claude-code-local — security grade SAFE, quality 65/100

Security audit verdict: SAFE · quality 65/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by nicedreamzapp · Claude Skill · ★ 3.3k

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is claude-code-local safe to install? View the security audit →

About claude-code-local

🧠⚡ Claude Code Local — The Lineup Three local AI brains. Four modes. One MacBook. Zero cloud.Pick your fighter and run Claude Code 100% on-device. <img src="https://img.shields.i

abliteratedai-privacyairgapambient-computinganthropicapple-siliconbrowser-agentclaude-codegemmallama

Quick Facts

Stars3,323
Forks629
LanguagePython
CategoryClaude Skill
LicenseMIT
Quality Score64.5124777693617/100
Open Issues2
Last Updated2026-09-20
Created2026-03-26
Platformsbrowser, claude-code, python
Est. Tokens~25k

Compatible Skills

These tools work well together with claude-code-local for enhanced workflows:

  • vllm-mlx — semantic(0.34)+complementary+shared_fw(anthropic)+rare_topics+same_lang+similar_pop+shared_platform (79%)
  • mlx-llm — semantic(0.40)+complementary+rare_topics+same_lang+similar_pop+shared_platform (63%)
  • ovo-local-llm — semantic(0.62)+complementary+rare_topics+shared_platform (62%)
  • mlx-omni-server — semantic(0.33)+complementary+rare_topics+same_lang+similar_pop+shared_platform (61%)
  • maclocal-api — semantic(0.39)+complementary+rare_topics+similar_pop+shared_platform (58%)

claude-code-local alternative? Top 6 similar tools

Looking for a claude-code-local alternative? If you're comparing claude-code-local with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • vllm-mlx by waybarrios · ⭐ 1.6k

    High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuou

  • mlx-serve by ddalcu · ⭐ 1.5k

    Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Includes MLX Core

  • awesome-llm-skills by Prat011 · ⭐ 1.7k

    A curated list of awesome LLM and AI Agent Skills, resources and tools for customising AI Agent workflows - th

  • OGAM by off-grid-ai · ⭐ 3.1k

    The Swiss Army Knife of Offline AI. Chat, see, speak, and generate images on your phone or Mac — GGUF LLMs, vi

  • webbrain by webbrain-one · ⭐ 1.1k

    Open-source AI browser agent for Chrome and Firefox (monorepo) 🧠

  • agent-sessions by jazzyalex · ⭐ 873

    Local-first macOS app to browse, search, analyze, and resume supported AI coding-agent session history across

More Claude Skill Tools

Explore other popular claude skill tools:

View all Claude Skill tools →

Popular Python Agent Tools

Frequently Asked Questions

What is claude-code-local?

claude-code-local is 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 12. It is categorized as a Claude Skill with 3.3k GitHub stars.

What programming language is claude-code-local written in?

claude-code-local is primarily written in Python. It covers topics such as abliterated, ai-privacy, airgap.

How do I install or use claude-code-local?

You can find installation instructions and usage details in the claude-code-local GitHub repository at github.com/nicedreamzapp/claude-code-local. The project has 3.3k stars and 629 forks, indicating an active community.

What license does claude-code-local use?

claude-code-local is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to claude-code-local?

The top alternatives to claude-code-local on Agent Skills Hub include vllm-mlx, mlx-serve, awesome-llm-skills. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Claude Skill tools