← the index
agno-agi/agno
22.7%
of 1,013 commits were committed by an AI agent — a floor, not an estimate
22.7% agent · top contributor 46.1%40 contributors
org-wide

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

230
agent commits
783
human commits
40
agent contributors
46.1%
largest contributor

Assisted or autonomous

230assisted
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

Feb26
Mar26
Apr26
May26
Jun26
Jul26
Aug26
Sep26

Peak month: 43%. Bars are scaled to that peak, not to 100%.

Which agents

Claude CodeAnthropic22322%
GitHub CopilotGitHub40.4%
OpenAI CodexOpenAI10.1%
Cursor AgentAnysphere10.1%
DevinCognition10.1%

Verify it yourself

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

  • 8ff564befix: add missing @property to RemoteAgent.role and RemoteTeam.role (#10172Claude Code
  • 6c5112eaRelease: v3.0.9 (#10076)Claude Code
  • 3da82342Release: v3.0.8 (#10066)Claude Code
  • 1174636dchore: re-enable litellm and crawl4ai extras (#9868)GitHub Copilot
  • f80f687ffix: change Gemini default model from gemini-flash-latest to gemini-3.5-flGitHub Copilot
  • 7db3e1a3fix: handle Pydantic model serialization in tool cache (#6678)GitHub Copilot
  • e73f53ae[fix] Await async chunking in JSONReader (#10167)OpenAI Codex
  • f28a2469cookbook: Add BGPT MCP cookbook example for evidence-grounded paper searchCursor Agent
  • 5d848b7fchore: update exa tools description (#7099)Devin

What was excluded

Commits in window1,029
Merge commits removed16
CI / dependency bots removed0
Considered1,013

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 agno-agi/agno

Scan another repository