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.

Stop configuring your AI stack. Start using it. One command brings a complete pre-wired LLM stack with hundreds of services to explore.

01Result

av/harbor ↗

av/harbor AI coding statistics: 4.8%

of 1,107 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

4.8% agent · top contributor 92.5%3 contributors

individual

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

agent commits

1,054

other considered commits

agent contributors

92.5%

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

50assisted

3autonomous

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: 38.6%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	50	4.5%
GitHub Copilot	GitHub	3	0.3%

03Evidence

Inspect the matches

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

Matched commit samples

9d310f2f on GitHubfeat(hf): enable hf_transfer for faster downloads; stamp config 0.5.3Claude Code
70d9144f on GitHubfix(unsloth-studio): replace GNU-only head -c with ddClaude Code
d741153d on GitHubfix(unsloth-studio): preserve docker compose run arg passthroughClaude Code
9fe07e90 on GitHubchore: upgrade OpenFang to v0.6.9GitHub Copilot
f9f7d2fc on GitHubRemove remaining vllm attention references from vLLM doc and SKILL.mdGitHub Copilot
93c26762 on GitHubRemove deprecated VLLM_ATTENTION_BACKEND env var and docsGitHub 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	1,122
Merge commits removed	−15
CI / dependency bots removed	−0
Considered	1,107

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 →Python AI coding statisticsCompare evidence across Python 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 av/harbor

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	0%	32
2026-03	0%	51
2026-04	38.6%	132
2026-05	0.5%	219
2026-06	0.3%	381
2026-07	0%	85
2026-08	0%	175
2026-09	0%	32