17.2%

of 583 commits were committed by an AI agent — a floor, not an estimate

17.2% agent · top contributor 78%15 contributors

team

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

100

agent commits

483

human commits

agent contributors

78%

largest contributor

Assisted or autonomous

100assisted

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

Peak month: 28.3%. Bars are scaled to that peak, not to 100%.

Which agents

OpenAI Codex	OpenAI	53	9.1%
Claude Code	Anthropic	43	7.4%
GitHub Copilot	GitHub	12	2.1%
Cursor Agent	Anysphere	1	0.2%

Verify it yourself

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

7af4b6edtest: remove unused empty fixture configs (#10501)OpenAI Codex
81001a49ci: trigger pkg.pr.new on backport branch and workflow dispatch (#10547)OpenAI Codex
4c26d767fix(ui)!: harden UI API access (#10583)OpenAI Codex
51acd577fix(browser): inlined awaited import should not trigger syntax error afterClaude Code
b05e5d63perf(coverage): speed up v8 report generation (bounded-memory merge + precClaude Code
3d421d4echore: setup PR-driven release pipeline (#10550)Claude Code
613c7706chore: remove direct `esbuild` devDependency (#10849)GitHub Copilot
3d421d4echore: setup PR-driven release pipeline (#10550)GitHub Copilot
62756547fix: fix mixed stdout/stderr log timestamps in `onUserConsoleLog` (#10308)GitHub Copilot
209b1b0efeat(ui): add duration sorting to explorer (#9603)Cursor Agent

What was excluded

Commits in window	624
Merge commits removed	−0
CI / dependency bots removed	−41
Considered	583

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 vitest-dev/vitest

Scan another repository

Try