Dataset: 2026-10-27-catalog-ai-v2
Ruleset: b2e8889c66f7
Scanned: 2026-10-27
Window: February–September 15, 2026

Catalog tracking observation. This repository is measured with the same fixed window and ruleset, but it is not part of the published benchmark or its aggregate claims.

Symbolic programming for the next generation of numerical software

01Result

JuliaSymbolics/Symbolics.jl ↗

JuliaSymbolics/Symbolics.jl AI coding statistics: 18.8%

of 234 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

18.8% agent · top contributor 54.5%9 contributors

team

A small group is using agents. Adoption has spread beyond one person but is not project-wide.

agent commits

190

other considered commits

agent contributors

54.5%

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

44assisted

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.

Agent share by month

Peak month: 58.3%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	36	15.4%
Cursor Agent	Anysphere	5	2.1%
Devin	Cognition	2	0.9%
OpenAI Codex	OpenAI	2	0.9%

03Evidence

Inspect the matches

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

Matched commit samples

6411e971 on GitHubRequire SymbolicUtils 4.46.2 so `dims` reductions stop corrupting their arClaude Code
219cd305 on GitHubdocs: how to define derivatives of registered array functions (#1965)Claude Code
a0ab8aab on GitHubFix Symbolics method ambiguities and Aqua piracy ownership (#1971)Claude Code
55f5a6af on GitHubFix SymbolicUtils UUID clobber in Project.toml deps.Cursor Agent
7c261bc0 on GitHubRequire SymbolicUtils 4.46.4 for 32-bit hasha_seed fix.Cursor Agent
10f31d05 on GitHubRequire SymbolicUtils 4.46.3 for 32-bit hash seeds. (#1978)Cursor Agent
2366f583 on GitHubError instead of silent zeros for derivatives through lazy reductionsDevin
8edb13ed on GitHubDocument build_function's return value in its docstring (#1987)Devin
22973399 on GitHubPrevent recursive solver factor cyclesOpenAI Codex
97708c2c on GitHubFix Latexify for array equation vectorsOpenAI Codex

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	385
Merge commits removed	−142
CI / dependency bots removed	−9
Considered	234

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

Continue exploring

Claude Code commitsBrowse repositories with detected Claude Code signatures →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →Devin commitsBrowse repositories with detected Devin 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 JuliaSymbolics/Symbolics.jl

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	10%	30
2026-03	21.4%	14
2026-04	2.9%	34
2026-05	40%	25
2026-06	13.8%	29
2026-07	7.3%	55
2026-08	34.3%	35
2026-09	58.3%	12