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.

The open-source AI research workbench for scientific research and agent workflows. Local-first, model-agnostic desktop app with extensible skills, MCP tools and connectors, Python/R execution and traceable artifacts for reproducible research on macOS, Windows and Linux.

01Result

aipoch/open-science ↗

aipoch/open-science AI coding statistics: 5.2%

of 2,303 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

5.2% agent · top contributor 82.4%7 contributors

individual

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

119

agent commits

2,184

other considered commits

agent contributors

82.4%

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

119assisted

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: 23.6%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	116	5%
Cursor Agent	Anysphere	3	0.1%

03Evidence

Inspect the matches

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

Matched commit samples

5205316f on GitHubfix(providers): probe incompatible providers on their own route and allow Claude Code
87fba82d on GitHubfix(files): resolve the diff module by absolute path for the eval worker (Claude Code
84e0e257 on GitHubfix(session-plan): verify plan read-back through unpublished version read Claude Code
5616f049 on GitHubfeat(web): sync external project and session lifecycle (#317)Cursor Agent
d2c7c72b on GitHubfeat(web): add project and session deep links (#318)Cursor Agent
b6a42fac on GitHubfeat(cli): manage the headless backend as a daemon (#206)Cursor Agent

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	2,312
Merge commits removed	−3
CI / dependency bots removed	−6
Considered	2,303

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 →TypeScript AI coding statisticsCompare evidence across TypeScript 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 aipoch/open-science

Scan another repository

Try

Month	Agent share	Considered commits
2026-07	23.6%	458
2026-08	0.6%	1291
2026-09	0.5%	554