Claude Local Stack

claude-local-stack

**Requires Apple Silicon (M1/M2/M3/M4)** — MLX inference is ARM-only. macOS only.

Local AI stack for Claude Code on Apple Silicon. Configuration per profile:

• offline mono or multi-model routing,
• cloud With token optimization

Since I work with many llm model and tool, it was time for me to try to manage all the mess in a more rational way. This stack is far from state of the art, but it help me a lot for :

• my daily job
• encrypt secret (and don't wrote them everywhere ...)
• manage token compression, plugins configuration
• start playing with voice (STT/TTS) integration
• experimenting model

I know that my installation and scripts are macos only... But with the help of an agent and local docs, i'm sure that you could translate all this stack for your personal computer.

Architecture

Default Profile (fully local)

flowchart LR
    CC[Claude Code] --> H[Headroom :8787]
    H --> CCR[CCR :3456]
    CCR --> R[rapid-mlx :8000]
    R --> M[Qwen3.6-35B-A3B MLX]

Cloud Profile (AWS Bedrock)

flowchart LR
    CC[Claude Code] --> H[Headroom :8787]
    H --> B[AWS Bedrock]
    B --> Claude[Claude Sonnet/Opus]

Components

Component	Role	Port
Headroom	Token compression proxy	8787
CCR	Multi-provider task router	3456
rapid-mlx	Local MLX inference server	8000+
AWS Bedrock	Cloud LLM provider	—

Claude Plugins (token saving)

Plugin
RTK