← the index
danny-avila/LibreChat ↗
2.7%
of 1,281 commits were committed by an AI agent — a floor, not an estimate
2.7% agent · top contributor 20.6%23 contributors
org-wide

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

34
agent commits
1,247
human commits
23
agent contributors
20.6%
largest contributor

Assisted or autonomous

34assisted
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

Peak month: 4.2%. Bars are scaled to that peak, not to 100%.

Which agents

Claude CodeAnthropic262%
GitHub CopilotGitHub70.5%
Cursor AgentAnysphere10.1%

Verify it yourself

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

  • da390fa9🩹 fix: apply agent updates that match the newest version entry (#14810)Claude Code
  • 8f1f43f3🫧 refactor: Fading Pre-Response Dot, Legacy Cursor CSS Removed (#14772)Claude Code
  • ae244611🚣‍♀️ feat: Smooth Streaming Text Fade-In (#14757)Claude Code
  • e8d76542📡 feat: add rum browser page-load diagnostics (#14106)GitHub Copilot
  • b84e2667🕒 feat: Track Terms Acceptance Timestamp (#10810)GitHub Copilot
  • 1746153c🪬 fix: Skip MCP Tools When Required Custom User Vars Are Unset (#13152)GitHub Copilot
  • b5c097e5⚗️ feat: Agent Context Compaction/Summarization (#12287)Cursor Agent

What was excluded

Commits in window1,306
Merge commits removed−0
CI / dependency bots removed−25
Considered1,281

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