": "Makefile"
}
}
],
"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": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 11
},
{
"key": "static_type_checking",
"name": "Static type checking",
"detail": "src/inspect_swe/py.typed",
"points": 11,
"status": "met",
"details": [
{
"code": "file_list",
"params": {
"files": "src/inspect_swe/py.typed"
}
}
],
"max_points": 11
},
{
"key": "reproducible_environment",
"name": "Reproducible environment",
"detail": "Dockerfile, lockfile",
"points": 10,
"status": "met",
"details": [
{
"code": "file_list",
"params": {
"files": "Dockerfile, lockfile"
}
}
],
"max_points": 10
},
{
"key": "demonstrated_agent_practice",
"name": "Demonstrated agent practice",
"detail": "20 of the last 100 commits agent-authored or agent-credited",
"points": 10,
"status": "met",
"details": [
{
"code": "agent_authored_commits",
"params": {
"count": 20,
"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": "excellent",
"name": "Code legibility for models",
"note": null,
"notes": [],
"value": 82,
"inputs": {
"primary_language": "Python",
"largest_source_bytes": 40132,
"source_files_sampled": 118,
"oversized_source_files": 0
},
"components": [
{
"key": "type_checkable_code",
"name": "Type-checkable code",
"detail": "Python with type-check config (src/inspect_swe/py.typed)",
"points": 27,
"status": "partial",
"details": [
{
"code": "typecheck_config_language",
"params": {
"files": "src/inspect_swe/py.typed",
"language": "Python"
}
}
],
"max_points": 45
},
{
"key": "manageable_file_sizes",
"name": "Manageable file sizes",
"detail": "0/118 source files over 60KB",
"points": 55,
"status": "met",
"details": [
{
"code": "oversized_source_files",
"params": {
"kb": 60,
"sampled": 118,
"oversized": 0
}
}
],
"max_points": 55
}
]
},
{
"key": "ai_interfaces",
"band": "moderate",
"name": "Machine-readable interfaces",
"note": null,
"notes": [],
"value": 60,
"inputs": {
"example_dirs": [
"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": "examples",
"points": 40,
"status": "met",
"details": [
{
"code": "file_list",
"params": {
"files": "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"
],
"scores": {
"library": 6,
"mcp-server": 3
},
"primary": "library",
"evidence": [
{
"tier": "distribution",
"label": "library",
"source": "registry:pypi",
"weight": 6
},
{
"tier": "structure",
"label": "mcp-server",
"source": "mcp_signal",
"weight": 3
}
],
"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",
"deps.dev does not index pypi:inspect_swe@0.2.67; advisories assessed against the repository dependency graph instead"
],
"report_type": "repository",
"generated_at": "2026-07-29T15:25:34.774988Z",
"schema_version": "0.27.0",
"badge_url": "https://raw.githubusercontent.com/inspect-software/badges/main/v1/m/meridianlabs-ai/inspect_swe.svg",
"full_name": "meridianlabs-ai/inspect_swe",
"license_state": "standard",
"license_spdx": "MIT"
}
Related records
Inspected repositories sharing catalogue tags or ecosystems with meridianlabs-ai/inspect_swe. Read them side by side →
Scores are signals, not warranties. They reflect publicly visible practices on GitHub — not a code audit, and not a security guarantee.
Missing data is excluded and weights renormalized, never scored as zero. Methodology is versioned and open: metrics v2.3.1, schema v0.27.0 — full methodology · metrics wiki.
