Osaurus is an open-source AI edge infrastructure platform designed specifically for macOS environments to run and manage AI models locally. The project provides a native runtime that allows applications to access large language models and AI tools directly on the user’s machine without relying entirely on cloud services. Osaurus supports running both local and remote models, enabling developers to build AI-powered applications that can operate offline or leverage external APIs when needed. The platform acts as an always-on runtime that coordinates AI tasks, tools, and workflows while enabling applications to communicate with models through standardized interfaces. Developers can extend the system through plugins that expose additional capabilities, tools, or services to the runtime using a structured plugin architecture. Osaurus also supports the Model Context Protocol, allowing tools and AI services to share context and interact with multiple applications simultaneously.

Features

  • Native macOS runtime for running AI models locally
  • Support for both local and cloud-based model execution
  • Plugin architecture for extending tools and capabilities
  • Model Context Protocol integration for cross-application tool sharing
  • Always-on AI runtime for coordinating tasks and workflows
  • Infrastructure designed for AI-powered desktop applications

Project Samples

Project Activity

See All Activity >

License

MIT License

Follow Osaurus

Osaurus Web Site

Other Useful Business Software
Earn up to 15% annual interest with Nexo. Icon
Earn up to 15% annual interest with Nexo.

Access competitive interest rates on your digital assets.

Generate interest, borrow against your crypto, and trade a range of cryptocurrencies — all in one platform. Geographic restrictions, eligibility, and terms apply.
Get started with Nexo.
Rate This Project
Login To Rate This Project

User Reviews

Be the first to post a review of Osaurus!

Additional Project Details

Programming Language

Swift

Related Categories

Swift Large Language Models (LLM)

Registered

2026-03-05