#local-llm

raullenchai/Rapid-MLX

Python

89

health

The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider.

xyproto/algernon

JavaScript

88

health

Small self-contained pure-Go web server with Lua, Teal, Markdown, Ollama, HTTP/2, QUIC, Redis, TypeScript, SQLite and PostgreSQL support ++

kennss/SiliconScope

Swift

88

health

Sudoless Apple Silicon system monitor (native SwiftUI GUI) with ANE / Media Engine / memory-bandwidth tracking

benmaster82/writher

Python

62

health

🎙️ Offline voice productivity for Windows - dictate text into any app and control a local AI assistant by voice. Manages notes, to-do lists, appointments & reminders. 100% local: faster-whisper + Ollama + SQLite. No cloud, no telemetry. Free and open source alternative to Wispr Flow