← the index
browser-use/browser-harness
20.5%
of 430 commits were committed by an AI agent — a floor, not an estimate
20.5% agent · top contributor 25%29 contributors
org-wide

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

88
agent commits
342
human commits
29
agent contributors
25%
largest contributor

Assisted or autonomous

88assisted
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: 28.1%. Bars are scaled to that peak, not to 100%.

Which agents

Claude CodeAnthropic8419.5%
GitHub CopilotGitHub20.5%
DevinCognition10.2%
Cursor AgentAnysphere10.2%

Verify it yourself

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

  • c5e5d4f6Match the uv tool-list entry, not a substringClaude Code
  • f533f9e1Only hint at pip when uv does not manage the installClaude Code
  • df3cbc55Tell pip and pipx users how to upgrade when uv tool upgrade failsClaude Code
  • fd3e25c9feat: add field-tested Flipkart shopping domain skillGitHub Copilot
  • d0ebf863Add Expedia domain skill: hotel search automationGitHub Copilot
  • 4720fe43Add MCP server wrapper over browser-harness helpers.Devin
  • ce35175bUpdate README bitter lesson and skills footer linksCursor Agent

What was excluded

Commits in window635
Merge commits removed205
CI / dependency bots removed0
Considered430

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 browser-use/browser-harness

Scan another repository