osaurus
Verified Safeby dinoki-ai
Overview
Osaurus is a native macOS LLM server running local language models with OpenAI and Ollama compatible APIs, enabling tool calling and a plugin ecosystem for AI agents.
Installation
osaurus serveEnvironment Variables
- OSU_PORT
- OSU_MODELS_DIR
- GH_TOKEN
- MACOS_CERTIFICATE_BASE64
- MACOS_CERTIFICATE_PASSWORD
- KEYCHAIN_PASSWORD
- SPARKLE_PRIVATE_KEY
- APPLE_ID
- APPLE_ID_PASSWORD
- APPLE_TEAM_ID
- DEVELOPMENT_TEAM
- DEVELOPER_ID_NAME
- DISCORD_WEBHOOK
- CHANGELOG
Security Notes
The project demonstrates strong security practices including mandated code signing for plugins, explicit user consent for tool execution (e.g., via ToolPermissionView), and secure handling of sensitive credentials (Keychain integration for MCP tokens, environment variables for CI/CD secrets). The plugin system, while powerful, inherently introduces a surface for potential vulnerabilities if malicious plugins are installed, though this is mitigated by strict signing and permission models. Configuration details shared for inter-app communication do not include sensitive data.
Similar Servers
XcodeBuildMCP
A Model Context Protocol (MCP) server that provides Xcode-related tools for AI assistants, enabling programmatic interaction with Xcode projects, simulators, devices, and Swift packages.
mcp-client-for-ollama
An interactive Python client for connecting local Ollama LLMs to Model Context Protocol (MCP) servers, enabling advanced tool use and workflow automation.
claude-prompts-mcp
Manages hot-reloadable prompt templates, structured reasoning, and multi-step chain workflows to enhance AI assistant interactions through a Model Context Protocol (MCP) compatible server.
action_mcp
Provides Model Context Protocol (MCP) server capabilities to Ruby on Rails applications, enabling AI assistants to interact with external data sources and tools via JSON-RPC over HTTP/SSE.