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.

🦛 CHONK docs with Chonkie ✨ — The lightweight ingestion library for fast, efficient and robust RAG pipelines

01Result

feyninc/chonkie ↗

feyninc/chonkie AI coding statistics: 13.3%

of 285 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

13.3% agent · top contributor 52.6%9 contributors

team

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

agent commits

247

other considered commits

agent contributors

52.6%

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

36assisted

2autonomous

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: 21.4%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
GitHub Copilot	GitHub	15	5.3%
Claude Code	Anthropic	12	4.2%
Gemini CLI	Google	12	4.2%

03Evidence

Inspect the matches

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

Matched commit samples

cbb65147 on GitHubPotential fix for pull request findingGitHub Copilot
ab7e2806 on GitHubPotential fix for pull request findingGitHub Copilot
80e45ae7 on GitHubPotential fix for pull request findingGitHub Copilot
33b50841 on GitHubfix: forward kwargs in BasePorter.__call__ and use points attr in qdrant sClaude Code
f50f2301 on GitHubstyle: fix line length in json.py to comply with ruff formatClaude Code
5f254dac on GitHubfeat: replace all tokenizer backends with tokieClaude Code
85fc8009 on GitHubUpdate src/chonkie/chef/liteparse.pyGemini CLI
de04f315 on GitHubUpdate src/chonkie/chunker/code.pyGemini CLI
9b69c856 on GitHubUpdate tests/test_cli.pyGemini 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	496
Merge commits removed	−167
CI / dependency bots removed	−44
Considered	285

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 →Gemini CLI commitsBrowse repositories with detected Gemini CLI 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 feyninc/chonkie

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	21.4%	70
2026-03	9.1%	33
2026-04	11.5%	87
2026-05	8.9%	45
2026-06	21.4%	28
2026-07	0%	10
2026-08	0%	12