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.

Sandbox your local AI agents so they can read/write only what they need

01Result

eugene1g/agent-safehouse ↗

eugene1g/agent-safehouse AI coding statistics: 23.3%

of 262 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

23.3% agent · top contributor 67.2%10 contributors

team

A small group is using agents. Adoption has spread beyond one person but is not project-wide.

agent commits

201

other considered commits

agent contributors

67.2%

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

61assisted

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: 77.8%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	59	22.5%
Cursor Agent	Anysphere	1	0.4%
OpenAI Codex	OpenAI	1	0.4%

03Evidence

Inspect the matches

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

Matched commit samples

3b22b30b on GitHubfeat(core)!: grant read of XDG binary directory subpathClaude Code
eb93e2af on GitHubfeat(python)!: disallow uv install/upgrade inside sandboxClaude Code
ca95b092 on GitHubfeat(python): allow running a uv-installed ruffClaude Code
aba9906b on GitHubfeat(cursor-app): Add Cursor Desktop app profileCursor Agent
2a5cdefd on GitHubfix(python): allow multiprocessing semaphores (#171)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	312
Merge commits removed	−28
CI / dependency bots removed	−22
Considered	262

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 →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex signatures →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 eugene1g/agent-safehouse

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	10.3%	78
2026-03	2.3%	86
2026-04	0%	2
2026-05	0%	7
2026-06	77.8%	9
2026-07	42.3%	26
2026-08	60%	40
2026-09	64.3%	14