← the index
crewAIInc/crewAI ↗
13.1%
of 927 commits were committed by an AI agent — a floor, not an estimate
13.1% agent · top contributor 49.6%21 contributors
org-wide

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

121
agent commits
806
human commits
21
agent contributors
49.6%
largest contributor

Assisted or autonomous

120assisted
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: 44.3%. Bars are scaled to that peak, not to 100%.

Which agents

Claude CodeAnthropic9710.5%
Cursor AgentAnysphere192%
GitHub CopilotGitHub91%
DevinCognition10.1%

Verify it yourself

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

  • c6ff7865fix(memory): honor read_only on update() and recall() access times (#7369)Claude Code
  • 66ef97c7fix(llms): send reasoning_effort to every openai reasoning model (#7187)Claude Code
  • 9393a47ffix(agents): request the forced final answer as a user turn (#7450)Claude Code
  • 3d72c707chore(ci): ignore unpatched nltk GHSA-8mgp-746c-j5xp (#7215)Cursor Agent
  • f90d37b4feat(flow): promote conversational flows to stable (#7107)Cursor Agent
  • a9cb0bdfLorenze/deprecate/answer from history (#7105)Cursor Agent
  • 9b1f4938fix(tools): pin SSRF checks to each redirect hop and peer IP (#6981)GitHub Copilot
  • 754d7323fix: native tool calls broken over OpenAI Responses API (#6515)GitHub Copilot
  • f630c471Document flow agent options (#6420)GitHub Copilot
  • 3010f128chore: widen click dependency constraint to allow 8.2+Devin

What was excluded

Commits in window933
Merge commits removed−0
CI / dependency bots removed−6
Considered927

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 crewAIInc/crewAI

Scan another repository

Try