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.

Personal AI, On Personal Devices

01Result

open-jarvis/OpenJarvis ↗

open-jarvis/OpenJarvis AI coding statistics: 59.9%

of 863 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

59.9% agent · top contributor 59.4%37 contributors

team

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

517

agent commits

346

other considered commits

agent contributors

59.4%

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

517assisted

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: 78.1%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	514	59.6%
Cursor Agent	Anysphere	2	0.2%
GitHub Copilot	GitHub	1	0.1%

03Evidence

Inspect the matches

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

Matched commit samples

ca419968 on GitHubfix(memory): preserve short paragraphs during chunking (#885)Claude Code
83329b15 on GitHubfeat: add You.com web search engine with a keyless default (#926)Claude Code
dbd4a1df on GitHubFeature/afm3 support (#904)Claude Code
d6f70587 on GitHubfeat(cli): interactive TUI model picker and Ollama runtime panel (#384)Cursor Agent
5990244a on GitHubchore(deploy): add Render Blueprint for the FastAPI server (#305)Cursor Agent
c3d8ca66 on GitHubOptimize DenseMemory delete path (#826)GitHub 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	1,118
Merge commits removed	−87
CI / dependency bots removed	−168
Considered	863

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 →Python AI coding statisticsCompare evidence across Python 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 open-jarvis/OpenJarvis

Scan another repository

Try

Month	Agent share	Considered commits
2026-03	72.6%	409
2026-04	54.6%	119
2026-05	42.6%	108
2026-06	78.1%	73
2026-07	42.3%	26
2026-08	38.4%	99
2026-09	10.3%	29