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.

Turn long-horizon goals into verifiable results. A local-first semantic control plane and research workbench for long-running agent teams, across sessions and runtimes.

01Result

loopx-project/loopx ↗

loopx-project/loopx AI coding statistics: 0.6%

of 5,314 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

0.6% agent · top contributor 46.7%9 contributors

org-wide

Adoption is broad. Many contributors are committing agent-authored work, which is what a real organisational rollout looks like.

agent commits

5,284

other considered commits

agent contributors

46.7%

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

30assisted

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: 2.5%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Cursor Agent	Anysphere	25	0.5%
Claude Code	Anthropic	4	0.1%
OpenAI Codex	OpenAI	1	0%

03Evidence

Inspect the matches

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

Matched commit samples

a577e4e4 on GitHubdocs: close GH-C77 after fixture-oracle KNN smokeCursor Agent
6a7c435d on GitHubRefresh visible-governance Stage-2 proposal vs shipped truth (GH-C62).Cursor Agent
120a999d on GitHubfix(auto-research): retarget GH-C43 walkthrough smoke to demo packageCursor Agent
7f1c7dbe on GitHubAdd SWE-Marathon case-insight projections (#3887)Claude Code
c2bac23b on GitHubfix(contract): stop the credential pattern from flagging non-literal valueClaude Code
812b6048 on GitHubfix(contract): keep `loopx check` running past unreadable files (#3124)Claude Code
f853dc9f on GitHubAdd typed Goal lifecycle action catalogOpenAI Codex

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	6,370
Merge commits removed	−1,055
CI / dependency bots removed	−1
Considered	5,314

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 →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex 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 loopx-project/loopx

Scan another repository

Try

Month	Agent share	Considered commits
2026-05	0%	2
2026-06	0%	1425
2026-07	0%	1810
2026-08	2.5%	1134
2026-09	0.2%	943