Home / AI Trending / nicedreamzapp/claude-code-local

claude-code-local — What is it?

This project enables on-device, offline execution of Claude Code 100% locally on Apple Silicon, addressing privacy and performance concerns in sensitive workflows.

⭐ 2,204 Stars 🍴 418 Forks Python — Author: nicedreamzapp
Source: Description per README View on GitHub →

Why it matters

The project is attracting attention due to its focus on privacy and offline capabilities, filling a gap in the market for secure, on-device AI processing. Unique technical choices include the use of MLX-native Anthropic-API server and support for multiple large language models.

Source: Synthesis of README and project traits

Core Features

On-device AI processing

Supports running Claude Code 100% on-device with local AI, ensuring data privacy and reducing latency.

Source: Description per README
Multiple AI models

Incorporates multiple AI models (Qwen 3.5 122B, Llama 3.3 70B, Gemma 4 31B) with varying speeds and capabilities, allowing users to choose the best fit for their needs.

Source: README - The Lineup
Offline and airgap-ready

Built for NDA / legal / healthcare workflows, ensuring that all processing is done locally without the need for cloud connectivity.

Source: Description per README

Architecture

The architecture is modular, with separate components for the MLX-native Anthropic-API server, different AI models, and a proxy server. The code tree indicates a separation of concerns with dedicated directories for documentation, launchers, and scripts.

Source: Code tree

Project Knowledge Graph

Knowledge graph: project (center) + core features (inner hexagons) + key dependencies (outer chips) MLX-native Anthropic-API serverMLX-native Ant… antirez/ds4 On-device AI processingOn-device AI proces… Multiple AI models Offline and airgap-readyOffline and airgap-… claude-code-local Project Core feature Key dependency

Center: project; inner ring: core feature modules; outer ring: key dependencies. Auto-generated from core_features and tech_stack.key_deps.

Tech Stack

LanguagePythonFrameworkNot enough information.
Key dependencies
MLX-native Anthropic-API serverantirez/ds4
Infrastructure / Deployment
Not enough information.
Source: Dependency files + code tree

Quick Start

1. Clone the repository. 2. Run `setup.sh` to install dependencies. 3. Choose an AI model and run the corresponding launcher command (e.g., `Gemma 4 Code.command`).
Source: README Installation/Quick Start

Use Cases

This project is suitable for professionals in legal, healthcare, and other fields requiring secure, on-device AI processing. It is useful for tasks such as confidential document analysis, patient data processing, and other sensitive workflows.

Source: README

Strengths & Limitations

Strengths

  • Strength 1: Strong focus on privacy and security with on-device processing.
  • Strength 2: Offers a variety of AI models to cater to different needs.
  • Strength 3: Designed for specific industries with sensitive data requirements.

Limitations

  • Limitation 1: Limited information on the technical stack and infrastructure.
  • Limitation 2: May require significant computational resources to run certain models.
Source: Synthesis of README, code structure and dependencies

Latest Release

v0.1.0 (2026-05-08): First tagged release with verified offline capabilities and support for 16GB Macs.

Source: GitHub Releases

Verdict

This project is worth watching for its innovative approach to on-device AI processing, particularly for those in industries with strict privacy and security requirements. It is best suited for teams or individuals who prioritize data security and are willing to invest in the necessary hardware and resources.

Source: Synthesis
Transparency Notice
This page is auto-generated by AI (a large language model) from the following public materials: GitHub README, code tree, dependency files and release notes. Analyzed at: 2026-05-23 00:12. Quality score: 85/100.

Data sources: README, GitHub API, dependency files