Pulse
2026-09-18-v3.0
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.

Private local AI assistant for your desktop. Voice and text chat, personal memory, dictation and MCP tools. Runs offline with Ollama or OpenAI-compatible servers on macOS, Windows and Linux.

isair/jarvis ↗

isair/jarvis AI coding statistics: 51.5%

of 237 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
51.5% agent · top contributor 100%1 contributor
individual

One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.

122
agent commits
115
other considered commits
1
agent contributors
100%
largest contributor

What shapes this result

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

Assisted or autonomous

122assisted
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

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-0316%25
2026-0479.8%124
2026-0595%20
2026-070%48
2026-080%20

Peak month: 95%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic12251.5%

Inspect the matches

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

Matched commit samples

  • de93d671 on GitHubfix(mcp): keep MCP server sessions alive across tool calls (#381)Claude Code
  • 1b6310d5 on GitHubrefactor(memory): replace regex deflection scrub with prompt + LLM rewriteClaude Code
  • bb49f5bf on GitHubfix(planner): normalise URL-shaped tool args before dispatch (#365)Claude Code

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 window237
Merge commits removed−0
CI / dependency bots removed−0
Considered237

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

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 isair/jarvis

Scan another repository