2.1%

of 1,324 commits were committed by an AI agent — a floor, not an estimate

2.1% agent · top contributor 82.1%3 contributors

individual

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

agent commits

1,296

human commits

agent contributors

82.1%

largest contributor

Assisted or autonomous

28assisted

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: 23.4%. Bars are scaled to that peak, not to 100%.

Which agents

Claude Code

Anthropic

2.1%

Verify it yourself

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

2ba0e21cci(emscripten): skip SFTP deploy on forksClaude Code
bee6ac56docs(mcp): drop dangling tracy://catalog referenceClaude Code
6e4041b1feat(mcp): expose sections accessor in eval bindingsClaude Code

What was excluded

Commits in window	1,425
Merge commits removed	−101
CI / dependency bots removed	−0
Considered	1,324

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 wolfpld/tracy

Scan another repository

Try