← the index
alibaba/nacos
1.8%
of 657 commits were committed by an AI agent — a floor, not an estimate
1.8% agent · top contributor 50%6 contributors
team

A small group is using agents. Adoption has spread beyond one person but is not project-wide.

12
agent commits
645
human commits
6
agent contributors
50%
largest contributor

Assisted or autonomous

12assisted
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: 5.2%. Bars are scaled to that peak, not to 100%.

Which agents

Claude CodeAnthropic91.4%
GitHub CopilotGitHub30.5%

Verify it yourself

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

  • 4a42e580docs: align pre-submission checks with spotless/checkstyle in AGENTS.md anClaude Code
  • b3fd6634[ISSUE #15279]feat(lock): implement distributed reentrant/non-reentrant loClaude Code
  • fd5114fd[ISSUE #15032] Fix TCP health-check channel leak and member IP prefix matcClaude Code
  • ff5be200[ISSUE #15131] Use mvnd (Maven Daemon) in integration-test workflow (#1513GitHub Copilot
  • d0408fe4Add code coverage badge to README (#14948)GitHub Copilot
  • 156c30f4Potential fix for pull request finding 'CodeQL / Workflow does not containGitHub Copilot

What was excluded

Commits in window676
Merge commits removed15
CI / dependency bots removed4
Considered657

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 alibaba/nacos

Scan another repository