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.

Emulate Arduino, ESP32 & Raspberry Pi. in your browser. Write code, compile, and run on 19 real boards — Arduino Uno, ESP32, ESP32-C3, Raspberry Pi Pico, Raspberry Pi 3, and more. No hardware, no cloud, no limits.. Discord: https://discord.gg/3mARjJrh4E

01Result

davidmonterocrespo24/velxio ↗

davidmonterocrespo24/velxio AI coding statistics: 23.8%

of 1,666 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

23.8% agent · top contributor 41.9%6 contributors

team

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

396

agent commits

1,270

other considered commits

agent contributors

41.9%

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

370assisted

26autonomous

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: 56.7%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	368	22.1%
GitHub Copilot	GitHub	28	1.7%

03Evidence

Inspect the matches

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

Matched commit samples

5d7271c8 on GitHubdocs(esp32): the chip-net patch, what was measured, what still failsClaude Code
25251b72 on GitHubfix(esp32): let a custom chip reach the backend runtime againClaude Code
3f7307cf on GitHubtest(esp32): cover the chip-net description sent to the workerClaude Code
46f615ef on GitHubPotential fix for pull request findingGitHub Copilot
5c70f09a on GitHubPotential fix for pull request findingGitHub Copilot
13ee547a on GitHubfeat: add GA4 key events tracking (run_simulation, open_example, create_prGitHub Copilot

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	1,892
Merge commits removed	−222
CI / dependency bots removed	−4
Considered	1,666

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 →TypeScript AI coding statisticsCompare evidence across TypeScript 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 davidmonterocrespo24/velxio

Scan another repository

Try

Month	Agent share	Considered commits
2026-03	17.5%	274
2026-04	30.7%	140
2026-05	56.7%	383
2026-06	27%	189
2026-07	7.7%	195
2026-08	0.3%	311
2026-09	12.1%	174