41%

of 781 commits were committed by an AI agent — a floor, not an estimate

41% agent · top contributor 84.4%30 contributors

individual

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

320

agent commits

461

human commits

agent contributors

84.4%

largest contributor

Assisted or autonomous

320assisted

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

Which agents

Claude Code	Anthropic	315	40.3%
GitHub Copilot	GitHub	3	0.4%
Cursor Agent	Anysphere	2	0.3%

Verify it yourself

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

51fc0d60test(e2e): drive the MCP server through a real stdio clientClaude Code
5dd8325eci: cache pip downloads between runsClaude Code
82ef9d0efix(incremental): match ignore rules on repo-relative update inputsClaude Code
6e454683fix: ignore missing PyYAML stubsGitHub Copilot
5af39e71feat: add GitHub Copilot platform supportGitHub Copilot
7a3c9158fix(main): restore _apply_tool_filter on fastmcp>=3 and refresh testsGitHub Copilot
33b039e7fix(install): inject AGENTS.md instructions for Codex (#668)Cursor Agent
533e581cperf: remove recursive sub-community splitting, cap Leiden iterations, batCursor Agent

What was excluded

Commits in window	1,080
Merge commits removed	−293
CI / dependency bots removed	−6
Considered	781

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 tirth8205/code-review-graph

Scan another repository

Try