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.

Ouroboros — self-creating AI agent. Born Feb 16, 2026.

01Result

razzant/ouroboros ↗

razzant/ouroboros AI coding statistics: 10.9%

of 3,575 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

10.9% agent · top contributor 48.1%19 contributors

org-wide

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

389

agent commits

3,186

other considered commits

agent contributors

48.1%

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

389assisted

0autonomous

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: 54.9%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	389	10.9%
Cursor Agent	Anysphere	1	0%

03Evidence

Inspect the matches

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

Matched commit samples

b8c46e57 on GitHubKeep one convertible card per owner message after an adoptClaude Code
94a9a67c on GitHubReport what the routing rail actually didClaude Code
ac2b0025 on GitHubfix(review-evidence): task-scope the current_repo stale markerClaude Code
1543c2fe on GitHubAdd remote backends to unix computer use (#64)Cursor Agent

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	4,239
Merge commits removed	−664
CI / dependency bots removed	−0
Considered	3,575

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 →Cursor Agent commitsBrowse repositories with detected Cursor Agent 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 razzant/ouroboros

Scan another repository

Try

Month	Agent share	Considered commits
2026-04	0%	50
2026-05	1.9%	162
2026-06	40.4%	213
2026-07	54.9%	142
2026-08	14.8%	1159
2026-09	2.8%	1849