Public record
Software health reportschema 0.34.0 · metrics 2.10.0 · 2026-10-23 04:58 UTC

core-aix / agitrack

Every agent turn becomes a traceable commit carrying the full interaction trace, model, and token cost, plus a live dashboard and a coach that teaches you, from your own sessions, to drive agents and your codebase better.

PythonApache-2.0★ 24 stars⑂ 1 forksince Jun 2026View on GitHub ↗
KindCommand-line toolLibraryhow this is determined
#ai-agents#ai-coding#coding-agents#efficiency#historical-data#learn-to-code#prompt#traceability

core-aix/agitrack holds a health index of 78 out of 100, placing it in the Good band. It scores highest on AI Readiness (88/100) and lowest on Community & Adoption (46/100). It was last updated today. A single contributor accounts for most of its recent work.

78
overall / 100
Good

Software health index

Metrics are grouped into weighted categories on one standardized 1–100 scale. Overall starts as their weighted mean, calibrated against the distribution of the public record so bands carry percentile meaning; when public evidence triggers the High-Risk Jurisdiction Policy, the rating is adjusted and receives an At Risk ceiling of 34.

78
Exceptional93-100The record's top tier (≈ top 5%); essentially all checked criteria met
Excellent80-92Strong across the board; minor gaps
Good65-79Healthy; gaps are limited and manageable
Moderate50-64Acceptable with notable gaps; review recommended
Weak35-49Material weaknesses across several areas
At Risk20-34Significant weaknesses; adoption warrants caution
Critical1-19Severe problems (abandoned, single-maintainer, no hygiene)
VitalityCommunity &AdoptionSustainability &GovernanceEngineeringQualitySecurityAI Readiness

Score profile

Each axis is a category. The shape matters more than the average — a healthy subject fills the whole shape, while a spike-and-crater profile means strength in one dimension is masking risk in another.

The weighted overall 67 is calibrated to 78 on the published index scale (record calibration 2026-08-02).

Ownership

core-aixOrganization
1 follower9 public repossince Nov 2025

This repository is backed by an organization — shared, accountable stewardship that can outlive any single maintainer.

Package ecosystems

RegistryPackageVersionDownloads / moVersionsLast publish
PyPIagitrack0.6.30918860 days ago

Metrics by category

Vitality

Is the project alive — is code being written and are releases shipping?

83Excellent · 21% of overall

Development activity

78Good
How it's scored
36/36Push recency — last push 0 days ago
13.8/36Commit cadence — 20/52 weeks with commits
18/18Commit volume — 1,174 commits in the last year
10/10OpenSSF Scorecard: Maintained — 30 commit(s) and 4 issue activity found in the last 90 days -- score normalized to 10
Inputs used
commits_last_year1,174
human_commit_share0.82
days_since_last_push0
active_weeks_last_year20

Release discipline

90Excellent
How it's scored
27/27Ships releases — 88 releases published
36/36Release recency — latest release 0 days ago
27/27Release cadence — a release every ~5.5 days
0/10OpenSSF Scorecard: Signed-Releases — Project has not signed or included provenance with any releases.
Inputs used
releases_count88
latest_release_tagv0.6.30
releases_from_tagsno
days_since_latest_release0
mean_days_between_releases5.5

Community & Adoption

Does the project have users, downloads, attention, and a welcoming setup for contributors?

46Weak · 17% of overall

Popularity & adoption

22At Risk
How it's scored
22.1/60Stars — 24 stars
0/25Forks — 1 forks
0/15Watchers — 0 watchers
Inputs used
forks1
stars24
watchers0
growth_stateunverified
growth_factor_pct100
growth_unverified_reasonno_history

Community health

70Good
How it's scored
22.5/22.5README
22.5/22.5License — recognized license (Apache-2.0)
18/18CONTRIBUTING guide
0/13.5Code of conduct
0/7.2Issue template
0/6.3PR template
Inputs used
has_readmeyes
has_licenseyes
readme_badges3
has_contributingyes
has_issue_templateno
has_code_of_conductno
readme_badge_servicesshields.io
has_pull_request_templateno

Ecosystem adoption (downloads)

49Weak
How it's scored
39.5/80Monthly downloads — 918 downloads/month across pypi
0/20Registry dependents — not reported by this ecosystem
Inputs used
packagesagitrack
dependents—
ecosystemspypi
total_downloads—
monthly_downloads918
unverified_packages_excluded—
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?

56Moderate · 23% of overall

Maintainer resilience (bus factor)

18Critical
How it's scored
9/54Bus factor — 1 contributor(s) cover half of all commits
0.7/22.5Commit distribution — top contributor authored 97% of commits
5.4/13.5Contributor breadth — 4 contributors
3/10OpenSSF Scorecard: Contributors — project has 1 contributing companies or organizations -- score normalized to 3
Inputs used
bus_factor1
contributors_sampled4
top_contributor_share0.967

Issue & PR responsiveness

80Excellent
How it's scored
40.6/42Issue resolution — 97% of issues closed
29.2/30PR acceptance — 241/248 decided PRs merged
0/13Newcomer PR acceptance — no first-time contributor's PR decided in 30d
0/15OpenSSF Scorecard: Code-Review — Found 0/8 approved changesets -- score normalized to 0
Inputs used
merged_prs241
open_issues2
closed_issues57
prs_merged_7d4
prs_decided_7d4
prs_merged_30d8
prs_decided_30d8
issue_closed_ratio0.966
closed_unmerged_prs7
first_time_authors_30d0
first_time_prs_merged_30d0
first_time_prs_decided_30d0
Excluded from scoring (no data or not applicable): Newcomer PR acceptance. Remaining weights renormalized.

Ownership & stewardship

41Weak
How it's scored
30/30Ownership backing — organization-owned
0/20Verified domain
2.2/25Owner reach — 1 followers of core-aix
9.1/25Track record — 9 public repos, account ~0 yr old
Inputs used
followers1
owner_typeOrganization
is_verifiedno
owner_logincore-aix
public_repos9
account_age_days332

Package maintenance

100Exceptional
How it's scored
25/25Published & resolvable — 1 package(s) on pypi
35/35Publish recency — latest publish 0 days ago
20/20Version history — 86 published versions
20/20Not deprecated — active, not deprecated or yanked
Inputs used
packagesagitrack
ecosystemspypi
any_deprecatedno
min_days_since_publish0

Engineering Quality

Are baseline engineering and documentation practices in place?

86Excellent · 19% of overall

Engineering practices

84Excellent
How it's scored
24/24CI workflows — 8 workflow(s)
24/24Tests present
16/16Linter config — pyproject.toml ([tool.ruff])
9.6/9.6Pre-commit hooks
0/6.4.editorconfig
10/20OpenSSF Scorecard: CI-Tests — 4 out of 8 merged PRs checked by a CI test -- score normalized to 5
Inputs used
has_ciyes
has_testsyes
has_editorconfigno
has_linter_configyes
has_precommit_configyes

Documentation

90Excellent
How it's scored
30/30README
25/25Documentation directory
15/15Documentation / homepage site — http://agitrack.core-aix.org/
10/10Repository description
10/10Topics — 8 topics
0/10Wiki
Inputs used
topicsai-agents, ai-coding, coding-agents, efficiency, historical-data, learn-to-code, prompt, traceability
has_wikino
homepagehttp://agitrack.core-aix.org/
docs_sitehttp://agitrack.core-aix.org/
has_readmeyes
has_docs_diryes
has_descriptionyes

Security

Are visible security and supply-chain practices strong, without unresolved high-risk jurisdiction exposure?

59Moderate · 16% of overall

Security posture

49Weak
How it's scored
7.5/7.5Binary-Artifacts — no binaries found in the repo
0.8/7.5Branch-Protection — branch protection is not maximal on development and all release branches
1.2/2.5CI-Tests — 4 out of 8 merged PRs checked by a CI test -- score normalized to 5
0/2.5CII-Best-Practices — no effort to earn an OpenSSF best practices badge detected
0/7.5Code-Review — Found 0/8 approved changesets -- score normalized to 0
0.8/2.5Contributors — project has 1 contributing companies or organizations -- score normalized to 3
10/10Dangerous-Workflow — no dangerous workflow patterns detected
7.5/7.5Dependency-Update-Tool — update tool detected
0/5Fuzzing — project is not fuzzed
2.5/2.5License — license file detected
7.5/7.5Maintained — 30 commit(s) and 4 issue activity found in the last 90 days -- score normalized to 10
0/5Packaging — no data
1.5/5Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 3
4.5/5SAST — SAST tool detected but not run on all commits
5/5Security-Policy — security policy file detected
0/7.5Signed-Releases — Project has not signed or included provenance with any releases.
0/7.5Token-Permissions — detected GitHub workflow tokens with excessive permissions
0/7.5Vulnerabilities — 10 existing vulnerabilities detected
Inputs used
sourceopenssf_scorecard
checks_evaluated17
scorecard_versionv5.5.0
checks_inconclusive1
scorecard_aggregate4.9
Excluded from scoring (no data or not applicable): Packaging. Remaining weights renormalized.

Dependency advisories

100Exceptional
How it's scored
35/35Direct dependencies free of known advisories — no direct dependency carries a known advisory
0/25Indirect dependencies free of known advisories — transitive set not separable from development and test dependencies in this scope
0/40No advisories left outstanding — no advisory carries a publication date
Inputs used
sourceosv
advisories10
affected_packages2
assessed_packages201
unassessed_packages0
affected_by_severityhigh 1, moderate 1
direct_affected_packages0
Excluded from scoring (no data or not applicable): Indirect dependencies free of known advisories, No advisories left outstanding. Remaining weights renormalized. Matched 201 resolved dependencies against OSV. This repository publishes no package the index resolves, so the repository dependency graph was assessed instead. That graph mixes development and test pins with shipped dependencies, so only the declared runtime dependencies are scored; transitive findings are reported as context and excluded from the score. Reachability is not analyzed.

AI Readiness

How well is the repo equipped to be developed and maintained with AI coding agents? Carries a deliberately small weight (4%): agent tooling is a real maintenance signal, but a repository with none can still reach 100/100.

88Excellent · 4% of overall

Agent context & guidance

100Exceptional
How it's scored
45/45Agent instructions — AGENTS.md
15/15Machine-readable docs (llms.txt) — llms.txt served by the project website (https://docs.claude.com/llms.txt)
40/40Legible commit history — 80 of 82 human commits state their intent (structured subject or explanatory body)
Inputs used
has_llms_txtyes
llms_txt_urlhttps://docs.claude.com/llms.txt
legible_history_share0.976
agent_instruction_filesAGENTS.md
agent_instruction_max_bytes397,681

Verify loop (build / test / typecheck)

83Excellent
How it's scored
18/18One-command bootstrap — Makefile
22/22Automated tests
11/11Lint / format config — pyproject.toml ([tool.ruff])
11/11Static type checking — editors/vscode/tsconfig.json
10/10Reproducible environment — lockfile
0/10Demonstrated agent practice — no agent-authored commits among the last 100
8/8Automated maintenance — 9 of the last 100 commits are automated dependency updates
3/10OpenSSF Scorecard: Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 3
Inputs used
has_nixno
has_testsyes
lockfilespackage-lock.json, uv.lock
has_dockerfileno
typed_languageno
bootstrap_filesMakefile
has_devcontainerno
has_linter_configyes
typecheck_configseditors/vscode/tsconfig.json
agent_commit_share0
toolchain_manifests—
dependency_bot_commit_share0.09

Code legibility for models

76Good
How it's scored
27/45Type-checkable code — Python with type-check config (editors/vscode/tsconfig.json)
49.1/55Manageable file sizes — 30/280 source files over 60KB
Inputs used
primary_languagePython
largest_source_bytes718,497
source_files_sampled280
oversized_source_files30

Key facts

24GitHub stars
4contributors
1,174commits, last 12 months
0days since last push
88releases
1bus factor
2open issues
PyPIpackage ecosystems

Data collection warnings

  • Star history unavailable: GitHub GraphQL error: Resource not accessible by personal access token
  • deps.dev does not index pypi:agitrack@0.6.30; advisories assessed against the repository dependency graph instead

More detail

OpenSSF Scorecard 4.9 / 10
4.9aggregate

Independent, tool-agnostic security assessment from the open-source OpenSSF Scorecard. Each check rewards a security practice, not a specific vendor's tool. Checks Scorecard could not determine are marked n/a and excluded from the security score (never counted as zero).Scorecard v5.5.0 · 2026-10-23 04:58 UTC

10Binary-Artifactsno binaries found in the repo
1Branch-Protectionbranch protection is not maximal on development and all release branches
5CI-Tests4 out of 8 merged PRs checked by a CI test -- score normalized to 5
0CII-Best-Practicesno effort to earn an OpenSSF best practices badge detected
0Code-ReviewFound 0/8 approved changesets -- score normalized to 0
3Contributorsproject has 1 contributing companies or organizations -- score normalized to 3
10Dangerous-Workflowno dangerous workflow patterns detected
10Dependency-Update-Toolupdate tool detected
0Fuzzingproject is not fuzzed
10Licenselicense file detected
10Maintained30 commit(s) and 4 issue activity found in the last 90 days -- score normalized to 10
n/aPackagingpackaging workflow not detected
3Pinned-Dependenciesdependency not pinned by hash detected -- score normalized to 3
9SASTSAST tool detected but not run on all commits
10Security-Policysecurity policy file detected
0Signed-ReleasesProject has not signed or included provenance with any releases.
0Token-Permissionsdetected GitHub workflow tokens with excessive permissions
0Vulnerabilities10 existing vulnerabilities detected
Direct dependencies 4
RegistryPackageVersion constraintManifest
PyPIprompt_toolkit>=3.0.52pyproject.toml
PyPIpyte>=0.8.2pyproject.toml
PyPIwatchdog>=6.0pyproject.toml
PyPIpywinpty>=2.0.13pyproject.toml
All dependencies 201

Full resolved dependency set from the GitHub dependency graph: 4 direct and 197 indirect (transitive) packages. The transitive closure is complete when the repository commits a lockfile.

RegistryPackageVersionRelation
PyPIprompt-toolkit3.0.53direct
PyPIpyte0.8.2direct
PyPIpywinpty3.1.0direct
PyPIwatchdog6.0.0direct
npm@azure/abort-controller2.2.0indirect
npm@azure/core-auth1.11.0indirect
npm@azure/core-client1.11.1indirect
npm@azure/core-process1.0.0indirect
npm@azure/core-rest-pipeline1.25.0indirect
npm@azure/core-tracing1.4.0indirect
npm@azure/core-util1.14.0indirect
npm@azure/identity4.13.3indirect
npm@azure/logger1.4.0indirect
npm@azure/msal-browser5.23.0indirect
npm@azure/msal-common16.14.1indirect
npm@azure/msal-node6.0.1indirect
npm@napi-rs/keyring1.3.0indirect
npm@napi-rs/keyring-darwin-arm641.3.0indirect
npm@napi-rs/keyring-darwin-x641.3.0indirect
npm@napi-rs/keyring-freebsd-x641.3.0indirect
npm@napi-rs/keyring-linux-arm-gnueabihf1.3.0indirect
npm@napi-rs/keyring-linux-arm64-gnu1.3.0indirect
npm@napi-rs/keyring-linux-arm64-musl1.3.0indirect
npm@napi-rs/keyring-linux-riscv64-gnu1.3.0indirect
npm@napi-rs/keyring-linux-x64-gnu1.3.0indirect
npm@napi-rs/keyring-linux-x64-musl1.3.0indirect
npm@napi-rs/keyring-win32-arm64-msvc1.3.0indirect
npm@napi-rs/keyring-win32-ia32-msvc1.3.0indirect
npm@napi-rs/keyring-win32-x64-msvc1.3.0indirect
npm@secretlint/core10.2.2indirect
npm@secretlint/profiler10.2.2indirect
npm@secretlint/secretlint-rule-no-dotenv10.2.2indirect
npm@secretlint/secretlint-rule-preset-recommend10.2.2indirect
npm@secretlint/source-creator10.2.2indirect
npm@secretlint/types10.2.2indirect
npm@types/node26.6.3indirect
npm@types/vscode1.93.0indirect
npm@typescript/typescript-aix-ppc647.0.2indirect
npm@typescript/typescript-darwin-arm647.0.2indirect
npm@typescript/typescript-darwin-x647.0.2indirect
npm@typescript/typescript-freebsd-arm647.0.2indirect
npm@typescript/typescript-freebsd-x647.0.2indirect
npm@typescript/typescript-linux-arm7.0.2indirect
npm@typescript/typescript-linux-arm647.0.2indirect
npm@typescript/typescript-linux-loong647.0.2indirect
npm@typescript/typescript-linux-mips64el7.0.2indirect
npm@typescript/typescript-linux-ppc647.0.2indirect
npm@typescript/typescript-linux-riscv647.0.2indirect
npm@typescript/typescript-linux-s390x7.0.2indirect
npm@typescript/typescript-linux-x647.0.2indirect
npm@typescript/typescript-netbsd-arm647.0.2indirect
npm@typescript/typescript-netbsd-x647.0.2indirect
npm@typescript/typescript-openbsd-arm647.0.2indirect
npm@typescript/typescript-openbsd-x647.0.2indirect
npm@typescript/typescript-sunos-x647.0.2indirect
npm@typescript/typescript-win32-arm647.0.2indirect
npm@typescript/typescript-win32-x647.0.2indirect
npm@typespec/ts-http-runtime0.3.9indirect
npm@vscode/vsce4.0.0indirect
npm@vscode/vsce-sign2.1.0indirect
npm@vscode/vsce-sign-alpine-arm642.0.6indirect
npm@vscode/vsce-sign-alpine-x642.0.6indirect
npm@vscode/vsce-sign-darwin-arm642.0.6indirect
npm@vscode/vsce-sign-darwin-x642.0.6indirect
npm@vscode/vsce-sign-linux-arm2.0.6indirect
npm@vscode/vsce-sign-linux-arm642.0.6indirect
npm@vscode/vsce-sign-linux-x642.0.6indirect
npm@vscode/vsce-sign-win32-arm642.0.6indirect
npm@vscode/vsce-sign-win32-x642.0.6indirect
npmagent-base7.1.4indirect
npmazure-devops-node-api12.5.0indirect
npmbalanced-match4.0.4indirect
npmbinaryextensions6.11.0indirect
npmboundary2.0.0indirect
npmbrace-expansion5.0.12indirect
npmbuffer-crc320.2.13indirect
npmbuffer-equal-constant-time1.0.1indirect
npmbundle-name4.1.1indirect
npmcall-bind-apply-helpers1.0.2indirect
npmcall-bound1.0.4indirect
npmcockatiel3.2.1indirect
npmcommander12.1.0indirect
npmdebug4.4.3indirect
npmdefault-browser5.5.1indirect
npmdefault-browser-id5.0.1indirect
npmdefine-lazy-prop3.0.0indirect
npmdunder-proto1.0.1indirect
npmecdsa-sig-formatter1.0.11indirect
npmeditions6.22.0indirect
npmentities8.1.0indirect
npmes-define-property1.0.1indirect
npmes-errors1.3.0indirect
npmes-object-atoms1.1.2indirect
npmfdir6.5.0indirect
npmfunction-bind1.1.2indirect
npmget-intrinsic1.3.0indirect
npmget-proto1.0.1indirect
npmgopd1.2.0indirect
npmgraceful-fs4.2.11indirect
npmhas-symbols1.1.0indirect
npmhasown2.0.4indirect
npmhosted-git-info4.1.0indirect
npmhttp-proxy-agent7.0.2indirect
npmhttps-proxy-agent7.0.6indirect
npmis-docker3.0.0indirect
npmis-inside-container1.0.0indirect
npmis-wsl3.1.1indirect
npmistextorbinary9.5.0indirect
npmjsonc-parser3.3.1indirect
npmjsonwebtoken9.0.3indirect
npmjwa2.0.1indirect
npmjws4.0.1indirect
npmlodash.includes4.3.0indirect
npmlodash.isboolean3.0.3indirect
npmlodash.isinteger4.0.4indirect
npmlodash.isnumber3.0.3indirect
npmlodash.isplainobject4.0.6indirect
npmlodash.isstring4.0.1indirect
npmlodash.once4.1.1indirect
npmlru-cache6.0.0indirect
npmmarked18.0.14indirect
npmmath-intrinsics1.1.0indirect
npmmime1.6.0indirect
npmminimatch10.2.6indirect
npmms2.1.3indirect
npmmute-stream0.0.8indirect
npmobject-inspect1.13.4indirect
npmopen10.2.0indirect
npmparse58.0.1indirect
npmpend1.2.0indirect
npmpicomatch4.0.7indirect
npmproper-lockfile4.1.2indirect
npmqs6.15.2indirect
npmread1.0.7indirect
npmretry0.12.0indirect
npmrun-applescript7.1.0indirect
npmsafe-buffer5.2.1indirect
npmsax1.6.0indirect
npmsemver7.8.5indirect
npmside-channel1.1.1indirect
npmside-channel-list1.0.1indirect
npmside-channel-map1.0.1indirect
npmside-channel-weakmap1.0.2indirect
npmsignal-exit3.0.7indirect
npmstructured-source4.0.0indirect
npmtextextensions6.11.0indirect
npmtinyglobby0.2.17indirect
npmtslib2.8.1indirect
npmtunnel0.0.6indirect
npmtyped-rest-client1.8.11indirect
npmtypescript7.0.2indirect
npmunderscore1.13.8indirect
npmundici-types8.9.0indirect
npmurl-join4.0.1indirect
npmversion-range4.15.0indirect
npmwsl-utils0.1.0indirect
npmxml2js0.5.0indirect
npmxmlbuilder11.0.1indirect
npmyallist4.0.0indirect
npmyauzl3.4.0indirect
npmyazl2.5.1indirect
PyPIagitrack0.6.28indirect
PyPIaltgraph0.17.5indirect
PyPIast-serialize0.12.1indirect
PyPIcfgv3.5.0indirect
PyPIcolorama0.4.6indirect
PyPIcoverage7.16.2indirect
PyPIdistlib0.4.2indirect
PyPIexceptiongroup1.3.1indirect
PyPIexecnet2.1.2indirect
PyPIfilelock3.29.3indirect
PyPIidentify2.6.19indirect
PyPIiniconfig2.3.0indirect
PyPIlibrt0.16.0indirect
PyPImacholib1.16.4indirect
PyPImypy2.4.0indirect
PyPImypy-baseline0.7.4indirect
PyPImypy-extensions1.1.0indirect
PyPInodeenv1.10.0indirect
PyPIpackaging26.2indirect
PyPIpathspec1.1.1indirect
PyPIpefile2024.8.26indirect
PyPIplatformdirs4.10.0indirect
PyPIpluggy1.6.0indirect
PyPIpre-commit4.6.2indirect
PyPIpygments2.20.0indirect
PyPIpyinstaller6.22.3indirect
PyPIpyinstaller-hooks-contrib2026.8indirect
PyPIpytest9.1.1indirect
PyPIpytest-cov7.1.0indirect
PyPIpytest-timeout2.4.0indirect
PyPIpytest-xdist3.8.0indirect
PyPIpython-discovery1.6.1indirect
PyPIpywin32-ctypes0.2.3indirect
PyPIpyyaml6.0.3indirect
PyPIruff0.17.1indirect
PyPIsetuptools84.0.0indirect
PyPItomli2.4.1indirect
PyPItyping-extensions4.15.0indirect
PyPIvirtualenv21.7.13indirect
PyPIwcwidth0.7.0indirect
Dependency advisories 2

This repository publishes no package the index resolves, so its own dependency graph was assessed — 201 packages, which also include development and test pins that never ship: 2 carry known advisories, of which 0 are direct.

PackageVersionRelationSeverityAdvisoriesFixed in
virtualenv21.7.13indirecthigh821.14.9
qs6.15.2indirectmoderate26.16.0

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

Feedback

Spotted something off in this report, or have thoughts to share? Wrong measurements, missed tooling, ideas, questions — anything is welcome. Every message is read and gets a response.

The message is kept through sign-in.

Related records

Inspected repositories sharing catalogue tags or ecosystems with core-aix/agitrack. Read them side by side →

95Nano-Collective/nanocoderAn open coding agent for your terminal, built by a community collective rather than a company. Bring your own model, keep your code on your machine, and owe nothing to anyone.Exceptional94OrchestratorInc/agent-orchestratorOpen-source (Apache-2.0) orchestrator for Claude Code, Codex & 30+ coding agents. Plan, run and supervise agent teams from task to merged PR. Desktop (macOS, Windows, Linux) + iPhone & Android apps.Exceptional90cobusgreyling/loop-engineeringPractical patterns, starters & CLI tools for loop engineering with AI coding agents. Design systems that prompt and orchestrate agents (inspired by Addy Osmani and Boris Cherny). Includes loop-audit, loop-init, loop-cost.Excellent90Gentleman-Programming/gentle-aiGentle-AI configures the AI coding agents you already use: Claude Code, Cursor, OpenCode, Codex, Pi, and more. Choose persistent memory, Organic-Driven Development, curated skills, MCP servers, personas, and optional bounded review. Open source, no agent lock-in.Excellent96sickn33/agentic-awesome-skillsAAS Core is the local, agent-first control plane for complete catalog discovery, agent-owned selection, stack validation, and planning, backed by 2,115+ agentic skills. Includes CLI, local MCP, catalog, plugins, and Workbench.Exceptional94marcusquinn/aidevopsVibe-Coding is easy. DevOps is hard. OpenCode & Git token-efficient AI agent automation for your app, business, and personal development. Opinionated tools, services, CLI & API stack for speed, security, and 24/7 results. Open-source first. SOTA everything. The best AI harness for GitHub & teamwork.Exceptional

Scores are signals, not warranties. They reflect publicly visible practices on GitHub — not a code audit, and not a security guarantee.

Missing data is excluded and weights renormalized, never scored as zero. Methodology is versioned and open: metrics v2.10.0, schema v0.34.0 — full methodology · metrics wiki.

How one result sits in the wider record: aggregate statistics — PyPI.