← the index
labring/sealos
5.7%
of 263 commits were committed by an AI agent — a floor, not an estimate
5.7% agent · top contributor 33.3%6 contributors
team

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

15
agent commits
248
human commits
6
agent contributors
33.3%
largest contributor

Assisted or autonomous

15assisted
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: 11.1%. Bars are scaled to that peak, not to 100%.

Which agents

Claude CodeAnthropic103.8%
GitHub CopilotGitHub51.9%
Cursor AgentAnysphere10.4%

Verify it yourself

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

  • 553ef241feat(desktop): suppress the dock while Brain is the topmost window (#7267)Claude Code
  • a04e0eb5feat(desktop): route Stripe returns to declared app (#7208)Claude Code
  • 91fa34cafeat(dbprovider): dataflow support (#6925)Claude Code
  • 95c027dbfix(resources): bind monitor lifecycle to manager leadership (#7315)GitHub Copilot
  • 30669519fix(account): close payment watches and await worker shutdown (#7304)GitHub Copilot
  • 15ad047bfix(stargz): annotate injected runtime pods (#84) (#7144)GitHub Copilot
  • 9fedc50cfeat(webhooks): add stargz runtime injector webhook (#7042)Cursor Agent

What was excluded

Commits in window263
Merge commits removed0
CI / dependency bots removed0
Considered263

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 labring/sealos

Scan another repository