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.

LeanCTX is the Context Gateway for AI Systems. Select task-relevant context, apply supported controls, connect local knowledge and inspect recorded evidence. Open-source Engine: CLI, MCP, hooks and supported proxy paths.

01Result

yvgude/lean-ctx ↗

yvgude/lean-ctx AI coding statistics: 73%

of 7,401 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

73% agent · top contributor 77.9%16 contributors

team

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

5,404

agent commits

1,997

other considered commits

agent contributors

77.9%

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

5404assisted

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: 92.8%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Cursor Agent	Anysphere	5225	70.6%
Claude Code	Anthropic	180	2.4%
OpenAI Codex	OpenAI	1	0%
GitHub Copilot	GitHub	1	0%

03Evidence

Inspect the matches

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

Matched commit samples

fdc01594 on GitHubfix(ci): temporarily re-disable SDK Conformance MatrixCursor Agent
202f0490 on GitHubfix(ci): restore sdk-conformance.sh shebang (MCP corruption)Cursor Agent
04b449fa on GitHubfix(ci): re-enable SDK Conformance Matrix jobCursor Agent
df2e73d9 on GitHubfix: free an abandoned ctx_shell call, and stop logging pipe closes as craClaude Code
a5be0aee on GitHubtest: close four races that made CI red without a product defectClaude Code
ea24d4bc on GitHubfix(security): update rustls to 0.23.45 (RUSTSEC-2026-0285)Claude Code
c527caa7 on GitHubfeat(benchmark): deterministic summary + fixture token expectationsOpenAI Codex
dcb85125 on GitHubFurther cleanup in injected tools promptGitHub 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	8,069
Merge commits removed	−634
CI / dependency bots removed	−34
Considered	7,401

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 →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex signatures →Rust AI coding statisticsCompare evidence across Rust 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 yvgude/lean-ctx

Scan another repository

Try

Month	Agent share	Considered commits
2026-03	0%	485
2026-04	0.2%	652
2026-05	92.8%	390
2026-06	85.8%	1003
2026-07	88.5%	4217
2026-08	69.6%	542
2026-09	61.6%	112