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.

Burning through your subscriptions too fast? Paying for stuff you never use? Stop guessing. OpenUsage is free and open source.

01Result

robinebers/openusage ↗

robinebers/openusage AI coding statistics: 64.8%

of 443 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
64.8% agent · top contributor 92.7%8 contributors
individual

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

287
agent commits
156
other considered commits
8
agent contributors
92.7%
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

287assisted
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

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-0686.6%157
2026-0756.3%213
2026-0844.7%47
2026-0938.5%26

Peak month: 86.6%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Cursor AgentAnysphere17138.6%
Claude CodeAnthropic12428%

03Evidence

Inspect the matches

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

Matched commit samples

  • 3b84fec5 on GitHubdocs: changelog for v0.7.12-beta.2Cursor Agent
  • 6a28acec on GitHubFix exhausted Devin weekly quota when percentage is omitted (#1251)Cursor Agent
  • da037481 on GitHubfix(claude): keep usage records whose nested iteration model is null (#126Cursor Agent
  • 54ee194c on GitHubMake Ollama opt-in rather than auto-enabledClaude Code
  • 8f6942e8 on GitHubAddress review: surface plan failures, tighten key check, fix spend copyClaude Code
  • 07459778 on GitHubStop showing a fabricated "~100% left at reset" on untouched meters (#1016Claude Code

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 window585
Merge commits removed−127
CI / dependency bots removed−15
Considered443

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 →Swift AI coding statisticsCompare evidence across Swift 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 robinebers/openusage

Scan another repository

Try