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.

Find, benchmark and install in CLI 170+ FREE coding LLM models across 15+ providers in real time

01Result

vava-nessa/free-coding-models ↗

vava-nessa/free-coding-models AI coding statistics: 6.3%

of 664 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

6.3% agent · top contributor 61.9%3 contributors

individual

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

agent commits

622

other considered commits

agent contributors

61.9%

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

31assisted

11autonomous

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: 15%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	31	4.7%
GitHub Copilot	GitHub	11	1.7%

03Evidence

Inspect the matches

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

Matched commit samples

ec0d979a on GitHubfeat(website): add interactive demo placeholder sectionClaude Code
eb105dc9 on GitHubfix(website): switch to SPA mode + add vercel.json + verify-website skillClaude Code
ba768673 on GitHubchore(website): work in progress — Sprint 1 landing pageClaude Code
3736233d on GitHubSkip release when NPM token is missingGitHub Copilot
1df12aeb on GitHubInitial planGitHub Copilot
1de05aec on GitHubAdd explicit permissions to check-discord-link workflowGitHub Copilot

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	757
Merge commits removed	−60
CI / dependency bots removed	−33
Considered	664

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 →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 vava-nessa/free-coding-models

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	15%	153
2026-03	7.3%	124
2026-04	6.6%	61
2026-05	4%	100
2026-06	0%	81
2026-07	0%	57
2026-08	5.6%	36
2026-09	0%	52