← the index
langbot-app/LangBot
9.4%
of 672 commits were committed by an AI agent — a floor, not an estimate
9.4% agent · top contributor 38.1%14 contributors
org-wide

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

63
agent commits
609
human commits
14
agent contributors
38.1%
largest contributor

Assisted or autonomous

61assisted
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
Sep26

Peak month: 28.4%. Bars are scaled to that peak, not to 100%.

Which agents

Claude CodeAnthropic517.6%
GitHub CopilotGitHub131.9%
Cursor AgentAnysphere10.1%

Verify it yourself

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

  • 463b1209feat(platform): pass original image URL to Image component in 6 adapters (Claude Code
  • 9ecb587arefactor(provider): use LiteLLM as unified LLM requester backend (#2150)Claude Code
  • bca710dbfeat(platform): show deployment outbound IPs on adapter config formsClaude Code
  • 3a82aa5fPotential fix for pull request finding 'Empty except'GitHub Copilot
  • 4e5a6ee7feat(models): add provider model scanning (#2106)GitHub Copilot
  • 49239e0efeat(ci): add i18n key consistency check for frontend locales (#2133)GitHub Copilot
  • cadcf100Feat/rag plugin (#1995)Cursor Agent

What was excluded

Commits in window710
Merge commits removed35
CI / dependency bots removed3
Considered672

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 langbot-app/LangBot

Scan another repository