4.4%

of 591 commits were committed by an AI agent — a floor, not an estimate

4.4% agent · top contributor 38.5%13 contributors

org-wide

Adoption is broad. Many contributors are committing agent-authored work, which is what a real organisational rollout looks like.

agent commits

565

human commits

agent contributors

38.5%

largest contributor

Assisted or autonomous

26assisted

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: 7.5%. Bars are scaled to that peak, not to 100%.

Which agents

GitHub Copilot	GitHub	14	2.4%
Claude Code	Anthropic	9	1.5%
OpenAI Codex	OpenAI	3	0.5%
Cursor Agent	Anysphere	1	0.2%

Verify it yourself

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

eda57336docs(api-javascript): fix build() return type and loadConfigFromFile descrGitHub Copilot
456901bbfeat(create-vite): use Oxlint for react templates and add ESLint option (#GitHub Copilot
1c065507ci: rewrite issue-helper with JS script (#22584)GitHub Copilot
84f5ccccfix(server): handle malformed URI in indexHtmlMiddleware (#22781)Claude Code
6f3ccf5fdocs: remove fathom analytics (#22770)Claude Code
f8d75f77feat: integrate with Vite Task for zero-config build caching (#22453)Claude Code
374bb5d5fix(css): use unique key for cssEntriesMap to prevent same-basename collisOpenAI Codex
bc5c6a7adocs: fix wording in sass error comment (#22214)OpenAI Codex
9163412fdocs: fix reuses wording in dev environment comment (#22173)OpenAI Codex
f8b38e31fix(module-runner): don't crash stack-trace source mapping when globalThisCursor Agent

What was excluded

Commits in window	675
Merge commits removed	−0
CI / dependency bots removed	−84
Considered	591

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 vitejs/vite

Scan another repository

Try