← the index
JuliaLang/julia
29.8%
of 1,397 commits were committed by an AI agent — a floor, not an estimate
29.8% agent · top contributor 23.3%29 contributors
org-wide

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

417
agent commits
980
human commits
29
agent contributors
23.3%
largest contributor

Assisted or autonomous

417assisted
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: 41.2%. Bars are scaled to that peak, not to 100%.

Which agents

Claude CodeAnthropic40629.1%
OpenAI CodexOpenAI171.2%
Cursor AgentAnysphere10.1%

Verify it yourself

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

  • 9110d5baFix simulated longjmp on FreeBSD/AArch64 (#62968)Claude Code
  • fd4b58c3gf: fix bug in has_ambig computation, improve accuracy with union of candiClaude Code
  • 2f4f6976Call jl_init_options from jl_autoinit_and_adopt_thread (#62883)Claude Code
  • 2fefd012lowering: in-place broadcast returns the lhs (#61846)OpenAI Codex
  • 80c56e6fscopedvalues: Fold reads from enclosing scopes (#62762)OpenAI Codex
  • 3e9e9a0dcontrib/asan: reduce sanitizer overhead (#62783)OpenAI Codex
  • 21696f4d[docs] Document `WITH_NVTX` build option (#62271)Cursor Agent

What was excluded

Commits in window1,448
Merge commits removed44
CI / dependency bots removed7
Considered1,397

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