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 Swiss Army Knife of Offline AI. Chat, see, speak, and generate images on your phone or Mac — GGUF LLMs, vision, Whisper speech-to-text, Stable Diffusion, tool calling, and local-network servers. Runs on your CPU, GPU, or NPU. No account, no API key, zero data leaves your device.

01Result

off-grid-ai/OGAM ↗

off-grid-ai/OGAM AI coding statistics: 40.2%

of 3,918 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

40.2% agent · top contributor 54.9%12 contributors

team

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

1,575

agent commits

2,343

other considered commits

agent contributors

54.9%

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

1485assisted

90autonomous

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: 84.6%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	1573	40.1%
Gemini CLI	Google	2	0.1%

03Evidence

Inspect the matches

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

Matched commit samples

dfbae6c1 on GitHubfix(remote): auto-recover the remote connection on network changeClaude Code
dc967575 on GitHubchore: bump mobile-pro (desktop tools controlled entirely by device sync)Claude Code
87adccb2 on GitHubfeat(chat): chatOverlay slot for the pending computer-use approval cardClaude Code
b0e4e7f7 on GitHubApply suggestions from code reviewGemini CLI
ee96ef7b on GitHubApply suggestions from code reviewGemini 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	4,304
Merge commits removed	−329
CI / dependency bots removed	−57
Considered	3,918

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 →Gemini CLI commitsBrowse repositories with detected Gemini CLI 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 off-grid-ai/OGAM

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	84.6%	533
2026-03	48.8%	432
2026-04	28.4%	416
2026-05	7.8%	128
2026-06	52.7%	374
2026-07	52%	1125
2026-08	0.4%	681
2026-09	0%	229