← the index
astral-sh/uv
6.3%
of 1,263 commits were committed by an AI agent — a floor, not an estimate
6.3% agent · top contributor 81.3%12 contributors
individual

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

80
agent commits
1,183
human commits
12
agent contributors
81.3%
largest contributor

Assisted or autonomous

78assisted
2autonomous

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: 17.4%. Bars are scaled to that peak, not to 100%.

Which agents

Claude CodeAnthropic695.5%
OpenAI CodexOpenAI100.8%
GitHub CopilotGitHub10.1%

Verify it yourself

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

  • a2a02424ci: use perf for CodSpeed walltime benchmarks (#21055)Claude Code
  • c6e19ef8Add docker integration test for Windows NanoServer entrypoint installationClaude Code
  • f70693a4Fix inclusion of extra specified in dependency group when listed in a confClaude Code
  • 9b58a2e4Support `--require-hashes` in `requirements.txt files` (#19336)OpenAI Codex
  • b4d32e43Vendor packse scenarios and serve them from an in-memory index (#18084)OpenAI Codex
  • 78d8fe93Refactor hint handling (#18090)OpenAI Codex
  • 726047a4Sync latest Python releases (#19268)GitHub Copilot

What was excluded

Commits in window1,831
Merge commits removed0
CI / dependency bots removed568
Considered1,263

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 astral-sh/uv

Scan another repository