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.

A simple tool for coordinating several AI agents.

01Result

unclebob/swarm-forge ↗

unclebob/swarm-forge AI coding statistics: 2.4%

of 327 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

2.4% agent · top contributor 62.5%4 contributors

team

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

agent commits

319

other considered commits

agent contributors

62.5%

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

8assisted

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: 30.4%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	8	2.4%

03Evidence

Inspect the matches

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

Matched commit samples

deb3ed5a on GitHubAdd iTerm2 terminal backendClaude Code
9aa45c24 on GitHubFix bugs in helper shell scriptsClaude Code
4579cabb on GitHubAdd dodecahedron structural specs and helper functionsClaude Code

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	331
Merge commits removed	−4
CI / dependency bots removed	−0
Considered	327

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 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 unclebob/swarm-forge

Scan another repository

Try

Month	Agent share	Considered commits
2026-04	30.4%	23
2026-05	0%	62
2026-06	0.6%	165
2026-07	0%	4
2026-08	0%	65
2026-09	0%	8