Pulse
2026-09-18-v3.0
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.

🐸 Rybbit - open-source and privacy-friendly alternative to Google Analytics that is 10x more intuitive.

rybbit-io/rybbit ↗

rybbit-io/rybbit AI coding statistics: 13.5%

of 683 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
13.5% agent · top contributor 71.7%6 contributors
team

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

92
agent commits
591
other considered commits
6
agent contributors
71.7%
largest contributor

What shapes this result

Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.

Assisted or autonomous

18assisted
74autonomous

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

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-010%2
2026-028.1%148
2026-0312%83
2026-0415.8%38
2026-059.9%71
2026-0611.9%67
2026-0717.8%152
2026-0813.3%60
2026-0922.6%62

Peak month: 22.6%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic9113.3%
Cursor AgentAnysphere10.1%
GitHub CopilotGitHub10.1%

Inspect the matches

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

Matched commit samples

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 window690
Merge commits removed−0
CI / dependency bots removed−7
Considered683

Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.

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 rybbit-io/rybbit

Scan another repository