Dataset: 2026-10-27-catalog-ai-v2
Ruleset: b2e8889c66f7
Scanned: 2026-10-27
Window: February–September 15, 2026

Catalog tracking observation. This repository is measured with the same fixed window and ruleset, but it is not part of the published benchmark or its aggregate claims.

Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budgeted evolution loop. MCP server, 14 runtimes: Claude Code, Codex CLI, Gemini CLI, OpenCode, Copilot, Kiro and more.

01Result

Q00/ouroboros ↗

Q00/ouroboros AI coding statistics: 44.4%

of 2,108 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

44.4% agent · top contributor 40.3%38 contributors

org-wide

Adoption is broad. Many contributors are committing agent-authored work, which is what a real organisational rollout looks like.

935

agent commits

1,173

other considered commits

agent contributors

40.3%

largest contributor

02Drivers

What shapes this result

Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.

Assisted or autonomous

925assisted

10autonomous

Assisted — a developer’s identity authored the commit and the agent added itself as co-author. Autonomous — a bot identity authored the commit without a human identity attached.

Agent share by month

Peak month: 99%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	933	44.3%
OpenAI Codex	OpenAI	5	0.2%

03Evidence

Inspect the matches

Public commit samples let you inspect the signatures behind the aggregate result.

Matched commit samples

4c06457c on GitHubchore(release): v0.54.3 (#2389)Claude Code
6cd08826 on GitHubfix(telemetry): name pre-launch and recovered run failures instead of unknClaude Code
7aa307cf on GitHubchore(release): v0.54.2 (#2384)Claude Code
6d5af353 on GitHubfix(#1566): JobManager._run_job can strand a job in RUNNING forever if theOpenAI Codex
c0a59082 on GitHubfix(core): honor worktree_cleanup policy and add ooo cleanup for auto-sessOpenAI Codex
3d52b711 on GitHubfix(#1501): evolve_step: 'NoneType' object is not iterable via plugin MCP OpenAI Codex

04Method

What entered the denominator

The result begins with commit history, removes merges and routine automation, and reports literal agent signatures as a lower bound.

Exclusion ledger

Commits in window	2,214
Merge commits removed	−51
CI / dependency bots removed	−55
Considered	2,108

Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.

Continue exploring

Claude Code commitsBrowse repositories with detected Claude Code signatures →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex signatures →Python AI coding statisticsCompare evidence across Python repositories →GitHub AI commit analyzerInspect another repository with the same evidence model →

Reproduce this observation

Run the same detector locally.

Deterministic signature matching; no code-style inference. Squash merges can remove trailers, so this result remains a measured floor.

npx qmmit-cli Q00/ouroboros

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	99%	105
2026-03	82.6%	265
2026-04	49.3%	306
2026-05	26.3%	734
2026-06	46.4%	110
2026-07	36.2%	232
2026-08	34.7%	314
2026-09	57.1%	42