of 4,766 commits were committed by an AI agent — a floor, not an estimate

7% agent · top contributor 58.7%32 contributors

team

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

334

agent commits

4,432

human commits

agent contributors

58.7%

largest contributor

Assisted or autonomous

334assisted

0autonomous

Assisted — a developer’s identity authored the commit and the agent added itself as co-author. The agent ran git commit during a working session, with a person there. Autonomous — a bot identity is the author, no human in the loop. Across the whole index, 93.7% of agent commits are assisted.

Agent share by month

Feb26

Mar26

Apr26

May26

Jun26

Jul26

Aug26

Sep26

Peak month: 11.7%. Bars are scaled to that peak, not to 100%.

Which agents

Claude Code	Anthropic	319	6.7%
GitHub Copilot	GitHub	15	0.3%
Cursor Agent	Anysphere	2	0%

Verify it yourself

Sample commits that matched. Every one links to GitHub — check the trailers.

304bd9aefix(linter/eslint/no-array-constructor): handle ASI hazards in fixer (#261Claude Code
3910e2b9fix(linter/eslint/no-unassigned-vars): skip Svelte and Vue files (#26042)Claude Code
af82a070fix(minifier): keep unary `+` when the other operand has side effects (#25Claude Code
409b4e27perf(lsp): increase concurrency level by available threads (#25153)GitHub Copilot
60bed4abfeat(linter): extends `no-redundant-roles` and `prefer-tag-over-role` suppGitHub Copilot
cf86d7abfeat(linter): bulk suppression (#19328)GitHub Copilot
116c8b83fix(transformer/class-properties): keep private methods in class-expressioCursor Agent
57b94afcfix(linter/promise/no-multiple-resolved): ignore unresolved globals (#2553Cursor Agent

What was excluded

Commits in window	5,105
Merge commits removed	−0
CI / dependency bots removed	−339
Considered	4,766

Bots are excluded from the denominator entirely. Counting dependabot as “AI-written code” is the fastest way to produce a meaningless number.

How this was measured

Measured over February–August 2026, cloned directly. Detection is deterministic string matching against signatures agents write about themselves — no heuristics, no style analysis. Merge commits and CI bots are excluded from the denominator. The figure is a floor: squash merges strip trailers, so real usage is higher. Contributor counts are aggregate — no individual is named.

Run it yourself: npx qmmit-cli oxc-project/oxc

Scan another repository

Try