← the index
JuliaLang/julia ↗
28.6%
of 1,491 commits were committed by an AI agent — a floor, not an estimate
28.6% agent · top contributor 22.5%28 contributors
org-wide

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

426
agent commits
1,065
human commits
28
agent contributors
22.5%
largest contributor

Assisted or autonomous

426assisted
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

Jan26
Feb26
Mar26
Apr26
May26
Jun26
Jul26
Aug26
Sep26

Peak month: 41.3%. Bars are scaled to that peak, not to 100%.

Which agents

Claude CodeAnthropic41427.8%
OpenAI CodexOpenAI181.2%
Cursor AgentAnysphere10.1%

Verify it yourself

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

  • 738c697dtests: Pick the UDP cancellation test port via the OS, not listenany (#630Claude Code
  • 3ee18532deps: give LLVM build-tree binaries an rpath to the bundled libraries on mClaude Code
  • 80c869f7deps: build compiler-rt builtins standalone for the LLVM source build on mClaude Code
  • 95b9f7dbcodegen: Split small copies into integer chunks (#63015)OpenAI Codex
  • 1d3abe30codegen: Apply odd-bit storage widths consistentlyOpenAI Codex
  • 2fefd012lowering: in-place broadcast returns the lhs (#61846)OpenAI Codex
  • 21696f4d[docs] Document `WITH_NVTX` build option (#62271)Cursor Agent

What was excluded

Commits in window1,557
Merge commits removed−59
CI / dependency bots removed−7
Considered1,491

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 JuliaLang/julia

Scan another repository

Try