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.

Quantization, kernels, runtime and inference engine for mobiles, wearables, smart home and robots.

01Result

cactus-compute/cactus ↗

cactus-compute/cactus AI coding statistics: 1.2%

of 486 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

1.2% agent · top contributor 33.3%5 contributors

team

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

agent commits

480

other considered commits

agent contributors

33.3%

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

6assisted

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: 2.2%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	3	0.6%
GitHub Copilot	GitHub	2	0.4%
Cursor Agent	Anysphere	1	0.2%

03Evidence

Inspect the matches

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

Matched commit samples

42006202 on GitHubfix(graph): apply SIGMOID/TANH activations in MoE layer (#736)Claude Code
3227a7f9 on GitHubfix: add missing <iomanip> include for Linux ARM64 builds (#647)Claude Code
f8afc46f on GitHubKaren/needle (#574)Claude Code
9488def9 on GitHubEnhance model publishing workflow with detailed metadata and licenses (#45GitHub Copilot
6c1d1e40 on GitHubKaren/vlm fix (#311)GitHub Copilot
efdec8a4 on GitHubadd scalar log (#390)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	493
Merge commits removed	−7
CI / dependency bots removed	−0
Considered	486

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 →GitHub Copilot commitsBrowse repositories with detected GitHub Copilot signatures →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →C++ AI coding statisticsCompare evidence across C++ repositories →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 cactus-compute/cactus

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	2.2%	137
2026-03	0%	63
2026-04	1.9%	53
2026-05	2%	50
2026-06	1.3%	77
2026-07	0%	85
2026-08	0%	19
2026-09	0%	2