by dinoki-ai
AI edge infrastructure for macOS. Run local or cloud models, share tools across apps via MCP, and power AI workflows with a native, always-on runtime.
# Add to your Claude Code skills
git clone https://github.com/dinoki-ai/osaurusGuides for using mcp servers skills like osaurus.
Last scanned: 4/21/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-04-21T06:03:23.314Z",
"semgrepRan": false,
"npmAuditRan": true,
"pipAuditRan": true
}No comments yet. Be the first to share your thoughts!
Top skills in this category by stars
Osaurus is the AI edge runtime for macOS.
It runs local and cloud models, exposes shared tools via MCP, and provides a native, always-on foundation for AI apps and workflows on Apple Silicon.
Created by Dinoki Labs (dinoki.ai)
Documentation · Discord · Plugin Registry · Contributing
⚠️ Naming Changes in This Release ⚠️
We've renamed two core concepts to better reflect their purpose:
- Personas are now called Agents — custom AI assistants with unique prompts, tools, and themes.
- Agent Mode is now called Work Mode — autonomous task execution with issue tracking and file operations.
All existing data is automatically migrated. This notice will be removed in a future release.
brew install --cask osaurus
Or download from Releases.
After installing, launch from Spotlight (⌘ Space → "osaurus") or run osaurus ui from the terminal.
Osaurus is the AI edge runtime for macOS. It brings together:
| Feature | Description |
| ------------------------ | ---------------------------------------------------------------------- |
| Local LLM Server | Run Llama, Qwen, Gemma, Mistral, and more locally |
| Remote Providers | Anthropic, OpenAI, OpenRouter, Ollama, LM Studio, or custom |
| OpenAI Compatible | /v1/chat/completions with streaming and tool calling |
| Anthropic Compatible | /messages endpoint for Claude Code and Anthropic SDK clients |
| Open Responses | /responses endpoint for multi-provider interoperability |
| 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 |
| Skills | Import AI capabilities from GitHub or files, with smart context saving |
| Agents | Custom AI assistants with unique prompts, tools, and themes |
| Schedules | Automate AI tasks with daily, weekly, monthly, or yearly runs |
| Watchers | Monitor folders and trigger AI tasks on file system changes |
| Work Mode | Autonomous multi-step task execution with parallel task support |
| Custom Themes | Create, import, and export themes with full color customization |
| Developer Tools | Request insights, API explorer, and live endpoint testing |
| Multi-Window Chat | Multiple independent chat windows with per-window agents |
| Menu Bar Chat | Chat overlay with session history, context tracking (⌘;) |
| Voice Input | Speech-to-text with WhisperKit, real-time transcription |
| VAD Mode | Always-on listening with wake-word agent activation |
| Transcription Mode | Global hotkey to dictate into any focused text field |
| 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 (Anthropic, OpenAI, xAI, 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 remote APIs 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 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.
Create custom AI assistants with unique behaviors, capabilities, and styles.
Each agent can have: