← the index
JuliusBrussee/caveman
45.8%
of 424 commits were committed by an AI agent — a floor, not an estimate
45.8% agent · top contributor 63.9%9 contributors
team

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

194
agent commits
230
human commits
9
agent contributors
63.9%
largest contributor

Assisted or autonomous

194assisted
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

Apr26
May26
Jun26
Jul26
Aug26
Sep26

Peak month: 78.8%. Bars are scaled to that peak, not to 100%.

Which agents

Claude CodeAnthropic19345.5%
Cursor AgentAnysphere20.5%

Verify it yourself

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

  • 3b74643ffix(cli): wait for a freshly started proxy's run state before judging its Claude Code
  • f9a039a9chore(release): cut v2.5.0 and @caveman-ai/cli 1.3.2 on the bin-v1.1.5 runClaude Code
  • 14b1c15ffix(cli): fail closed on unverifiable proxy owners, strip attributed routeClaude Code
  • 1b7ff8fafix(proxy): scope repo intelligence to project source and require direct eCursor Agent
  • 902eba34fix: opencode .jsonc config, plugin agent discovery, shrink nested descripCursor Agent

What was excluded

Commits in window518
Merge commits removed75
CI / dependency bots removed19
Considered424

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 JuliusBrussee/caveman

Scan another repository