67.8%

of 859 commits were committed by an AI agent — a floor, not an estimate

67.8% agent · top contributor 98.8%4 contributors

individual

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

582

agent commits

277

human commits

agent contributors

98.8%

largest contributor

Assisted or autonomous

582assisted

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

Mar26

Apr26

May26

Jun26

Jul26

Aug26

Peak month: 90.5%. Bars are scaled to that peak, not to 100%.

Which agents

Claude Code	Anthropic	556	64.7%
Cursor Agent	Anysphere	25	2.9%
GitHub Copilot	GitHub	1	0.1%

Verify it yourself

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

f95c48b0refactor(knowledges): give knowledgeId back to the route paramClaude Code
e51f686erefactor: drop the header-order comment and the rest of the narrationClaude Code
f24b75f3refactor: cut the comments that only explain the authorClaude Code
5319d1cbfeat(frontend): unify list tables with URL sync, navigation, and VitestCursor Agent
fff79b39feat(knowledges): inline rename and delete actions in knowledge header andCursor Agent
bce4d790feat(templates): inline rename and delete actions in template header and lCursor Agent
de6f527eApply suggestions from code reviewGitHub Copilot

What was excluded

Commits in window	938
Merge commits removed	−75
CI / dependency bots removed	−4
Considered	859

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 vxcontrol/pentagi

Scan another repository

Try