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.

Open-source Grok Bot alternative with a virtual machine that bots can use

01Result

milind-soni/OpenMausBot ↗

milind-soni/OpenMausBot AI coding statistics: 36.3%

of 1,508 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

36.3% agent · top contributor 33%38 contributors

org-wide

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

548

agent commits

960

other considered commits

agent contributors

33%

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

548assisted

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: 38.5%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	543	36%
Cursor Agent	Anysphere	5	0.3%

03Evidence

Inspect the matches

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

Matched commit samples

9308eeba on GitHubfeat(routines): keep the computer awake for due routines; say where the scClaude Code
e7299e1d on GitHubfeat(rooms): recent-work brief, per-turn log lines, recall by time (#1302)Claude Code
88a83c4a on GitHubfix(test): include claudeUserMcp in the expected features shape (#1300)Claude Code
954d99a9 on GitHubfeat: add Cursor Agent CLI driver (agent acp) (#302)Cursor Agent
9b73b24b on GitHubAdd an extended reaction palette behind a "+" on the reaction bar (#264)Cursor Agent
ea8e0f22 on GitHubAdd one pinned message per thread, shown as a banner above the transcript 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	1,932
Merge commits removed	−399
CI / dependency bots removed	−25
Considered	1,508

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 →TypeScript AI coding statisticsCompare evidence across TypeScript 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 milind-soni/OpenMausBot

Scan another repository

Try

Month	Agent share	Considered commits
2026-08	38.5%	884
2026-09	33.3%	624