osaurus
Active·★ 38·MIT·Updated 2026-02-24
Osaurus is an AI edge runtime for macOS, leveraging Apple Silicon for optimized local inference and connecting to various cloud models. It provides a native foundation for AI applications, exposing tools via the Model Context Protocol (MCP) and supporting custom assistants and automated workflows.
#macOS#AI Runtime#MLX#LLMs#API Gateway
01
Features
01Optimized local LLM inference for Apple Silicon (MLX)
02Compatibility with OpenAI, Anthropic, Ollama, and custom remote AI APIs
03MCP server for exposing tools and an extensible plugin system
04Customizable AI personas and automated task scheduling
05On-device voice input, wake-word activation, and global transcription
02
Compatibility
macOS
Native
Verified via docs
OpenAI API
Compatible
Verified via docs
Anthropic API
Compatible
Verified via docs
Ollama API
Compatible
Verified via docs
MCP
Native Server
Verified via docs
Apple Foundation Models
Supported
Verified via docs
03
Quick start
1
$ brew install --cask osaurus
04
Use cases
↳Building and deploying AI applications and workflows locally on macOS
↳Automating recurring AI tasks and customizing AI assistants with unique personas
↳Unifying access to local and cloud AI models and tools via compatible APIs
05
Alternatives
xiaozhi-esp32-server★ 11.1k
本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.
vexa★ 2.9k
Open-source meeting transcription API for Google Meet, Microsoft Teams & Zoom. Auto-join bots, real-time WebSocket transcripts, MCP server for AI agents. Self-host or use hosted SaaS.
langchain4j-aideepin★ 1.4k
基于AI的工作效率提升工具（聊天、绘画、知识库、工作流、 MCP服务市场、语音输入输出、长期记忆） | Ai-based productivity tools (Chat,Draw,RAG,Workflow,MCP marketplace, ASR,TTS, Long-term memory etc)
voice-ai★ 749
Rapida is an open-source, end-to-end voice AI orchestration platform for building real-time conversational voice agents with audio streaming, STT, TTS, VAD, multi-channel integration, agent state management, and observability.
FedML★ 4.1k
FEDML - The unified and scalable ML library for large-scale distributed training, model serving, and federated learning. FEDML Launch, a cross-cloud scheduler, further enables running any AI jobs on any GPU cloud or on-premise cluster. Built on this library, TensorOpera AI (https://TensorOpera.ai) is your generative AI platform at scale.
open-connector★ 6.1k
Open-source auth gateway connecting 1000+ SaaS providers to AI agents through SDK, CLI, MCP, HTTP, and OpenAPI.
Comments
Log in to leave a comment
No comments yet. Be the first!