Public recordModerate
Software health reportschema 0.27.0 · metrics 1.13.0 · 2026-07-24 03:44 UTC
tangle-network / agent-knowledge
Build, search, evaluate, and improve source-backed knowledge bases.
tangle-network/agent-knowledge holds a health index of 62 out of 100, placing it in the Moderate band. It scores highest on Engineering Quality (80/100) and lowest on Community & Adoption (33/100). It was last updated today. A single contributor accounts for most of its recent work.
62
overall / 100Software health index
Metrics are grouped into weighted categories on one standardized 1–100 scale. Overall starts as their weighted mean; when public evidence triggers the High-Risk Jurisdiction Policy, the rating is adjusted and receives an At risk ceiling of 49. AI Readiness sits outside the overall score.
62
Excellent85-100Exemplary; meets essentially all checked criteria
Good70-84Healthy; minor gaps
Moderate50-69Acceptable with notable gaps; review recommended
At risk30-49Significant weaknesses; adoption warrants caution
Critical1-29Severe 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.
Ownership
TangleOrganization
758 followers248 public repossince Jan 2021
This repository is backed by an organization — shared, accountable stewardship that can outlive any single maintainer.
Package ecosystems
| Registry | Package | Version | Downloads / mo | Versions | Last publish |
|---|---|---|---|---|---|
| npm | @tangle-network/agent-knowledge | 4.1.0 | 13,588 | 31 | 5 days ago |
Metrics by category
Vitality
Is the project alive — is code being written and are releases shipping?
72
Development activity
62Moderate
How it's scored
| 36/36 | Push recency — last push 0 days ago |
| 8.3/36 | Commit cadence — 12/52 weeks with commits |
| 17.4/18 | Commit volume — 85 commits in the last year |
| 0/10 | OpenSSF Scorecard: Maintained — project was created within the last 90 days. Please review its contents carefully |
Inputs used
| commits_last_year | 85 |
| human_commit_share | 1 |
| days_since_last_push | 0 |
| active_weeks_last_year | 12 |
Release discipline
88Excellent
How it's scored
| 16.2/27 | Ships releases — 25 version tags (no GitHub releases) |
| 36/36 | Release recency — latest release 5 days ago |
| 27/27 | Release cadence — a release every ~0.5 days |
| 0/10 | OpenSSF Scorecard: Signed-Releases — no data |
Inputs used
| releases_count | 25 |
| latest_release_tag | v4.1.0 |
| releases_from_tags | yes |
| days_since_latest_release | 5 |
| mean_days_between_releases | 0.5 |
Excluded from scoring (no data or not applicable): OpenSSF Scorecard: Signed-Releases. Remaining weights renormalized.
Community & Adoption
Does the project have users, downloads, attention, and a welcoming setup for contributors?
33
Popularity & adoption
1Critical
How it's scored
| 0/60 | Stars — 0 stars |
| 0/25 | Forks — 0 forks |
| 0/15 | Watchers — 0 watchers |
Inputs used
| forks | 0 |
| stars | 0 |
| watchers | 0 |
| growth_state | unverified |
| growth_factor_pct | 100 |
| growth_unverified_reason | no_history |
Community health
44At risk
How it's scored
| 22.5/22.5 | README |
| 16.9/22.5 | License — license file present, not a recognized license |
| 0/18 | CONTRIBUTING guide |
| 0/13.5 | Code of conduct |
| 0/7.2 | Issue template |
| 0/6.3 | PR template |
Inputs used
| has_readme | yes |
| has_license | yes |
| has_contributing | no |
| has_issue_template | no |
| has_code_of_conduct | no |
| has_pull_request_template | no |
Ecosystem adoption (downloads)
69Moderate
How it's scored
| 55.1/80 | Monthly downloads — 13,588 downloads/month across npm |
| 0/20 | Registry dependents — not reported by this ecosystem |
Inputs used
| packages | @tangle-network/agent-knowledge |
| dependents | — |
| ecosystems | npm |
| total_downloads | — |
| monthly_downloads | 13,588 |
Excluded from scoring (no data or not applicable): Registry dependents. Remaining weights renormalized.
Sustainability & Governance
Will the project survive its people — bus factor, responsiveness, who backs it, and package upkeep?
68
Maintainer resilience (bus factor)
16Critical
How it's scored
| 9/54 | Bus factor — 1 contributor(s) cover half of all commits |
| 1.3/22.5 | Commit distribution — top contributor authored 94% of commits |
| 2.7/13.5 | Contributor breadth — 2 contributors |
| 3/10 | OpenSSF Scorecard: Contributors — project has 1 contributing companies or organizations -- score normalized to 3 |
Inputs used
| bus_factor | 1 |
| contributors_sampled | 2 |
| top_contributor_share | 0.943 |
Issue & PR responsiveness
96Excellent
How it's scored
| 0/46.8 | Issue resolution — no issues or no data |
| 36.3/38.3 | PR acceptance — 73/77 decided PRs merged |
| 15/15 | OpenSSF Scorecard: Code-Review — all changesets reviewed |
Inputs used
| merged_prs | 73 |
| open_issues | 0 |
| closed_issues | 0 |
| issue_closed_ratio | — |
| closed_unmerged_prs | 4 |
Excluded from scoring (no data or not applicable): Issue resolution. Remaining weights renormalized.
Ownership & stewardship
75Good
How it's scored
| 30/30 | Ownership backing — organization-owned |
| 0/20 | Verified domain |
| 20.7/25 | Owner reach — 758 followers of tangle-network |
| 24.1/25 | Track record — 248 public repos, account ~5 yr old |
Inputs used
| followers | 758 |
| owner_type | Organization |
| is_verified | — |
| owner_login | tangle-network |
| public_repos | 248 |
| account_age_days | 2,029 |
Package maintenance
100Excellent
How it's scored
| 25/25 | Published & resolvable — 1 package(s) on npm |
| 35/35 | Publish recency — latest publish 5 days ago |
| 20/20 | Version history — 31 published versions |
| 20/20 | Not deprecated — active, not deprecated or yanked |
Inputs used
| packages | @tangle-network/agent-knowledge |
| ecosystems | npm |
| any_deprecated | no |
| min_days_since_publish | 5 |
Engineering Quality
Are baseline engineering and documentation practices in place?
80
Engineering practices
84Good
How it's scored
| 24/24 | CI workflows — 2 workflow(s) |
| 24/24 | Tests present |
| 16/16 | Linter config — biome.json |
| 0/9.6 | Pre-commit hooks |
| 0/6.4 | .editorconfig |
| 20/20 | OpenSSF Scorecard: CI-Tests — 28 out of 28 merged PRs checked by a CI test -- score normalized to 10 |
Inputs used
| has_ci | yes |
| has_tests | yes |
| has_editorconfig | no |
| has_linter_config | yes |
| has_precommit_config | no |
Documentation
75Good
How it's scored
| 30/30 | README |
| 25/25 | Documentation directory |
| 0/15 | Documentation / homepage site |
| 10/10 | Repository description |
| 0/10 | Topics |
| 10/10 | Wiki |
Inputs used
| topics | — |
| has_wiki | yes |
| homepage | — |
| has_readme | yes |
| has_docs_dir | yes |
| has_description | yes |
Security
Are visible security and supply-chain practices strong, without unresolved high-risk jurisdiction exposure?
52
Security posture
40At risk
How it's scored
| 7.5/7.5 | Binary-Artifacts — no binaries found in the repo |
| 0/7.5 | Branch-Protection — no data |
| 2.5/2.5 | CI-Tests — 28 out of 28 merged PRs checked by a CI test -- score normalized to 10 |
| 0/2.5 | CII-Best-Practices — no effort to earn an OpenSSF best practices badge detected |
| 7.5/7.5 | Code-Review — all changesets reviewed |
| 0.8/2.5 | Contributors — project has 1 contributing companies or organizations -- score normalized to 3 |
| 10/10 | Dangerous-Workflow — no dangerous workflow patterns detected |
| 0/7.5 | Dependency-Update-Tool — no update tool detected |
| 0/5 | Fuzzing — project is not fuzzed |
| 2.2/2.5 | License — license file detected |
| 0/7.5 | Maintained — project was created within the last 90 days. Please review its contents carefully |
| 0/5 | Packaging — no data |
| 0/5 | Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 0 |
| 0/5 | SAST — SAST tool is not run on all commits -- score normalized to 0 |
| 0/5 | Security-Policy — security policy file not detected |
| 0/7.5 | Signed-Releases — no data |
| 0/7.5 | Token-Permissions — detected GitHub workflow tokens with excessive permissions |
| 3.8/7.5 | Vulnerabilities — 5 existing vulnerabilities detected |
Inputs used
| source | openssf_scorecard |
| checks_evaluated | 15 |
| scorecard_version | v5.5.0 |
| checks_inconclusive | 3 |
| scorecard_aggregate | 4 |
Excluded from scoring (no data or not applicable): branch_protection, packaging, signed_releases. Remaining weights renormalized.
Dependency advisories
100Excellent
How it's scored
| 35/35 | Direct dependencies free of known advisories — no direct dependency carries a known advisory |
| 25/25 | Indirect dependencies free of known advisories — no indirect dependency carries a known advisory |
| 0/40 | No advisories left outstanding — no advisory carries a publication date |
Inputs used
| source | osv |
| advisories | 0 |
| affected_packages | 0 |
| assessed_packages | 41 |
| unassessed_packages | 0 |
| affected_by_severity | none |
| direct_affected_packages | 0 |
Excluded from scoring (no data or not applicable): No advisories left outstanding. Remaining weights renormalized. Matched the npm:@tangle-network/agent-knowledge@4.1.0 runtime dependency closure — what installing the published package pulls in — 41 packages. Reachability is not analyzed.
AI Readiness
How well is the repo equipped to be developed and maintained with AI coding agents? An independent, experimental badge — weight 0.0, so it is surfaced on its own and does not affect the overall health score.
73
Agent context & guidance
85Excellent
How it's scored
| 45/45 | Agent instructions — AGENTS.md |
| 0/15 | Machine-readable docs (llms.txt) |
| 40/40 | Legible commit history — 87 of 87 human commits state their intent (structured subject or explanatory body) |
Inputs used
| has_llms_txt | no |
| legible_history_share | 1 |
| agent_instruction_files | AGENTS.md |
| agent_instruction_max_bytes | 5,626 |
Verify loop (build / test / typecheck)
54Moderate
How it's scored
| 0/18 | One-command bootstrap |
| 22/22 | Automated tests |
| 11/11 | Lint / format config — biome.json |
| 11/11 | Static type checking — tsconfig.json |
| 10/10 | Reproducible environment — lockfile |
| 0/10 | Demonstrated agent practice — no agent-authored commits among the last 87 |
| 0/8 | Automated maintenance — no automated dependency updates observed |
| 0/10 | OpenSSF Scorecard: Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 0 |
Inputs used
| has_nix | no |
| has_tests | yes |
| lockfiles | pnpm-lock.yaml |
| has_dockerfile | no |
| typed_language | yes |
| bootstrap_files | — |
| has_devcontainer | no |
| has_linter_config | yes |
| typecheck_configs | tsconfig.json |
| agent_commit_share | 0 |
| toolchain_manifests | — |
| dependency_bot_commit_share | 0 |
Code legibility for models
100Excellent
How it's scored
| 45/45 | Type-checkable code — TypeScript (statically typed) |
| 55/55 | Manageable file sizes — 0/179 source files over 60KB |
Inputs used
| primary_language | TypeScript |
| largest_source_bytes | 36,856 |
| source_files_sampled | 179 |
| oversized_source_files | 0 |
Key facts
0GitHub stars
2contributors
85commits, last 12 months
0days since last push
25releases
1bus factor
0open issues
npmpackage ecosystems
Data collection warnings
- GitHub dependency-graph SBOM unavailable (404); the dependency graph may be disabled for this repository
More detail
OpenSSF Scorecard 4.0 / 10
4.0aggregate
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).
| 10 | Binary-Artifacts | no binaries found in the repo |
| n/a | Branch-Protection | internal error: error during branchesHandler.setup: internal error: some github tokens can't read classic branch protection rules: https://github.com/ossf/scorecard-action/blob/main/docs/authentication/fine-grained-auth-token.md |
| 10 | CI-Tests | 28 out of 28 merged PRs checked by a CI test -- score normalized to 10 |
| 0 | CII-Best-Practices | no effort to earn an OpenSSF best practices badge detected |
| 10 | Code-Review | all changesets reviewed |
| 3 | Contributors | project has 1 contributing companies or organizations -- score normalized to 3 |
| 10 | Dangerous-Workflow | no dangerous workflow patterns detected |
| 0 | Dependency-Update-Tool | no update tool detected |
| 0 | Fuzzing | project is not fuzzed |
| 9 | License | license file detected |
| 0 | Maintained | project was created within the last 90 days. Please review its contents carefully |
| n/a | Packaging | packaging workflow not detected |
| 0 | Pinned-Dependencies | dependency not pinned by hash detected -- score normalized to 0 |
| 0 | SAST | SAST tool is not run on all commits -- score normalized to 0 |
| 0 | Security-Policy | security policy file not detected |
| n/a | Signed-Releases | no releases found |
| 0 | Token-Permissions | detected GitHub workflow tokens with excessive permissions |
| 5 | Vulnerabilities | 5 existing vulnerabilities detected |
Direct dependencies 4
| Registry | Package | Version constraint | Manifest |
|---|---|---|---|
| npm | @tangle-network/agent-eval | ^0.123.8 | package.json |
| npm | @tangle-network/agent-interface | ^0.31.0 | package.json |
| npm | proper-lockfile | 4.1.2 | package.json |
| npm | zod | ^4.4.3 | package.json |
All dependencies not collected
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
Dependency advisories 0
Installing npm:@tangle-network/agent-knowledge@4.1.0 pulls in 41 packages, direct and transitive: 0 carry known advisories, of which 0 are direct dependencies.
No known advisories affect the assessed dependencies.
An advisory means the version recorded in the dependency graph falls inside an advisory’s affected range. Reachability is not analysed, and the graph includes development and test pins — a finding may concern tooling rather than shipped software.
Raw JSON report machine-readable
{
"data": {
"repo": {
"topics": [],
"is_fork": false,
"size_kb": 1360,
"has_wiki": true,
"homepage": null,
"languages": {
"JavaScript": 18050,
"TypeScript": 1616888
},
"pushed_at": "2026-07-24T01:50:55Z",
"created_at": "2026-05-03T17:18:52Z",
"owner_type": "Organization",
"updated_at": "2026-07-24T01:50:59Z",
"description": "Build, search, evaluate, and improve source-backed knowledge bases.",
"is_archived": false,
"is_disabled": false,
"license_spdx": null,
"default_branch": "main",
"license_spdx_raw": "NOASSERTION",
"primary_language": "TypeScript",
"significant_languages": [
"TypeScript"
]
},
"owner": {
"blog": "https://tangle.tools",
"name": "Tangle",
"type": "Organization",
"login": "tangle-network",
"company": null,
"location": null,
"followers": 758,
"avatar_url": "https://avatars.githubusercontent.com/u/76852793?v=4",
"created_at": "2021-01-01T21:51:44Z",
"is_verified": null,
"public_repos": 248,
"account_age_days": 2029
},
"license": {
"state": "custom",
"spdx_id": null,
"raw_spdx": "NOASSERTION",
"file_present": true,
"scorecard_found": true,
"profile_has_license": true
},
"activity": {
"releases": [
{
"tag": "v4.1.0",
"kind": "minor",
"published_at": "2026-07-18T17:51:48Z"
},
{
"tag": "v4.0.1",
"kind": "patch",
"published_at": "2026-07-18T14:46:59Z"
},
{
"tag": "v4.0.0",
"kind": "major",
"published_at": "2026-07-18T06:49:33Z"
},
{
"tag": "v3.2.1",
"kind": "patch",
"published_at": "2026-07-18T02:24:41Z"
},
{
"tag": "v3.2.0",
"kind": "minor",
"published_at": "2026-07-18T00:48:36Z"
},
{
"tag": "v3.1.0",
"kind": "minor",
"published_at": "2026-07-17T22:56:47Z"
},
{
"tag": "v3.0.1",
"kind": "patch",
"published_at": "2026-07-16T18:19:37Z"
},
{
"tag": "v3.0.0",
"kind": "major",
"published_at": "2026-07-15T17:06:03Z"
},
{
"tag": "v2.0.1",
"kind": "patch",
"published_at": "2026-07-14T16:09:52Z"
},
{
"tag": "v2.0.0",
"kind": "major",
"published_at": "2026-07-14T04:37:38Z"
},
{
"tag": "v1.12.1",
"kind": "patch",
"published_at": "2026-07-12T03:02:40Z"
},
{
"tag": "v1.12.0",
"kind": "minor",
"published_at": "2026-07-12T02:55:42Z"
},
{
"tag": "v1.11.2",
"kind": "patch",
"published_at": "2026-07-11T06:16:42Z"
},
{
"tag": "v1.11.1",
"kind": "patch",
"published_at": "2026-07-08T19:53:11Z"
},
{
"tag": "v1.11.0",
"kind": "minor",
"published_at": "2026-07-08T19:29:35Z"
},
{
"tag": "v1.10.0",
"kind": "minor",
"published_at": "2026-06-25T01:26:01Z"
},
{
"tag": "v1.9.0",
"kind": "minor",
"published_at": "2026-06-24T22:26:54Z"
},
{
"tag": "v1.8.0",
"kind": "minor",
"published_at": "2026-06-24T21:37:25Z"
},
{
"tag": "v1.7.0",
"kind": "minor",
"published_at": "2026-06-05T00:04:58Z"
},
{
"tag": "v1.6.0",
"kind": "minor",
"published_at": "2026-06-04T12:05:03Z"
},
{
"tag": "v1.5.2",
"kind": "patch",
"published_at": "2026-06-02T12:38:10Z"
},
{
"tag": "v1.5.1",
"kind": "patch",
"published_at": "2026-05-28T20:50:13Z"
},
{
"tag": "v1.5.0",
"kind": "minor",
"published_at": "2026-05-26T12:18:27Z"
},
{
"tag": "v1.3.0",
"kind": "minor",
"published_at": "2026-05-20T08:47:53Z"
},
{
"tag": "v1.2.0",
"kind": "minor",
"published_at": "2026-05-14T17:34:57Z"
}
],
"recent_commits": [
{
"oid": "95ae68270082c1cedbc0b1983c3b65c954875dda",
"body": null,
"is_bot": false,
"headline": "fix(optimization): require explicit retrieval methods (#77)",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-07-24T01:50:55Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "32e1c1ba680eef0a89234ae0260882ecdab7d67f",
"body": "…#76)",
"is_bot": false,
"headline": "feat(optimization): run knowledge searches through complete methods (…",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-07-24T01:37:08Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "77f2394d891485d9eeb84e22945b710210cc1494",
"body": "* feat(skills): add knowledge adoption workflow\n\n* fix(skills): harden package checks\n\n* fix(skills): validate folded descriptions\n\n* fix(skills): harden installed skill verification",
"is_bot": false,
"headline": "feat(skills): add knowledge adoption workflow (#75)",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-07-23T03:52:38Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "37a613c2767f8b98a706ff2b4e41e642353ab3ab",
"body": "* feat(search): expose filesystem search provider\n\n* docs(readme): lead with developer entry points",
"is_bot": false,
"headline": "docs(readme): lead with developer entry points (#74)",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-07-23T01:41:32Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "94ad1dde4cbb8e0db8e82643799874c3cb667b94",
"body": "* refactor(knowledge): modularize KB and RAG internals\n\n* fix(release): accept holdout scenario evidence\n\n* fix(sources): correct HTTP provenance contract\n\n* chore(package): simplify dependencies and documentation\n\n* docs(sources): preserve HTTP fetch invariants",
"is_bot": false,
"headline": "refactor(knowledge): modularize KB and RAG internals (#73)",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-07-18T17:51:48Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "1516d2071d7dda6b41dcffcb1855f54d40c4fc9b",
"body": "Preserve the public API and behavior while splitting oversized memory and benchmark modules, centralizing test support, and removing the remaining source import cycle.",
"is_bot": false,
"headline": "refactor(memory): modularize benchmarks and experiments (#72)",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-07-18T14:46:59Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "428fcd745e774ec8a5a09579d8ed41e954657922",
"body": "* feat(memory): add branchable provider improvement system\n\n* fix(memory): harden provider recovery and cost controls\n\n* fix(memory): harden parallel resume and activation\n\n* fix(memory): close provider isolation and recovery gaps",
"is_bot": false,
"headline": "feat(memory): add branchable provider improvement system (#71)",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-07-18T06:49:33Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "b3589bb2e4ac734e862d0d418154cbddb2ea9f52",
"body": null,
"is_bot": false,
"headline": "fix(improvement): keep promoted run reopening read-only (#70)",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-07-18T02:24:41Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "a43e91d4bf9c2fdbb55b7800b7af8b1ef1e485df",
"body": null,
"is_bot": false,
"headline": "feat(improvement): bind activations to knowledge changes (#69)",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-07-18T00:48:36Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "b66fe2a26957caffca23816f8ad63d23c9726623",
"body": "…store\n\nfeat(improvement): restore approved knowledge baseline",
"is_bot": false,
"headline": "Merge pull request #68 from tangle-network/feat/knowledge-baseline-re…",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-07-17T22:56:47Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "06febc98e05fc88314bcaedfecb15832063a367e",
"body": null,
"is_bot": false,
"headline": "feat(improvement): restore approved knowledge baseline",
"author_name": "Drew Stone",
"author_login": "drewstone",
"committed_at": "2026-07-17T22:45:45Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "3cc44665dcd66e3f19dbf5dc33675b2f25b64b6b",
"body": null,
"is_bot": false,
"headline": "chore(release): align agent stack (#67)",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-07-16T18:19:37Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "ef94d373980ce641a178448ac7d845d0eefff5d4",
"body": null,
"is_bot": false,
"headline": "fix(package): make published tarballs re-packable (#66)",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-07-16T18:10:29Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "820c08bd10561c3176b3d4ffb7a44b7cd2a39946",
"body": "…te-contract\n\nrefactor(contract): remove knowledge candidate schema versions",
"is_bot": false,
"headline": "Merge pull request #65 from tangle-network/refactor/unversion-candida…",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-07-15T17:06:03Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "6e9a398cdcbebe5b56f6588b008814298c4ba6e7",
"body": null,
"is_bot": false,
"headline": "refactor(contract): remove knowledge candidate schema versions",
"author_name": "Drew Stone",
"author_login": "drewstone",
"committed_at": "2026-07-15T17:03:14Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "c662e5d65982308a0a07a86de866278ca221715b",
"body": null,
"is_bot": false,
"headline": "feat(candidate): export shared knowledge references (#64)",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-07-14T16:09:52Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "9cad919ec0ad77bc0414eb54ab96dee7afbbed97",
"body": "Make candidate measurement, approval, promotion, persistence, cost accounting, and crash recovery exact and reusable.",
"is_bot": false,
"headline": "feat(improvement): promote exact knowledge candidates",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-07-14T04:37:38Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "f849558968fe87833430f35ddb434dce91237471",
"body": null,
"is_bot": false,
"headline": "chore(release): bump agent-knowledge to 1.12.1 (#62)",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-07-12T03:02:40Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d24de53c8d5f87708df9de8d86713235cdb4a1ff",
"body": null,
"is_bot": false,
"headline": "chore(release): bump agent-knowledge to 1.12.0 (#61)",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-07-12T02:55:42Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "5e90f385fb7e202d84429bbf35c68c5528fe3806",
"body": null,
"is_bot": false,
"headline": "feat(discovery): pursue bounded follow-up research (#60)",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-07-12T02:54:08Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "0f5e53acef43fa23806faa04f563753f333f2697",
"body": null,
"is_bot": false,
"headline": "chore(deps): align agent-eval 0.113 (#59)",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-07-11T06:16:42Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "4c6a2def2a78e6e2dc52c029812dd3760869b567",
"body": "Clarifies the agent-knowledge README use cases and runtime integration path for KB improvement.",
"is_bot": false,
"headline": "docs(readme): clarify knowledge usage paths",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-07-08T20:16:48Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "8a5e9558c45e9f47fc7b674789d643e195ca9421",
"body": "Bump agent-knowledge to 1.11.1 and align its agent-eval dependency with the latest patch.",
"is_bot": false,
"headline": "chore(deps): align agent-eval 0.108.1",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-07-08T19:53:11Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "b83c1d3a444e1fde85b9db52a92f70e61ef13352",
"body": null,
"is_bot": false,
"headline": "feat(readiness): add KB readiness evaluator (#56)",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-07-08T19:29:35Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "3d9e76c3ddccbbe60046112b481556349b8728bf",
"body": null,
"is_bot": false,
"headline": "refactor(knowledge): make package runtime-independent (#55)",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-07-08T19:03:38Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d9be64f166f1b2723ed29826c2dcd93671e8ac73",
"body": null,
"is_bot": false,
"headline": "feat(benchmarks): rank real memory adapters (#54)",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-07-08T18:06:34Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "3eadd50865a787ce47a1f83dc03c5d400f58cb62",
"body": null,
"is_bot": false,
"headline": "feat(benchmarks): add memory benchmark suite (#53)",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-07-08T16:08:21Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "894154f93cea02e5a86511f3887ab89d1dcbb76b",
"body": null,
"is_bot": false,
"headline": "test(benchmarks): add all-family smoke pack (#52)",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-07-08T01:25:54Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "212cbd6d2ee644858f2a70b64d01fb254cc81a4d",
"body": null,
"is_bot": false,
"headline": "feat(benchmarks): add knowledge benchmark suite (#51)",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-07-08T01:21:01Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "456215176ac126f03497b587ff93d10d3819fe32",
"body": "Adds improveKnowledgeBase as a resumable candidate-KB wrapper around the existing RAG lifecycle, updates Tangle deps, and covers promotion/resume/parallel-safety behavior.",
"is_bot": false,
"headline": "feat(improvement): add resumable knowledge base loop",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-07-08T00:37:06Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "661c806fbd38fba241e2b0325c78b1ddb500fa1f",
"body": null,
"is_bot": false,
"headline": "feat(rag): add answer and KB quality evals (#49)",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-07-07T20:46:05Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "3003acb3cacd4bc9640ca9d26d73b0c5ec999008",
"body": null,
"is_bot": false,
"headline": "feat(rag): expose knowledge improvement lifecycle (#48)",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-07-07T20:18:12Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "65750bde27667cbd9421aa7f9634a76a17818118",
"body": "Add the retrieval/RAG eval improvement loop, tests, and SOTA eval roadmap.",
"is_bot": false,
"headline": "feat(retrieval): add RAG eval improvement loop",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-07-07T20:06:08Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "b1b82f8373b3210d028843aa6e4c85f827bc73f9",
"body": "…ounterfactual logging)\n\n* feat(memory): optional randomized retrieval holdout (epsilon-dropout) for treatment-effect logging\n\nOpt-in, default-off hook between adapter.search() and renderMemoryContext():\nwith per-session probability epsilon, suppress one watchlist item from every\nretrieval of that s\n[…]\nrted for test isolation.\n- New tests: IPS-vs-SNIPS divergence under arm imbalance with mixed\n candidate counts, doublyRobust with per-session qHat, partial-batch and\n missing-reward fail-loud paths.",
"is_bot": false,
"headline": "feat(memory): default-off retrieval-holdout hook (epsilon-dropout + c…",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-07-05T00:07:30Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "dba9ea95c6cd75fb8c509cab98cd40f109ef590e",
"body": "…rchLoop (#45)\n\n* feat(memory): optional randomized retrieval holdout (epsilon-dropout) for treatment-effect logging\n\nOpt-in, default-off hook between adapter.search() and renderMemoryContext():\nwith per-session probability epsilon, suppress one watchlist item from every\nretrieval of that session (s\n[…]\nhe\nVerified* family, matching the existing createVerifyingResearchDriver sibling.\n\nDeprecated aliases keep every old name exported (non-breaking); prefer the Verified* names.\ntsc clean, bundle builds.",
"is_bot": false,
"headline": "refactor(research): rename runTwoAgentResearchLoop → runVerifiedResea…",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-07-04T21:16:32Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "035a8d423037dafc82a31fc7e3b8525a30b61488",
"body": "… reliably discriminates (#44)\n\nRun a fixed K=32 independent slots (16 each over two non-memorized MoE\npapers, samples=4) through the causal-challenger -> refine -> accept loop\nand report the accepted-rate with a Wilson 95% CI, the per-slot gap\ndistribution, and the plain-vs-refined gap-widening wit\n[…]\n\n- docs/results/autodata-live.md: replace the noisy n=3 section with the\n powered rate + CI, the gap distribution, and two autopsied accepted\n examples (real weak-fails-strong-derives on both docs).",
"is_bot": false,
"headline": "feat(autodata): powered accept-rate with CI — settle whether the loop…",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-06-26T16:03:13Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "02302860a9d53258deb8509f6e2c43e8189d09d7",
"body": "…ak gap (#43)\n\n* feat(autodata): non-extractive causal challenger — open the strong/weak gap\n\nThe discriminative data-creation loop nulled because questions leaked their\nanswer (recall) and the default doc was memorized by the weak solver, so an 8B\nread/recalled as well as a frontier model and no ex\n[…]\nhe +0.20 gap-widening from the fold; what doesn't\nis the accepted count. Reframed from 'it works' to 'directionally confirmed but noisy/\nunder-powered at n=3' — the small-n mirage, flagged not buried.",
"is_bot": false,
"headline": "feat(autodata): non-extractive causal challenger — open the strong/we…",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-06-26T08:28:41Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "2db1feb0ffc8994c7653479449c7b2e84a68f32f",
"body": "…Tokens + tier env knobs (#42)\n\nThe strong reasoning-model solver returned empty visible content at maxTokens=1024\n(budget spent on hidden reasoning) and was silently scored 0 — manufacturing a false\nnegative strong/weak gap across every live run. Fix: maxTokens=8000 + throw on empty\ncontent (no sil\n[…]\nth the fix the gap\nis ~0 (not negative): on extractive doc-grounded QA an 8B scores as well as a frontier\nmodel — the lever is challenger difficulty, not model tier. See docs/results/autodata-live.md.",
"is_bot": false,
"headline": "fix(autodata): fail loud on empty solver content + reasoning-safe max…",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-06-25T22:30:05Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "26c617f49fb76a5434d0ad2564439198869e414c",
"body": "…irical strong/weak gap (#41)\n\nThe LIVE Autodata / Agentic Self-Instruct application: ground on a real source\ndocument, run the agentic data-creation inner loop with REAL two-tier solver\nmodels over the Tangle router, score with an llmJudge rubric, keep only examples\nthat DISCRIMINATE a strong solve\n[…]\nd\ncalibration even when nothing clears the bar.\n\nOffline tests are credentialless (scripted workers + mock-transport judge) so CI\nstays green without keys. Run live with `pnpm autodata` under dotenvx.",
"is_bot": false,
"headline": "feat(research): Autodata dataset builder — real two-tier solvers, emp…",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-06-25T20:57:51Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "5e9adb0daebf3aebe1dd29df4fd65315be7ed7bf",
"body": "…aced, a metric that needs investigation not retrieval (#40)\n\n* test(eval): held-out investment-research eval set (5 companies, 27 material facts)\n\nAdd tests/eval/investment-thesis-set.ts: a firewalled eval set for the\nresearch loop, mirroring tests/loops/held-out-exam.ts. Give a loop a company\n+ ti\n[…]\nesult link list at the tail.\n\nA/B numbers transcribed verbatim from commit 338bc54's recorded live run; calibration\nnumbers verified green offline (pnpm test investment-calibration). Docs-only change.",
"is_bot": false,
"headline": "feat(research): investment-thesis research eval — material-facts-surf…",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-06-25T14:44:54Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "939610ae5510fc564cce9ba1b91c502af35e95af",
"body": "…estions not dedup (#39)\n\n* feat(research): research-DRIVING driver (drives depth+validation, not source filtering)\n\nAdd createResearchDrivingDriver, a ResearchDriver for runTwoAgentResearchLoop\nwhose job is to drive the research DEEPER each round rather than filter sources\n(the opposite of the rele\n[…]\n 12-16x more — the verdict flips with\nthe compute budget (web variance), and ties a blind worker even when forced to\nrun its full multi-round mechanism. Numbers match docs/results/research-driving.md.",
"is_bot": false,
"headline": "feat(research): a research-driving loop, measured on held-out deep qu…",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-06-25T09:54:42Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "1a49608c0ac1ebe971dc9afe3dcec7758ef68b8b",
"body": "Ships unreleased exports already on main:\n- createClaimGroundingVerifier / groundClaimInText / withCitedClaim (claim-grounding.ts)\n- createAdaptiveResearchDriver (adaptive-driver.ts)\n- RouterClient.usage() + RouterUsage (per-arm cost instrumentation)",
"is_bot": false,
"headline": "chore(release): bump agent-knowledge to 1.10.0 (#38)",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-06-25T01:26:01Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "7013216442f1cf5dbf911b2d8da7ebd277b2ee99",
"body": "…lan (#37)\n\nFour AgentProfile sketches for the research/knowledge domain (researcher\nworker, verifier driver, research supervisor, thin dedup-verifier), informed\nby emilkowalski/skills' skill shape and the dedup insight (the verifier is a\nthin lens over the deterministic validator, not a heavy re-ju\n[…]\n status (exists at tangle-network/supervisor-lab, the\ntwo-agent loop is already ported as bench/supervise-topology.ts) and a concrete\nplan to land these profiles + wire the thin verifier gate into it.",
"is_bot": false,
"headline": "docs: supervisor prompt + agent-profile ideas + supervisor-lab port p…",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-06-25T01:21:22Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "a137d7dae0817590c5d23082437fb0371dfe5f83",
"body": "* feat(research): instrument per-arm router cost (tokens/$/latency/calls) for the A/B\n\n* docs(results): live cost/quality numbers — the two-agent loop's ~5-9x inference premium\n\n* feat(research): claim-grounding verifier mode — catch misattributed citations the relevance judge can't\n\nThe cost/qualit\n[…]\novers the de-dup\nhalf of cleanliness). Rewrite the 'simpler loop' section to reflect what was\nactually built (adaptive driver + claim-grounding mode), with only the\nAgentProfile worker still deferred.",
"is_bot": false,
"headline": "feat(research): per-arm cost instrumentation for the two-agent A/B (#36)",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-06-25T01:21:10Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "c74d8ee1a4261394944f90425cadcef45505ba97",
"body": null,
"is_bot": false,
"headline": "docs: two-agent research A/B as a short paper (#35)",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-06-24T23:24:05Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "c8beaf6dc854b3fe0122637317f11cf65f0eb07d",
"body": "* docs: two-agent research-loop A/B — result + how to run\n\nPublic-facing writeup of the equal-compute A/B between the two-agent\nresearch loop (worker + verifying driver) and a single-agent\naccumulate-only loop. Records the real result (n=9 ML topics, glm-5.2:\n2.33 fewer admitted sources/topic at ide\n[…]\ns to validity, and the\nverified offline + live run commands. Links it from the README's\ntwo-agent research loop section.\n\n* docs: note the independent re-run reproduced the A/B (+2.67, CI [2.22,3.00])",
"is_bot": false,
"headline": "docs: two-agent research-loop A/B — result + how to run (#34)",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-06-24T23:02:51Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "4586f45b7425a929fd0fccf79196011a577a4a7b",
"body": null,
"is_bot": false,
"headline": "chore(release): bump agent-knowledge to 1.9.0 (#33)",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-06-24T22:26:54Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "99e3bc8090f3dd78ed3e2e923f405d3e39dfcc06",
"body": "Replace the live A/B arm's skeleton (which ran the same offline naive\nproposer over a hardcoded pool with a junk/-prefix verifier) with a real,\nany-topic web-research worker and a real LLM verifying driver, so\nAGENT_KNOWLEDGE_LIVE=1 runs a genuine experiment.\n\nsrc/web-research-worker.ts (general, no\n[…]\nsearched, and reports\nadmitted-source count + coverage per arm with agent-eval's pairedBootstrap.\nThe offline arm is unchanged (CI, $0, deterministic) — the arm-runners gain\ndefaulted parameters only.",
"is_bot": false,
"headline": "feat(research): real web-research worker + genuinely-live A/B arm (#32)",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-06-24T22:20:51Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "48fcd7887d54e201d2c49ce3ba87a60ed490d607",
"body": null,
"is_bot": false,
"headline": "chore(release): bump agent-knowledge to 1.8.0 (#31)",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-06-24T21:37:25Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "1a7384d5ef610c83415c7bfe532d120e51dc977f",
"body": "…implify (#30)\n\nNon-breaking internal cleanup and test/doc coverage. No public export\nchanged, added, or removed (verified: zero export-line deltas across all\nmodified source files; new helpers stay out of the barrel).\n\nDedup (internal, non-exported helpers single-sourced):\n- isStructural/isStructur\n[…]\n holdout/corpus gate behaviour (minScenarioCount 0)\nso the scenario-corpus axis does not fail closed on a dimension the run-level\nreport cannot satisfy; document the hasHoldout fail-closed constraint.",
"is_bot": false,
"headline": "chore(agent-knowledge): modernize against runtime-0.77/eval-0.100 + s…",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-06-24T21:34:11Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "ba713dcc774ca69042248e2fbbdaa2c6a75d47c0",
"body": "…rch loop (#29)\n\nAnswer the VALUE question that #28 left open: the two-agent (verifying-driver)\nloop's mechanism is proven, but does it build a cleaner knowledge base than the\nsingle-agent loop AT THE SAME COMPUTE BUDGET? Comparing at equal rounds would\nhand the two-agent loop free verification comp\n[…]\nat equal compute, paired comparison of junk-admitted via\nagent-eval pairedBootstrap. Reuses both shipped loops, inProcessSandboxClient,\nthe readiness gate, and the substrate stats — reinvents nothing.",
"is_bot": false,
"headline": "test(research): equal-compute A/B for two-agent vs single-agent resea…",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-06-24T20:58:55Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "b09bccca766b7b906837baf954868065130dbe60",
"body": "…recursive-leaf skill (#28)\n\nAdd a two-agent sibling of runKnowledgeResearchLoop where BOTH agents research\nto grow ONE knowledge base, composing the existing KB atoms (initKnowledgeBase,\naddSourceText, applyKnowledgeWriteBlocks, buildEvalKnowledgeBundle /\nscoreKnowledgeReadiness, searchKnowledge) —\n[…]\n0 -> ^0.100.0 and sandbox ^0.4.0 -> ^0.8.0\n(0.9.1 pulls an unpublished sdk-core, so pin ^0.8.0). Migrate researcherProfile's\nfanout driver off the removed createDriver to the current Driver interface.",
"is_bot": false,
"headline": "feat(research): two-agent driver-worker research loop + supervisor + …",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-06-24T20:39:33Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "1b72e7e35c9e0ef85d77918f0df7cf947b6d6e45",
"body": "… aren't empty (#26)\n\n* fix(profiles): researcher reads opencode finalText so successful runs aren't parsed as empty\n\n* test(profiles): cover finalText parse paths; drop historical-narrative comment\n\nAddresses PR #26 audit: MEDIUM (no test coverage for finalText paths) + LOW\n(historical narrative in\n[…]\next no longer drops the real answer (isEmptyOutput guard).\n- Tests: assert citations/proposedWrites on the finalText paths; negative test for\n non-JSON finalText; regression test for the shadow case.",
"is_bot": false,
"headline": "fix(profiles): researcher reads opencode finalText so successful runs…",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-06-14T23:56:29Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "56b1d1fef7a1cdf916dfadaf9d4728b8f598272e",
"body": "Widen the agent-eval pin from `>=0.77.0 <0.80.0` to `^0.91.0` (the\nversion the rest of the fleet uses) and bump agent-runtime `^0.44.0`\nto `^0.50.0`. The old `<0.80` ceiling blocked a consistent fleet-wide\nagent-eval and risked a duplicate substrate install; both now resolve\nto a single agent-eval@0\n[…]\n winner across\niterations via `defaultSelectWinner`. Update the two tests that\nasserted the old driver's name/decision strings to the new\nDriverDecision contract (winner-selection behavior unchanged).",
"is_bot": false,
"headline": "chore(deps): widen agent-eval to ^0.91 + bump agent-runtime ^0.50 (#25)",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-06-14T00:56:25Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "ec52a135ea765bd07c5cecf2866ccf87cc9f24a6",
"body": null,
"is_bot": false,
"headline": "chore(release): bump agent-knowledge to 1.7.0 (#24)",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-06-05T00:04:58Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "28e18fd5b20af5ab85d5675724e5a8fb5d7163f1",
"body": "* feat(memory): add generic memory adapter and neo4j bridge\n\n* fix(memory): validate neo4j agent-memory sdk bridge\n\n* test(memory): preserve neo4j unsupported errors",
"is_bot": false,
"headline": "feat(memory): add adapter contract for agent memory (#23)",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-06-04T23:54:57Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d7b995ba93cff82f467e55844f2674972050c96f",
"body": "…blished 0.79.0\n\nThe 1.6.0 substrate bump pinned agent-eval ^0.77.0 (= >=0.77.0 <0.78.0 on a 0.x\nversion), which EXCLUDES the published 0.79.0 the fleet runs — installing 1.6.0\nnext to agent-eval 0.79.0 would resolve a second nested 0.77.x (dual-version type\nskew). Widen to >=0.77.0 <0.80.0 so it dedups to the consumer's 0.79.0. Verified\nlint/typecheck/build/test green against 0.79.0; --frozen-lockfile clean.",
"is_bot": false,
"headline": "chore(deps): widen agent-eval to >=0.77.0 <0.80.0 so 1.6.0 accepts pu…",
"author_name": "Drew Stone",
"author_login": "drewstone",
"committed_at": "2026-06-04T12:05:03Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "feebfd1492ef3b9cc57da3bf764be9f227f4b4bb",
"body": "…44.0 + docs to live API (#22)\n\nagent-knowledge was caret-trapped at agent-eval ^0.42.0 (>=0.42.0 <0.43.0, 35\nminors behind 0.77.0) and agent-runtime ^0.25.0 (19 behind 0.44.0), with an\nempty minimumReleaseAgeExclude that froze it under the 3-day install cooldown.\n\n- bump @tangle-network/agent-eval \n[…]\nariants, then\nknowledgeReleaseReport() folds the candidate/baseline RunRecords into release\nconfidence. README, AGENTS, architecture.md, and the release.ts docstring now\ndescribe only the current API.",
"is_bot": false,
"headline": "chore(deps): bump substrate to agent-eval ^0.77.0 / agent-runtime ^0.…",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-06-03T15:08:48Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "35519e30a5ee87a21072aaa1f816e0f31dae0a1b",
"body": "README orientation + npm provenance + OIDC-only publish since 1.5.1. First\nrelease via tokenless OIDC trusted publishing.",
"is_bot": false,
"headline": "chore(release): agent-knowledge 1.5.2 (#21)",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-06-02T12:38:10Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "b45fe705fb2f4085087066a8d5c83230a9155787",
"body": "Supersedes #18's provenance-on-token-path: pnpm signs provenance but doesn't\nmint the OIDC credential, and the NPM_TOKEN is dead. npm install -g npm@latest\n+ npm publish --provenance, drop NPM_TOKEN + setup-node registry-url. No\nworkspace deps so npm publish is safe. Needs the npmjs Trusted Publisher\n(org tangle-network, repo agent-knowledge, workflow publish.yml) configured once.",
"is_bot": false,
"headline": "chore(publish): OIDC-only tokenless npm publish (#20)",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-06-02T12:16:11Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "62a822bbdf85845277e63f7958baa81bd4bfa740",
"body": null,
"is_bot": false,
"headline": "ci: add npm provenance attestation to release publish (#18)",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-06-02T09:49:13Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "063c6eee5cca15f2a18b48f91af35f54fb776eef",
"body": "docs(readme): Table of Contents + 'Start here' orientation",
"is_bot": false,
"headline": "Merge pull request #17 from tangle-network/docs/readme-toc",
"author_name": "tangletools",
"author_login": "tangletools",
"committed_at": "2026-05-31T09:56:54Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "9495b16462caa8bfff471c1954a4a9e2faf9688d",
"body": "The content + code examples were already strong and accurate; the gap was\nnavigability — no ToC, and the doc led with a CLI dump + a long design bullet\nlist before orienting a newcomer. Adds:\n- an anchored Table of Contents over the existing sections, and\n- a \"Start here\" router: CLI (author/inspect\n[…]\nalKnowledgeBundle / runKnowledgeResearchLoop\n / researcher profile / runKnowledgeBaseOptimization / pluggable sources).\n\nNo API churn — all existing repo-specific examples are accurate and unchanged.",
"is_bot": false,
"headline": "docs(readme): add Table of Contents + \"Start here\" orientation",
"author_name": "Drew Stone",
"author_login": "drewstone",
"committed_at": "2026-05-31T09:56:30Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "891764c7679d680cad7302fbea900c7426eeacb8",
"body": "…^0.3.0\n\nsandbox was a runtime dependency but is only used as `import type`\n(SandboxEvent, CreateSandboxOptions, SandboxInstance) in two test files.\nAs a runtime dep it dragged sandbox@0.2.1 into every consumer's install\ngraph as a ghost alongside their own ^0.3.0 pin. Moving it to\ndevDependencies removes it from the consumer graph entirely; bumping to\n^0.3.0 keeps the test types current.",
"is_bot": false,
"headline": "fix(deps): move @tangle-network/sandbox to devDependencies + bump to …",
"author_name": "Drew Stone",
"author_login": "drewstone",
"committed_at": "2026-05-28T20:50:13Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "c5a82b2ad06d66ddf83e6b1797c80097202d4d45",
"body": "agent-knowledge depends on @tangle-network/agent-eval (substrate) and on\n@tangle-network/agent-runtime (runtime). The substrate MUST NOT import\nfrom either — type inversions are a smell, not a feature.\n\nDocuments the rule, lists the substrate primitives agent-knowledge\nconsumes from agent-eval (Anal\n[…]\nling layering sections in agent-eval/CLAUDE.md (PR\ntangle-network/agent-eval#118) and agent-runtime/CLAUDE.md (PR\ntangle-network/agent-runtime#67).\n\nCo-authored-by: Drew Stone <drewstone329@gmail.com>",
"is_bot": false,
"headline": "docs: add repo-layering section to AGENTS.md (#16)",
"author_name": "tangletools",
"author_login": "tangletools",
"committed_at": "2026-05-27T12:09:40Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "d50fb0283f6d0823960207849128e920c36db684",
"body": "…ve release report (#15)\n\nagent-eval 0.42.0 deleted the multi-shot orchestration. agent-knowledge's\noptimization.ts was a thin wrapper over the deleted runMultiShotOptimization;\nrelease.ts consumed its MultiShotOptimizationResult shape + the deleted\nreleaseTraceEvidenceFromMultiShotTrials.\n\nBREAKING\n[…]\nent-eval ^0.42.0 + agent-runtime ^0.25.0. This is the permanent fix for\nthe scoped-pin trap consumers needed (agent-knowledge no longer imports any\ndeleted symbol). typecheck + build + 99 tests green.",
"is_bot": false,
"headline": "feat(1.5.0)!: shed legacy KB-optimization orchestrator; campaign-nati…",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-05-26T12:18:27Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "2ed1ae35bd460fcbe0b8135347b6555aaa4ba189",
"body": null,
"is_bot": false,
"headline": "chore(1.4.0): bump — 1.3.0 was claimed by proposeFromFinding PR",
"author_name": "Drew Stone",
"author_login": "drewstone",
"committed_at": "2026-05-24T17:39:48Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "eaa165b5c3c699f0ac75e9c3b7a342e82bc5a7a9",
"body": "…#14)\n\nSource-grounded research profile that pairs with @tangle-network/agent-\nruntime/loops. The profile ships an AgentProfile, prompt formatter,\noutput adapter, and validator; the runtime kernel owns iteration,\nconcurrency, cost, and trace emission.\n\nThree invariants the validator enforces:\n - na\n[…]\nace isolation,\npropose-without-materialize, loose-output passthrough (raw[] preserves\nagent extras), and end-to-end runLoop through a stub sandbox.\n\nCo-authored-by: Drew Stone <drewstone329@gmail.com>",
"is_bot": false,
"headline": "feat(0.x): researcherProfile + multiHarnessResearcherFanout (1.3.0) (…",
"author_name": "tangletools",
"author_login": "tangletools",
"committed_at": "2026-05-24T17:39:19Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "331ac4628e6c716b95ffae4d6f9d935135c78823",
"body": "agent-knowledge is public — unlimited free hosted minutes. Self-hosted\nstaging-runner pool is reserved for the private agent repos; routing\npublic CI there congests the same runner the private workflows\ndepend on (agent-eval v0.30.0 publish queued behind staging load —\nreverting all three public repos: agent-eval (#63), agent-knowledge\n(this PR), agent-runtime (already on hosted)).",
"is_bot": false,
"headline": "ci: revert public-repo workflows to ubuntu-latest (#13)",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-05-20T10:24:39Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "2c5506cc67649ab2c2a2a4ac422dd30ccc6e5df5",
"body": null,
"is_bot": false,
"headline": "docs: add open source license",
"author_name": "Drew Stone",
"author_login": "drewstone",
"committed_at": "2026-05-20T09:27:42Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "93e56ba9eb0e1d1394c73f858c0f3573d3fcaa65",
"body": null,
"is_bot": false,
"headline": "ci: use self-hosted runners (#11)",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-05-20T09:20:53Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "12911b09425fe118d157cbfddc24e43d3b7a6d4f",
"body": null,
"is_bot": false,
"headline": "chore(1.3.0): bump for proposeFromFinding; agent-eval ^0.29.1",
"author_name": "Drew Stone",
"author_login": "drewstone",
"committed_at": "2026-05-20T08:47:53Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "e3c3df928b4204a29f0f7a9458d119b31e24346d",
"body": "Closes the analysis → wiki side of the recursive-self-improvement\nloop. A knowledge-gap or knowledge-poisoning finding produced by an\nanalyst now converts directly into a typed `KnowledgeProposal` an\noperator (or auto-merge bot) can review and apply through the\nexisting `applyKnowledgeWriteBlocks` p\n[…]\n - unsafe slug characters sanitised\n - batch helper partitions proposals / skipped / errors\n\nBumps `@tangle-network/agent-eval` peer to `^0.28.0` (AnalystFinding +\ntyped kinds shipped there in #56).",
"is_bot": false,
"headline": "feat(propose): bridge AnalystFinding → KnowledgeProposal (#9)",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-05-19T11:59:09Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "7c942773d51c313f25b114c0c5b42d073acccc77",
"body": null,
"is_bot": false,
"headline": "docs(agents): no historical narrative + no fallbacks rule",
"author_name": "Drew Stone",
"author_login": "drewstone",
"committed_at": "2026-05-17T14:18:44Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "bcbb8470faf2dc13d6e1aad7ae1ca3f8ed90fe5d",
"body": "Mirrors the tangle-network/agent-runtime publish workflow. Tag push\nfires verify (lint+typecheck+test+build+version-lock check), then\npublish (idempotent — skips if version already on npm registry).\nRequires NPM_TOKEN repo secret.\n\nCo-authored-by: Drew Stone <drewstone329@gmail.com>",
"is_bot": false,
"headline": "ci: add publish.yml — auto-publish to npm on v* tag push (#8)",
"author_name": "tangletools",
"author_login": "tangletools",
"committed_at": "2026-05-14T21:57:56Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "4daba13ca46ea344bba83c2d59cc40a5e3fa250d",
"body": "… (#7)\n\nStatic knowledge ships information rot — FTC non-compete rule vacated by Ryan\nLLC v. FTC (2024), Beverly-Killea → RULLCA, DTSA section confusion. This adds\nthe primitives that bridge \"live authority\" to \"eval re-runs\":\n\n- `KnowledgeSource` contract (`src/sources/types.ts`): pluggable `fetch(\n[…]\nnst. Verified\nagainst real Cornell LII (18 USC § 1836 + Wex restraint_of_trade), IRS\npublications index + p15, and CA SOS forms page on 2026-05-14.\n\nCo-authored-by: Drew Stone <drewstone329@gmail.com>",
"is_bot": false,
"headline": "feat(0.x): pluggable knowledge sources + freshness + change detection…",
"author_name": "tangletools",
"author_login": "tangletools",
"committed_at": "2026-05-14T17:34:57Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "c9f619f966b7fc8fe3933caabd85983915f73d9b",
"body": "Mirrors the directive in agent-eval's CLAUDE.md. Applies to every\ncontributor, including AI agents and subagents.",
"is_bot": false,
"headline": "chore(authorship): forbid Co-Authored-By trailers (#6)",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-05-08T23:39:46Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "860ede6dfef559382df7a852bdf240d9f9aa9be4",
"body": "…(#5)\n\n0.21 -> 0.23 added: capture-integrity primitives (RawProviderSink,\nassertLlmRoute, assertRunCaptured, onRunComplete hooks), the campaign\nartifact (runEvalCampaign, replayCache, sequential pairedEvalueSequence,\nresearchReport, rubricPredictiveValidity), and the RL bridge subpath\n(@tangle-network/agent-eval/rl: extractPreferences,\nanalyzeOptimizationResult, etc.).\n\nMechanical version bump only. Typecheck, tests (12/12), and build all\npass; no behavior changes expected.",
"is_bot": false,
"headline": "chore(deps): bump @tangle-network/agent-eval from ^0.20.0 to ^0.23.0 …",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-05-08T23:12:12Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "2d484a39b9488cd233dbe10e95aedd87d67eaeb2",
"body": null,
"is_bot": false,
"headline": "feat: add knowledge control-loop adapter (#4)",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-05-08T10:01:58Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "2be2b9a1f4351d1c41a06479e3accf8c85e1954c",
"body": "…C_DEFAULTS (#3)\n\n* feat(eval-readiness): add defineReadinessSpec builder + READINESS_SPEC_DEFAULTS\n\nKnowledgeReadinessSpec has eleven required fields. Most consumers — physim,\nblueprint-agent, gtm-agent, legal-agent, creative-agent — only meaningfully\nset four (id, description, query, requiredFor) \n[…]\ns, secrets that need\n sensitivity=secret, etc.).\n\nPurely additive — existing consumers that hand-roll the full spec keep\nworking. New consumers get a one-liner.\n\n* feat: add knowledge research loop",
"is_bot": false,
"headline": "feat(eval-readiness): add defineReadinessSpec builder + READINESS_SPE…",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-05-08T09:46:49Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "100b72f918d70110930dba8d26cd05bb96f15ac0",
"body": null,
"is_bot": false,
"headline": "feat: add source freshness readiness audit (#2)",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-05-04T14:54:00Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "177dadae6b25712d51b9a334e5f045400f03c487",
"body": "* fix(indexer): exclude scaffold files (index.md, log.md) from page index\n\ninitKnowledgeBase writes knowledge/index.md and knowledge/log.md as\nhuman-navigation scaffolds, but loadKnowledgePages was returning them as\ncontent pages. That inflated index.pages.length, polluted search hits,\nand forced do\n[…]\ne\nconfidence — documented in the type, README, and a test that pins\nscore === rrfScore, top.normalizedScore === 1, and the linear relationship.\n\n* feat(readiness): bridge knowledge index to agent-eval",
"is_bot": false,
"headline": "feat(readiness): bridge knowledge index to agent-eval (#1)",
"author_name": "drewstone",
"author_login": "drewstone",
"committed_at": "2026-05-03T18:48:22Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "8faeef4a0a9d64a77fa9258c55c41ed69cd6b482",
"body": null,
"is_bot": false,
"headline": "feat(v1): add knowledge store and discovery contracts",
"author_name": "Drew Stone",
"author_login": "drewstone",
"committed_at": "2026-05-03T15:29:03Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "49eee0cfba1f74010faaa9d4227f40c590d55177",
"body": null,
"is_bot": false,
"headline": "chore(release): 0.1.1",
"author_name": "Drew Stone",
"author_login": "drewstone",
"committed_at": "2026-05-03T15:18:01Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "5b8b7aa6f138ca7cf7164c93f2e76c6925a6dd40",
"body": null,
"is_bot": false,
"headline": "feat(cli): add agent-first knowledge workflows",
"author_name": "Drew Stone",
"author_login": "drewstone",
"committed_at": "2026-05-03T15:15:57Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "6d35a49237c1c77c380c6db0e7e66e9ffc53e4e3",
"body": null,
"is_bot": false,
"headline": "feat(sources): validate knowledge provenance",
"author_name": "Drew Stone",
"author_login": "drewstone",
"committed_at": "2026-05-03T09:47:17Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "5a62daced50c7c48d5332d185ee3f288d096d297",
"body": null,
"is_bot": false,
"headline": "feat(core): scaffold agent knowledge package",
"author_name": "Drew Stone",
"author_login": "drewstone",
"committed_at": "2026-05-03T09:44:53Z",
"body_truncated": false,
"is_coding_agent": false
}
],
"releases_count": 25,
"commits_last_year": 85,
"latest_release_at": "2026-07-18T17:51:48Z",
"latest_release_tag": "v4.1.0",
"releases_from_tags": true,
"days_since_last_push": 0,
"active_weeks_last_year": 12,
"days_since_latest_release": 5,
"mean_days_between_releases": 0.5
},
"community": {
"has_readme": true,
"has_license": true,
"has_description": true,
"has_contributing": false,
"health_percentage": 37,
"has_issue_template": false,
"has_code_of_conduct": false,
"has_pull_request_template": false
},
"ecosystem": {
"packages": [
{
"name": "@tangle-network/agent-knowledge",
"exists": true,
"license": "MIT",
"keywords": [],
"ecosystem": "npm",
"matches_repo": true,
"registry_url": "https://www.npmjs.com/package/@tangle-network/agent-knowledge",
"is_deprecated": false,
"latest_version": "4.1.0",
"repository_url": "https://github.com/tangle-network/agent-knowledge",
"versions_count": 31,
"total_downloads": null,
"dependents_count": null,
"deprecation_note": null,
"maintainers_count": 4,
"monthly_downloads": 13588,
"first_published_at": "2026-05-03T15:16:17.375000Z",
"latest_published_at": "2026-07-18T17:53:59.017000Z",
"latest_version_yanked": null,
"days_since_latest_publish": 5
}
]
},
"popularity": {
"forks": 0,
"stars": 0,
"watchers": 0,
"fork_history": {
"days": [],
"complete": true,
"collected": 0,
"total_forks": 0
},
"star_history": {
"days": [],
"complete": true,
"collected": 0,
"total_stars": 0,
"collected_at": null
},
"open_issues_and_prs": 0
},
"ai_readiness": {
"has_nix": false,
"example_dirs": [],
"has_llms_txt": false,
"has_dockerfile": false,
"has_mcp_signal": false,
"bootstrap_files": [],
"api_schema_files": [],
"has_devcontainer": false,
"typecheck_configs": [
"tsconfig.json"
],
"toolchain_manifests": [],
"largest_source_bytes": 36856,
"source_files_sampled": 179,
"oversized_source_files": 0,
"agent_instruction_files": [
"AGENTS.md"
],
"agent_instruction_max_bytes": 5626
},
"dependencies": {
"manifests": [
"package.json"
],
"advisories": {
"error": null,
"scope": "published_package",
"source": "osv",
"findings": [],
"collected": true,
"malicious": [],
"truncated": false,
"by_severity": {},
"advisory_count": 0,
"affected_count": 0,
"assessed_count": 41,
"malicious_count": 0,
"assessed_package": "npm:@tangle-network/agent-knowledge@4.1.0",
"unassessed_count": 0,
"direct_affected_count": 0
},
"ecosystems": [
"npm"
],
"dependencies": [
{
"name": "@tangle-network/agent-eval",
"manifest": "package.json",
"ecosystem": "npm",
"version_constraint": "^0.123.8"
},
{
"name": "@tangle-network/agent-interface",
"manifest": "package.json",
"ecosystem": "npm",
"version_constraint": "^0.31.0"
},
{
"name": "proper-lockfile",
"manifest": "package.json",
"ecosystem": "npm",
"version_constraint": "4.1.2"
},
{
"name": "zod",
"manifest": "package.json",
"ecosystem": "npm",
"version_constraint": "^4.4.3"
}
],
"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": 73,
"open_issues": 0,
"closed_ratio": null,
"closed_issues": 0,
"closed_unmerged_prs": 4
},
"bus_factor": 1,
"bot_contributors": 0,
"top_contributors": [
{
"type": "User",
"login": "drewstone",
"commits": 82,
"avatar_url": "https://avatars.githubusercontent.com/u/13153687?v=4"
},
{
"type": "User",
"login": "tangletools",
"commits": 5,
"avatar_url": "https://avatars.githubusercontent.com/u/254741087?v=4"
}
],
"contributors_sampled": 2,
"top_contributor_share": 0.943
},
"quality_signals": {
"has_ci": true,
"has_tests": true,
"ci_workflows": [
"ci.yml",
"publish.yml"
],
"has_docs_dir": true,
"linter_configs": [
"biome.json"
],
"has_editorconfig": false,
"has_linter_config": true,
"has_precommit_config": false
},
"security_signals": {
"lockfiles": [
"pnpm-lock.yaml"
],
"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": null,
"reason": "internal error: error during branchesHandler.setup: internal error: some github tokens can't read classic branch protection rules: https://github.com/ossf/scorecard-action/blob/main/docs/authentication/fine-grained-auth-token.md",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#branch-protection"
},
{
"name": "CI-Tests",
"score": 10,
"reason": "28 out of 28 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": 10,
"reason": "all changesets reviewed",
"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": 0,
"reason": "project is not fuzzed",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#fuzzing"
},
{
"name": "License",
"score": 9,
"reason": "license file detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#license"
},
{
"name": "Maintained",
"score": 0,
"reason": "project was created within the last 90 days. Please review its contents carefully",
"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": 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": 5,
"reason": "5 existing vulnerabilities detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#vulnerabilities"
}
],
"commit": "95ae68270082c1cedbc0b1983c3b65c954875dda",
"ran_at": "2026-07-24T03:44:19Z",
"aggregate_score": 4,
"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": "2026-07-24T01:51:56Z",
"oldest_open_prs": [],
"last_merged_pr_at": "2026-07-24T01:50:55Z",
"ci_last_conclusion": "SUCCESS",
"oldest_open_issues": []
}
},
"config": {
"disabled_metrics": [],
"disabled_categories": [],
"disabled_components": {}
},
"source": {
"url": "https://github.com/tangle-network/agent-knowledge",
"host": "github.com",
"name": "agent-knowledge",
"owner": "tangle-network"
},
"metrics": {
"overall": {
"key": "overall",
"band": "moderate",
"name": "Overall health",
"note": null,
"notes": [],
"value": 62,
"inputs": {
"security": 52,
"vitality": 72,
"community": 33,
"governance": 68,
"engineering": 80
},
"components": []
},
"categories": [
{
"key": "vitality",
"band": "good",
"name": "Vitality",
"value": 72,
"weight": 0.22,
"metrics": [
{
"key": "development_activity",
"band": "moderate",
"name": "Development activity",
"note": null,
"notes": [],
"value": 62,
"inputs": {
"commits_last_year": 85,
"human_commit_share": 1,
"days_since_last_push": 0,
"active_weeks_last_year": 12
},
"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": "12/52 weeks with commits",
"points": 8.3,
"status": "partial",
"details": [
{
"code": "commit_cadence_weeks",
"params": {
"weeks": 12
}
}
],
"max_points": 36
},
{
"key": "commit_volume",
"name": "Commit volume",
"detail": "85 commits in the last year",
"points": 17.4,
"status": "partial",
"details": [
{
"code": "commits_last_year",
"params": {
"count": 85
}
}
],
"max_points": 18
},
{
"key": "openssf_scorecard_maintained",
"name": "OpenSSF Scorecard: Maintained",
"detail": "project was created within the last 90 days. Please review its contents carefully",
"points": 0,
"status": "missed",
"details": [],
"max_points": 10
}
]
},
{
"key": "release_discipline",
"band": "excellent",
"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": 88,
"inputs": {
"releases_count": 25,
"latest_release_tag": "v4.1.0",
"releases_from_tags": true,
"days_since_latest_release": 5,
"mean_days_between_releases": 0.5
},
"components": [
{
"key": "ships_releases",
"name": "Ships releases",
"detail": "25 version tags (no GitHub releases)",
"points": 16.2,
"status": "partial",
"details": [
{
"code": "version_tags_no_releases",
"params": {
"count": 25
}
}
],
"max_points": 27
},
{
"key": "release_recency",
"name": "Release recency",
"detail": "latest release 5 days ago",
"points": 36,
"status": "met",
"details": [
{
"code": "release_recency",
"params": {
"days": 5
}
}
],
"max_points": 36
},
{
"key": "release_cadence",
"name": "Release cadence",
"detail": "a release every ~0.5 days",
"points": 27,
"status": "met",
"details": [
{
"code": "release_cadence",
"params": {
"gap": 0.5
}
}
],
"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": "excellent",
"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": "at_risk",
"name": "Community & Adoption",
"value": 33,
"weight": 0.18,
"metrics": [
{
"key": "popularity",
"band": "critical",
"name": "Popularity & adoption",
"note": null,
"notes": [],
"value": 1,
"inputs": {
"forks": 0,
"stars": 0,
"watchers": 0,
"growth_state": "unverified",
"growth_factor_pct": 100,
"growth_unverified_reason": "no_history"
},
"components": [
{
"key": "stars",
"name": "Stars",
"detail": "0 stars",
"points": 0,
"status": "missed",
"details": [
{
"code": "stars",
"params": {
"count": 0
}
}
],
"max_points": 60
},
{
"key": "forks",
"name": "Forks",
"detail": "0 forks",
"points": 0,
"status": "missed",
"details": [
{
"code": "forks",
"params": {
"count": 0
}
}
],
"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": "at_risk",
"name": "Community health",
"note": null,
"notes": [],
"value": 44,
"inputs": {
"has_readme": true,
"has_license": true,
"has_contributing": false,
"has_issue_template": false,
"has_code_of_conduct": false,
"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": "license file present, not a recognized license",
"points": 16.9,
"status": "partial",
"details": [
{
"code": "license_custom",
"params": {}
}
],
"max_points": 22.5
},
{
"key": "contributing_guide",
"name": "CONTRIBUTING guide",
"detail": null,
"points": 0,
"status": "missed",
"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": "moderate",
"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": 69,
"inputs": {
"packages": [
"@tangle-network/agent-knowledge"
],
"dependents": null,
"ecosystems": "npm",
"total_downloads": null,
"monthly_downloads": 13588
},
"components": [
{
"key": "monthly_downloads",
"name": "Monthly downloads",
"detail": "13,588 downloads/month across npm",
"points": 55.1,
"status": "partial",
"details": [
{
"code": "downloads_monthly",
"params": {
"count": 13588,
"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": "moderate",
"name": "Sustainability & Governance",
"value": 68,
"weight": 0.24,
"metrics": [
{
"key": "maintainer_resilience",
"band": "critical",
"name": "Maintainer resilience (bus factor)",
"note": null,
"notes": [],
"value": 16,
"inputs": {
"bus_factor": 1,
"contributors_sampled": 2,
"top_contributor_share": 0.943
},
"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 94% of commits",
"points": 1.3,
"status": "partial",
"details": [
{
"code": "top_contributor_share",
"params": {
"share": 94
}
}
],
"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": "excellent",
"name": "Issue & PR responsiveness",
"note": "Excluded from scoring (no data or not applicable): Issue resolution. Remaining weights renormalized.",
"notes": [
{
"code": "excluded_no_data",
"params": {
"components": [
"issue_resolution"
]
}
},
{
"code": "weights_renormalized",
"params": {}
}
],
"value": 96,
"inputs": {
"merged_prs": 73,
"open_issues": 0,
"closed_issues": 0,
"issue_closed_ratio": null,
"closed_unmerged_prs": 4
},
"components": [
{
"key": "issue_resolution",
"name": "Issue resolution",
"detail": "no issues or no data",
"points": 0,
"status": "excluded",
"details": [
{
"code": "no_issues_or_data",
"params": {}
}
],
"max_points": 46.75
},
{
"key": "pr_acceptance",
"name": "PR acceptance",
"detail": "73/77 decided PRs merged",
"points": 36.3,
"status": "partial",
"details": [
{
"code": "decided_prs_merged",
"params": {
"merged": 73,
"decided": 77
}
}
],
"max_points": 38.25
},
{
"key": "openssf_scorecard_code_review",
"name": "OpenSSF Scorecard: Code-Review",
"detail": "all changesets reviewed",
"points": 15,
"status": "met",
"details": [],
"max_points": 15
}
]
},
{
"key": "stewardship",
"band": "good",
"name": "Ownership & stewardship",
"note": null,
"notes": [],
"value": 75,
"inputs": {
"followers": 758,
"owner_type": "Organization",
"is_verified": null,
"owner_login": "tangle-network",
"public_repos": 248,
"account_age_days": 2029
},
"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": "758 followers of tangle-network",
"points": 20.7,
"status": "partial",
"details": [
{
"code": "owner_followers",
"params": {
"count": 758,
"login": "tangle-network"
}
}
],
"max_points": 25
},
{
"key": "track_record",
"name": "Track record",
"detail": "248 public repos, account ~5 yr old",
"points": 24.1,
"status": "partial",
"details": [
{
"code": "public_repos",
"params": {
"count": 248
}
},
{
"code": "account_age_years",
"params": {
"years": 5
}
}
],
"max_points": 25
}
]
},
{
"key": "package_maintenance",
"band": "excellent",
"name": "Package maintenance",
"note": null,
"notes": [],
"value": 100,
"inputs": {
"packages": [
"@tangle-network/agent-knowledge"
],
"ecosystems": "npm",
"any_deprecated": false,
"min_days_since_publish": 5
},
"components": [
{
"key": "published_resolvable",
"name": "Published & resolvable",
"detail": "1 package(s) on npm",
"points": 25,
"status": "met",
"details": [
{
"code": "packages_published",
"params": {
"count": 1,
"ecosystems": "npm"
}
}
],
"max_points": 25
},
{
"key": "publish_recency",
"name": "Publish recency",
"detail": "latest publish 5 days ago",
"points": 35,
"status": "met",
"details": [
{
"code": "publish_recency",
"params": {
"days": 5
}
}
],
"max_points": 35
},
{
"key": "version_history",
"name": "Version history",
"detail": "31 published versions",
"points": 20,
"status": "met",
"details": [
{
"code": "published_versions",
"params": {
"count": 31
}
}
],
"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": 80,
"weight": 0.2,
"metrics": [
{
"key": "engineering_practices",
"band": "good",
"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": "2 workflow(s)",
"points": 24,
"status": "met",
"details": [
{
"code": "ci_workflows",
"params": {
"count": 2
}
}
],
"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": "biome.json",
"points": 16,
"status": "met",
"details": [
{
"code": "file_list",
"params": {
"files": "biome.json"
}
}
],
"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": "28 out of 28 merged PRs checked by a CI test -- score normalized to 10",
"points": 20,
"status": "met",
"details": [],
"max_points": 20
}
]
},
{
"key": "documentation",
"band": "good",
"name": "Documentation",
"note": null,
"notes": [],
"value": 75,
"inputs": {
"topics": [],
"has_wiki": true,
"homepage": null,
"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": null,
"points": 0,
"status": "missed",
"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": "moderate",
"name": "Security",
"value": 52,
"weight": 0.16,
"metrics": [
{
"key": "security_posture",
"band": "at_risk",
"name": "Security posture",
"note": "Excluded from scoring (no data or not applicable): Branch-Protection, Packaging, Signed-Releases. Remaining weights renormalized.",
"notes": [
{
"code": "excluded_no_data",
"params": {
"components": [
"branch_protection",
"packaging",
"signed_releases"
]
}
},
{
"code": "weights_renormalized",
"params": {}
}
],
"value": 40,
"inputs": {
"source": "openssf_scorecard",
"checks_evaluated": 15,
"scorecard_version": "v5.5.0",
"checks_inconclusive": 3,
"scorecard_aggregate": 4
},
"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": "internal error: error during branchesHandler.setup: internal error: some github tokens can't read classic branch protection rules: https://github.com/ossf/scorecard-action/blob/main/docs/authentication/fine-grained-auth-token.md",
"points": 0,
"status": "excluded",
"details": [
{
"code": "no_data",
"params": {}
}
],
"max_points": 7.5
},
{
"key": "ci_tests",
"name": "CI-Tests",
"detail": "28 out of 28 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": "all changesets reviewed",
"points": 7.5,
"status": "met",
"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 not fuzzed",
"points": 0,
"status": "missed",
"details": [],
"max_points": 5
},
{
"key": "license",
"name": "License",
"detail": "license file detected",
"points": 2.2,
"status": "partial",
"details": [],
"max_points": 2.5
},
{
"key": "maintained",
"name": "Maintained",
"detail": "project was created within the last 90 days. Please review its contents carefully",
"points": 0,
"status": "missed",
"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 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": "5 existing vulnerabilities detected",
"points": 3.8,
"status": "partial",
"details": [],
"max_points": 7.5
}
]
},
{
"key": "dependency_advisories",
"band": "excellent",
"name": "Dependency advisories",
"note": "Excluded from scoring (no data or not applicable): No advisories left outstanding. Remaining weights renormalized. Matched the npm:@tangle-network/agent-knowledge@4.1.0 runtime dependency closure — what installing the published package pulls in — 41 packages. Reachability is not analyzed.",
"notes": [
{
"code": "excluded_no_data",
"params": {
"components": [
"no_advisories_left_outstanding"
]
}
},
{
"code": "weights_renormalized",
"params": {}
},
{
"code": "advisories_scope_published",
"params": {
"package": "npm:@tangle-network/agent-knowledge@4.1.0",
"assessed": 41
}
},
{
"code": "advisories_reachability",
"params": {}
}
],
"value": 100,
"inputs": {
"source": "osv",
"advisories": 0,
"affected_packages": 0,
"assessed_packages": 41,
"unassessed_packages": 0,
"affected_by_severity": "none",
"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": "no indirect dependency carries a known advisory",
"points": 25,
"status": "met",
"details": [
{
"code": "no_indirect_advisories",
"params": {}
}
],
"max_points": 25
},
{
"key": "no_advisories_left_outstanding",
"name": "No advisories left outstanding",
"detail": "no advisory carries a publication date",
"points": 0,
"status": "excluded",
"details": [
{
"code": "advisories_no_publication_date",
"params": {}
}
],
"max_points": 40
}
]
},
{
"key": "malicious_dependencies",
"band": "excellent",
"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": 41,
"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": "excellent",
"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"
],
"review_only_matches": 0,
"assessed_self_published_locations": 1
},
"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": 73,
"weight": 0,
"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": [
"AGENTS.md"
],
"agent_instruction_max_bytes": 5626
},
"components": [
{
"key": "agent_instructions",
"name": "Agent instructions",
"detail": "AGENTS.md",
"points": 45,
"status": "met",
"details": [
{
"code": "file_list",
"params": {
"files": "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": "87 of 87 human commits state their intent (structured subject or explanatory body)",
"points": 40,
"status": "met",
"details": [
{
"code": "legible_history",
"params": {
"legible": 87,
"sampled": 87
}
}
],
"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": [
"pnpm-lock.yaml"
],
"has_dockerfile": false,
"typed_language": true,
"bootstrap_files": [],
"has_devcontainer": false,
"has_linter_config": true,
"typecheck_configs": [
"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": "biome.json",
"points": 11,
"status": "met",
"details": [
{
"code": "file_list",
"params": {
"files": "biome.json"
}
}
],
"max_points": 11
},
{
"key": "static_type_checking",
"name": "Static type checking",
"detail": "tsconfig.json",
"points": 11,
"status": "met",
"details": [
{
"code": "file_list",
"params": {
"files": "tsconfig.json"
}
}
],
"max_points": 11
},
{
"key": "reproducible_environment",
"name": "Reproducible environment",
"detail": "lockfile",
"points": 10,
"status": "met",
"details": [
{
"code": "file_list",
"params": {
"files": "lockfile"
}
}
],
"max_points": 10
},
{
"key": "demonstrated_agent_practice",
"name": "Demonstrated agent practice",
"detail": "no agent-authored commits among the last 87",
"points": 0,
"status": "missed",
"details": [
{
"code": "no_agent_authored_commits",
"params": {
"sampled": 87
}
}
],
"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": 100,
"inputs": {
"primary_language": "TypeScript",
"largest_source_bytes": 36856,
"source_files_sampled": 179,
"oversized_source_files": 0
},
"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": "0/179 source files over 60KB",
"points": 55,
"status": "met",
"details": [
{
"code": "oversized_source_files",
"params": {
"kb": 60,
"sampled": 179,
"oversized": 0
}
}
],
"max_points": 55
}
]
}
],
"description": "How well is the repo equipped to be developed and maintained with AI coding agents? An independent, experimental badge — weight 0.0, so it is surfaced on its own and does not affect the overall health score."
}
],
"metrics_version": "1.13.0"
},
"warnings": [
"GitHub dependency-graph SBOM unavailable (404); the dependency graph may be disabled for this repository"
],
"report_type": "repository",
"generated_at": "2026-07-24T03:44:35.767732Z",
"schema_version": "0.27.0",
"badge_url": "https://raw.githubusercontent.com/inspect-software/badges/main/v1/t/tangle-network/agent-knowledge.svg",
"full_name": "tangle-network/agent-knowledge",
"license_state": "custom",
"license_spdx": null
}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 v1.13.0, schema v0.27.0 — full methodology · metrics wiki.
How one result sits in the wider record: aggregate statistics — npm.