Bushpilot

Charted routes through the chaotic LLM landscape.

Run Claude Code, OpenCode, Aider, Cline, or Pi locally on Apple Silicon — without guessing context limits, tuning MLX flags, or crashing unified memory.

$ brew install frank321/bushpilot/bushpilot

Apple Silicon (M1+) · macOS · 58 curated MLX models (31 verified on hardware) · MIT

bushpilot — hardware-aware picker, MLX server & live memory dashboard
Bushpilot terminal demo showing the hardware-aware model picker, MLX startup, and live memory dashboard

Why Bushpilot?

Hardware-aware sizing

Reads your chip and live free memory, greys out models that won't fit, and computes safe context length, concurrency, and estimated tok/s before you download.

Active memory backstop

Polls free memory and macOS pressure (kern.memorystatus_level) continuously and tears down the server cleanly before your Mac freezes.

Shared server + live hot-swap

Attach multiple coding tools to one local endpoint and swap models live (m on the dashboard or inside your tool) without restarting sessions.

Curated MLX + speculative decoding

Ships a tested MLX catalog (models.json) with optional mlx-dspark speculative-decoding variants measured up to 3x faster.

Quick Start

brew install frank321/bushpilot/bushpilot
bushpilot

bushpilot auto-splits your terminal (iTerm2, tmux, or Terminal.app) to start the server dashboard and attaches your coding tool. See the Guide for .zip/source installs, two-terminal mode, and tool config, or Architecture for safety mechanics, Ollama comparison, and benchmarks.