4.9%

of 9,595 commits were committed by an AI agent — a floor, not an estimate

4.9% agent · top contributor 85%26 contributors

individual

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

466

agent commits

9,129

human commits

agent contributors

85%

largest contributor

Assisted or autonomous

465assisted

1autonomous

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: 12.9%. Bars are scaled to that peak, not to 100%.

Which agents

Claude Code	Anthropic	456	4.8%
Cursor Agent	Anysphere	6	0.1%
GitHub Copilot	GitHub	3	0%
OpenAI Codex	OpenAI	2	0%

Verify it yourself

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

42740d0dfix(mcp-stdio-core): drop unused handler param and share child-spawn setupClaude Code
b8b58f24docs(evidence): record QA for issue-template version bumpClaude Code
e243389cdocs(issue-template): update stale OpenCode version placeholder (fixes #64Claude Code
4586c622docs(evidence): record Grok Sisyphus prompt QA evidenceCursor Agent
a88f1e2cfeat(sisyphus): route Grok 4.5/4.6 to a native model-specific promptCursor Agent
7ab5376dfeat(model-core): add Grok 4.5/4.6 family detectorsCursor Agent
39a3e39bUpdate docs/configurations.mdGitHub Copilot
44a16046Update src/config/schema/experimental.tsGitHub Copilot
6d5d250fUpdate src/hooks/write-existing-file-guard/index.test.tsGitHub Copilot
37c7231atest: isolate connected providers cache test setupOpenAI Codex
0dee4377feat(dispatch): wire marketplace plugin commands into slash command dispatOpenAI Codex

What was excluded

Commits in window	13,223
Merge commits removed	−3,166
CI / dependency bots removed	−462
Considered	9,595

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 code-yeongyu/oh-my-openagent

Scan another repository

Try