← the index
getpaseo/paseo
2.8%
of 4,127 commits were committed by an AI agent — a floor, not an estimate
2.8% agent · top contributor 27.2%42 contributors
org-wide

Adoption is broad. Many contributors are committing agent-authored work, which is what a real organisational rollout looks like.

114
agent commits
4,013
human commits
42
agent contributors
27.2%
largest contributor

Assisted or autonomous

113assisted
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: 5.7%. Bars are scaled to that peak, not to 100%.

Which agents

Claude CodeAnthropic1112.7%
Cursor AgentAnysphere30.1%

Verify it yourself

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

  • 0eac75befix(server): stop an expired application lease from permanently killing a Claude Code
  • 92442e74fix(server): reject pending Codex app-server requests on dispose (#4283)Claude Code
  • fa1f01ebfeat(app): add fullscreen viewer for Mermaid diagrams on web (#4107)Claude Code
  • d0e1edcafix(server): show the right thinking options for each Cursor model (#4180)Cursor Agent
  • 2347242cfix(usage): read Cursor plan usage from cursor-agent auth.json (#3486)Cursor Agent
  • 3786cf35Wait for Cursor ACP slash commands before listing. (#1099)Cursor Agent

What was excluded

Commits in window4,581
Merge commits removed216
CI / dependency bots removed238
Considered4,127

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 getpaseo/paseo

Scan another repository