← the index
PrefectHQ/fastmcp ↗
17.5%
of 932 commits were committed by an AI agent — a floor, not an estimate
17.5% agent · top contributor 28.8%24 contributors
org-wide

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

163
agent commits
769
human commits
24
agent contributors
28.8%
largest contributor

Assisted or autonomous

162assisted
1autonomous

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: 39.8%. Bars are scaled to that peak, not to 100%.

Which agents

Claude CodeAnthropic16217.4%
GitHub CopilotGitHub40.4%
Cursor AgentAnysphere10.1%

Verify it yourself

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

  • 73ad4abdty: resolve warnings surfaced by ty 0.0.79 (#5123)Claude Code
  • f31180e8renovate: cap routine PRs at 5 concurrent and 5 per hour (#5110)Claude Code
  • 6c2fbe7fdocs: attribute the back-channel removal to SEP-2322/2575, not SEP-2577 (#Claude Code
  • 75b9f925feat: Add telemetry interop mode for FastMCP (#4046)GitHub Copilot
  • 7934124fMake transformed tool required order deterministic (#4564)GitHub Copilot
  • 2d61d8a4fix: add OTEL spans to sampling step and tool execution (#4059)GitHub Copilot
  • 3fdeedb5Improve DescopeProvider scope discovery and well-known URL support (#4489)Cursor Agent

What was excluded

Commits in window1,059
Merge commits removed−41
CI / dependency bots removed−86
Considered932

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 PrefectHQ/fastmcp

Scan another repository

Try