← the index
fosrl/pangolin
0.7%
of 3,201 commits were committed by an AI agent — a floor, not an estimate
0.7% agent · top contributor 77.3%4 contributors
team

A small group is using agents. Adoption has spread beyond one person but is not project-wide.

22
agent commits
3,179
human commits
4
agent contributors
77.3%
largest contributor

Assisted or autonomous

5assisted
17autonomous

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: 3.2%. Bars are scaled to that peak, not to 100%.

Which agents

GitHub CopilotGitHub180.6%
Claude CodeAnthropic40.1%

Verify it yourself

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

  • 5428bf4efix: preserve rule IDs when saving policy rules through the GUIGitHub Copilot
  • 9a89579eInitial planGitHub Copilot
  • 22ac711drefactor: tighten ws batch typing and queue cleanup loggingGitHub Copilot
  • c19cb706fix(ci): harden app-readiness PID check; clarify version-source commentClaude Code
  • 938d7f14fix(ci): pin Node to 24.18.1 to match runtime; surface app startup logsClaude Code
  • b7081afffix: remove no-op autoFinalizeStatement wrapper and redundant busy_timeoutClaude Code

What was excluded

Commits in window3,897
Merge commits removed598
CI / dependency bots removed98
Considered3,201

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 fosrl/pangolin

Scan another repository