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.

AI Native platform to get companies compliant - Vanta & Drata Alternative

01Result

trycompai/comp ↗

trycompai/comp AI coding statistics: 65%

of 1,264 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

65% agent · top contributor 65.3%12 contributors

team

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

822

agent commits

442

other considered commits

agent contributors

65.3%

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

739assisted

83autonomous

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: 74.8%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	820	64.9%
Cursor Agent	Anysphere	4	0.3%

03Evidence

Inspect the matches

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

Matched commit samples

4cbcdd24 on GitHubMerge commit from forkClaude Code
76ae56cd on GitHubfix(cloud-security): add missing logGroupName to CreateLogGroup remediatioClaude Code
1940f067 on GitHubfeat(policies): add bulk upload for policy migration (#3514)Claude Code
ae1b5fe0 on GitHubfeat(admin): manage organization frameworksCursor Agent
cce868ec on GitHubfix(cloud-security): ignore unused govcloud session tokenCursor Agent
b318ca5b on GitHubfix(tasks): prevent framework-specific content leaks in split header paragCursor 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	3,084
Merge commits removed	−1,361
CI / dependency bots removed	−459
Considered	1,264

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 trycompai/comp

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	61.3%	31
2026-03	52%	123
2026-04	64.9%	356
2026-05	61.6%	268
2026-06	74.8%	317
2026-07	62.9%	167
2026-08	50%	2