Osaurus is an all-in-one native macOS LLM server built for Apple Silicon with MLX runtime for optimized local inference. It provides OpenAI and Ollama-compatible APIs (/v1/chat/completions) with streaming and tool calling, Model Context Protocol server support for Cursor and Claude Desktop, and remote provider connections to OpenAI, OpenRouter, Ollama, LM Studio, or any OpenAI-compatible endpoint. Supports Apple Foundation Models on macOS 26+ (Tahoe).
Features comprehensive plugin system with official tools (filesystem, browser automation, git, web search, fetch, time), remote MCP provider support for aggregating external MCP servers, built-in developer tools (request insights, API explorer, endpoint testing), menu bar chat with global hotkey (⌘;), model manager for Hugging Face downloads, and secure API key storage via macOS Keychain. Install via Homebrew or run as CLI server. Active development by Dinoki Labs.
Use Cases:
Release (https://img.shields.io/github/v/release/dinoki-ai/osaurus?sort=semver) Downloads (https://img.shields.io/github/downloads/dinoki-ai/osaurus/total) License (https://img.shields.io/github/license/dinoki-ai/osaurus) Stars (https://img.shields.io/github/stars/dinoki-ai/osaurus?style=social) !Platform-black?logo=apple>) !OpenAI API (https://img.shields.io/badge/OpenAI%20API-compatible-0A7CFF) !Ollama API (https://img.shields.io/badge/Ollama%20API-compatible-0A7CFF) !MCP Server (https://img.shields.io/badge/MCP-server-0A7CFF) !Foundation Models (https://img.shields.io/badge/Apple%20Foundation%20Models-supported-0A7CFF) !PRs Welcome (https://img.shields.io/badge/PRs-welcome-brightgreen)
Native macOS LLM server with MCP support. Run local and remote language models on Apple Silicon with OpenAI-compatible APIs, tool calling, and a built-in plugin ecosystem.
Created by Dinoki Labs (dinoki.ai (https://dinoki.ai))
Documentation (https://docs.osaurus.ai/) · Discord (https://discord.gg/dinoki) · Plugin Registry (https://github.com/dinoki-ai/osaurus-tools) · Contributing
brew install --cask osaurus
Or download from Releases (https://github.com/dinoki-ai/osaurus/releases/latest).
After installing, launch from Spotlight (⌘ Space → "osaurus") or run osaurus ui from the terminal.
Osaurus is an all-in-one LLM server for macOS. It combines:
| Feature | Description |
|---|---|
| Local LLM Server | Run Llama, Qwen, Gemma, Mistral, and more locally |
| Remote Providers | OpenAI, OpenRouter, Ollama, LM Studio, or custom endpoints |
| OpenAI Compatible | /v1/chat/completions with streaming and tool calling |
| MCP Server | Connect to Cursor, Claude Desktop, and other MCP clients |
| Remote MCP Providers | Aggregate tools from external MCP servers |
| Tools & Plugins | Browser automation, file system, git, web search, and more |
| Developer Tools | Request insights, API explorer, and live endpoint testing |
| Menu Bar Chat | Built-in chat overlay with global hotkey (⌘;) |
| Model Manager | Download and manage models from Hugging Face |
Launch Osaurus from Spotlight or run:
osaurus serve
The server starts on port 1337 by default.
Add to your MCP client configuration (e.g., Cursor, Claude Desktop):
{
"mcpServers": {
"osaurus": {
"command": "osaurus",
"args": ["mcp"]
}
}
}
Open the Management window (⌘ Shift M) → Providers → Add Provider.
Choose from presets (OpenAI, Ollama, LM Studio, OpenRouter) or configure a custom endpoint.
Run models locally with optimized Apple Silicon inference:
# Download a model
osaurus run llama-3.2-3b-instruct-4bit
# Use via API
curl http://127.0.0.1:1337/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{"model": "llama-3.2-3b-instruct-4bit", "messages": [{"role": "user", "content": "Hello!"}]}'
Connect to any OpenAI-compatible API to access cloud models alongside local ones.
Supported presets:
Features:
See Remote Providers Guide for details.
Osaurus is a full MCP (Model Context Protocol) server. Connect it to any MCP client to give AI agents access to your installed tools.
| Endpoint | Description |
|---|---|
GET /mcp/health |
Check MCP availability |
GET /mcp/tools |
List active tools |
POST /mcp/call |
Execute a tool |
Connect to external MCP servers and aggregate their tools into Osaurus:
provider_toolname)See Remote MCP Providers Guide for details.
Install tools from the central registry (https://github.com/dinoki-ai/osaurus-tools) or create your own.
Official System Tools:
| Plugin | Tools |
|---|---|
osaurus.filesystem |
read_file, write_file, list_directory, search_files, and more |
osaurus.browser |
browser_navigate, browser_click, browser_type, browser_screenshot |
osaurus.git |
git_status, git_log, git_diff, git_branch |
osaurus.search |
search, search_news, search_images (DuckDuckGo) |
osaurus.fetch |
fetch, fetch_json, fetch_html, download |
osaurus.time |
current_time, format_date |
# Install from registry
osaurus tools install osaurus.browser
# List installed tools
osaurus tools list
# Create your own plugin
osaurus tools create MyPlugin --language swift
See the Plugin Authoring Guide for details.
Built-in tools for debugging and development:
Insights — Monitor all API requests in real-time:
Server Explorer — Interactive API reference:
Access via Management window (⌘ Shift M) → Insights or Server.
See Developer Tools Guide for details.
Desktop LLM client packaging entire codebases with AI-selected files direct API execution to GPT/Gemini/OpenRouter and prompt templates for developers
Android client for hanime1 with ExoPlayer custom themes download management dual layouts playlists and privacy features including app lock
Kubernetes-native AI agent framework with declarative configs MCP tools multi-LLM support OpenTelemetry tracing and CNCF cloud-native architecture
High-performance local LLM server with GPU and NPU acceleration support, featuring multiple inference engines, OpenAI-compatible API, and cross-platform model deployment for AMD Ryzen AI processors.
Developer tool to kill processes blocking ports, manage development caches, and orchestrate services with smart restart, auto-detection, and YAML-based service orchestration across macOS, Linux, and Windows.
Flutter-based cross-platform video streaming client supporting iOS, Android, macOS, and Windows with multi-source search, DLNA casting, smart playback history, and optimized mobile and desktop experiences.