← the index
labring/FastGPT ↗
3.2%
of 793 commits were committed by an AI agent — a floor, not an estimate
3.2% agent · top contributor 36%11 contributors
org-wide

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

25
agent commits
768
human commits
11
agent contributors
36%
largest contributor

Assisted or autonomous

25assisted
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: 19.4%. Bars are scaled to that peak, not to 100%.

Which agents

GitHub CopilotGitHub101.3%
Claude CodeAnthropic91.1%
Cursor AgentAnysphere60.8%

Verify it yourself

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

  • 651b2091revert: rollback openapi app docs to previous version (#7026)GitHub Copilot
  • cd75ee16fix: team token auth (#6734)GitHub Copilot
  • 21b3f854refactor: merge standardConstants and standard in team plan (#6549)GitHub Copilot
  • 3002087afeat(dataset): 知识库级 pdfParseConfig 文档解析开关(#68624) (#7721)Claude Code
  • 0d3630adfeat(dataset/tag): upgrade knowledge base tag management (#7660)Claude Code
  • 0058e223feat(workflow): show first-token response time in AI chat node (#7685)Claude Code
  • 469de8c0fix: do not treat reasoning-only tool_calls finish as empty LLM response (Cursor Agent
  • 01732466feat(skill): optimize skill first-use UX and cross-tab associate flow (#74Cursor Agent
  • 8d29adcdfix(outlink/wechat): 空响应时续链延迟 10s，避免热循环刷屏 (#7327)Cursor Agent

What was excluded

Commits in window811
Merge commits removed−0
CI / dependency bots removed−18
Considered793

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/FastGPT

Scan another repository

Try