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.

Run Claude Code 100% on-device with local AI on Apple Silicon. MLX-native Anthropic-API server. 6 fighters incl. Muse-Glimmer 30B (now multimodal — reads images, abliterated), Gemma 4 31B, Qwen 3.5 122B (65 tok/s), DeepSeek V4 Flash (1M ctx). Private, offline, airgap-ready. Built for NDA / legal / healthcare workflows.

01Result

nicedreamzapp/claude-code-local ↗

nicedreamzapp/claude-code-local AI coding statistics: 64%

of 125 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
64% agent · top contributor 72.5%8 contributors
team

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

80
agent commits
45
other considered commits
8
agent contributors
72.5%
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

80assisted
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
2026-03100%16
2026-0463.3%49
2026-0568.4%19
2026-06100%4
2026-0766.7%6
2026-0833.3%27
2026-0975%4

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

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic7358.4%
Cursor AgentAnysphere75.6%

03Evidence

Inspect the matches

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

Matched commit samples

  • 033199ae on GitHubFix code-mode Skill stripping and array-shaped fenced tool callsClaude Code
  • 55fe329b on GitHubREADME: say plainly that leaderboard scores come from the Anvil reference Claude Code
  • 49fac592 on GitHubAdd bin/ helpers from the live treeClaude Code
  • edecb840 on GitHublaunchers/docs: enable 4-bit KV cache from token 0 + document SSE fixCursor Agent
  • 37a5e41c on GitHubproxy: implement SSE streaming for tool_use responsesCursor Agent
  • 3670ff58 on GitHubfix(launchers,docs): plug 100% offline leak — Claude Code calls api.anthroCursor 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 window127
Merge commits removed−2
CI / dependency bots removed−0
Considered125

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 →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 nicedreamzapp/claude-code-local

Scan another repository

Try