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.

⚒️ The open source dark software factory for expert engineers.

01Result

fabro-sh/fabro ↗

fabro-sh/fabro AI coding statistics: 65.6%

of 4,424 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

65.6% agent · top contributor 90.5%23 contributors

individual

One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.

2,900

agent commits

1,524

other considered commits

agent contributors

90.5%

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

2876assisted

24autonomous

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: 93.8%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	2896	65.5%
GitHub Copilot	GitHub	2	0%
Cursor Agent	Anysphere	1	0%
Gemini CLI	Google	1	0%

03Evidence

Inspect the matches

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

Matched commit samples

27f16f89 on GitHubDelete fabro's own pricing: lithos-llm prices every response onceClaude Code
3f9b19eb on GitHubSay unknown for a usage whose cost is unknown on the Usage tabClaude Code
c98785d8 on GitHubPin pebble a39f43e and refuse an older stored session record clearlyClaude Code
a966de25 on GitHubPotential fix for pull request findingGitHub Copilot
911f26f8 on GitHubApply suggestions from code reviewGitHub Copilot
53efde39 on GitHubfeat(search): add Venice backend for web_searchCursor Agent
445050dc on GitHubEnforce local timeout and cancellation for Daytona execute_commandGemini CLI

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	5,156
Merge commits removed	−494
CI / dependency bots removed	−238
Considered	4,424

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 →GitHub Copilot commitsBrowse repositories with detected GitHub Copilot signatures →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →Gemini CLI commitsBrowse repositories with detected Gemini CLI signatures →Rust AI coding statisticsCompare evidence across Rust 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 fabro-sh/fabro

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	93.8%	258
2026-03	88.7%	1377
2026-04	47.1%	1241
2026-05	50.5%	590
2026-06	68.9%	61
2026-07	46.3%	380
2026-08	52%	294
2026-09	82.5%	223