← the index
danny-avila/LibreChat ↗
3.5%
of 1,938 commits were committed by an AI agent — a floor, not an estimate
3.5% agent · top contributor 41.2%29 contributors
org-wide

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

68
agent commits
1,870
human commits
29
agent contributors
41.2%
largest contributor

Assisted or autonomous

68assisted
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: 5.4%. Bars are scaled to that peak, not to 100%.

Which agents

Claude CodeAnthropic562.9%
GitHub CopilotGitHub110.6%
Cursor AgentAnysphere10.1%

Verify it yourself

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

  • 2f8bc3df🎞️ fix: Deliver Opted-In Custom Endpoint Media Safely (#15937)Claude Code
  • 27acf97a📫 fix: Route Azure Astra Through Responses API (#15845)Claude Code
  • e49cb798🪢 fix: Keep One Code File per Sandbox Destination (#15817)Claude Code
  • c302ae6f🪁 fix: Honor Endpoint Drop Params in Parameter Panels (#15610)GitHub Copilot
  • 8a40e9f6🔄 fix: Reindex MeiliSearch Documents After Indexed-Projection Changes (#1GitHub Copilot
  • ce704f5c🔍 fix: Include Message-Matched Conversations in Sidebar Search (#15483)GitHub Copilot
  • b356c3d8🈳 fix: Treat Blank Mongo Index Settings as Unset (#15809)Cursor Agent

What was excluded

Commits in window1,966
Merge commits removed−0
CI / dependency bots removed−28
Considered1,938

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 danny-avila/LibreChat

Scan another repository

Try