Dataset: 2026-09-18-v3.0
Ruleset: b2e8889c66f7
Scanned: 2026-09-16
Window: February–September 15, 2026

Local to this browser

01Result

JuliaLang/julia ↗

JuliaLang/julia AI coding statistics: 28.6%

of 1,491 commits in February–September 15, 2026 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

other considered commits

agent contributors

22.5%

largest contributor

02Drivers

What shapes this result

Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.

Assisted or autonomous

426assisted

0autonomous

Assisted — a developer’s identity authored the commit and the agent added itself as co-author. Autonomous — a bot identity authored the commit without a human identity attached. Across the whole index, 96% of agent commits are assisted.

Agent share by month

Agent-attributed commit share by month
Month	Agent share	Considered commits
2026-01	0%	1
2026-02	11.1%	153
2026-03	27.4%	135
2026-04	22.8%	149
2026-05	17.7%	147
2026-06	32.8%	186
2026-07	37.5%	381
2026-08	41.3%	218
2026-09	14.9%	121

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

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	414	27.8%
OpenAI Codex	OpenAI	18	1.2%
Cursor Agent	Anysphere	1	0.1%

03Evidence

Inspect the matches

Public commit samples let you inspect the signatures behind the aggregate result.

Matched commit samples

738c697d on GitHubtests: Pick the UDP cancellation test port via the OS, not listenany (#630Claude Code
3ee18532 on GitHubdeps: give LLVM build-tree binaries an rpath to the bundled libraries on mClaude Code
80c869f7 on GitHubdeps: build compiler-rt builtins standalone for the LLVM source build on mClaude Code
95b9f7db on GitHubcodegen: Split small copies into integer chunks (#63015)OpenAI Codex
1d3abe30 on GitHubcodegen: Apply odd-bit storage widths consistentlyOpenAI Codex
2fefd012 on GitHublowering: in-place broadcast returns the lhs (#61846)OpenAI Codex
21696f4d on GitHub[docs] Document `WITH_NVTX` build option (#62271)Cursor Agent

04Method

What entered the denominator

The result begins with commit history, removes merges and routine automation, and reports literal agent signatures as a lower bound.

Exclusion ledger

Commits in window	1,557
Merge commits removed	−59
CI / dependency bots removed	−7
Considered	1,491

Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.

05Provenance

Pinned to a source state

This observation names the repository state, release, and detector that produced it. Use these identifiers when reproducing or citing the result.

Dataset release: 2026-09-18-v3.0
Scan date: 2026-09-16
Ruleset: sha256:b2e8889c66f72c18a61839f0bf1a9f77b5481ba2def044dba33c797b2f2bdcae
Canonical repository: JuliaLang/julia
Default branch: master
Resolved HEAD: 07e2c78d9b7515e37a79bec20795ca96123ade9f ↗
Resolved: 2026-09-16
Measurement window: February–September 15, 2026

Download observation JSONDeterministic export · same values as this page

06Peer context

Position among comparable repositories

The cohort uses the same release and measurement window, then narrows to the repository’s ecosystem and removes low-activity observations.

CohortJulia · 1 eligible repositories · at least 100 considered commits2026-09-18-v3.0 · February–September 15, 2026 · 0 of 1 ecosystem repositories excluded

Comparison withheld for a small cohort

Only 1 eligible repositories remain; qmmit requires at least 10 before showing a percentile. The cohort definition and sample size remain visible so the omission is auditable.

Continue exploring

Claude Code commitsBrowse repositories with detected Claude Code signatures →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex signatures →GitHub AI commit analyzerInspect another repository with the same evidence model →

Reproduce this observation

Run the same detector locally.

Deterministic signature matching; no code-style inference. Squash merges can remove trailers, so this result remains a measured floor.

npx qmmit-cli JuliaLang/julia

Scan another repository

Try