Native macOS harness for AI agents with persistent memory, autonomous execution, and cryptographic identity.
osaurus is worth checking the docs before setup with strong trust signals. Check agent compatibility and use-case fit before adding it to your workflow.
npx skills add osaurus-ai/osaurusRun the command in your terminal.
Confirm that the skill files were added to your agent workspace.
Check the README requirements before invoking the skill in your agent.
Repository setup guidance
Strong trust signals; still review the README and permissions before production use.
Last commit was about 24 days ago.
7630 GitHub stars indicate community interest.
164 open issues signal maintenance load.
MIT license detected.
3 security/trust notes recorded.
Setup difficulty is 3/5.
Run large language models locally with a simple CLI. Supports Llama, Mistral, Gemma, and 100+ models with one command.
A public repository of example skills for Claude, demonstrating how to create reusable instructions and resources for specialized tasks.
The leading open-source AI code assistant for VS Code and JetBrains. Connect any model, customize your workflow.
Anthropic's official CLI agent for coding. Claude-powered terminal agent that reads, writes, and refactors entire codebases.
Osaurus is a Mac app that lets you run AI agents locally. It keeps your data and memory on your device, works offline, and supports many AI models. You can use it for chat, automation, and coding tasks.
Osaurus is a native macOS harness for AI agents, built entirely in Swift and designed for Apple Silicon. It provides a local-first environment where agents can operate with persistent memory, autonomous execution, and cryptographic identity. The tool supports a wide range of models, including local models via MLX and Ollama, as well as cloud providers like OpenAI and Anthropic. It also integrates with Apple Foundation Models and offers an MCP server for extensibility. Osaurus emphasizes user ownership of AI, ensuring that context, memory, and tools remain on the user's machine unless explicitly shared. It includes a chat UI, a CLI, and a server mode, making it suitable for both interactive use and automated workflows. The project is open source under the MIT license and has gained significant traction with over 7,600 stars.
7,630
Stars
449
Forks
164
Issues
MIT
License
Native macOS harness for AI agents with persistent memory, autonomous execution, and cryptographic identity.
Privacy-conscious developers, macOS power users, AI application developers
The setup section provides repository-level starting guidance, not a guarantee of an independently verified installation. Check the official README and release notes.
Autonomous execution may perform unintended actions if not properly sandboxed. Cryptographic identity features could be misused if private keys are compromised.
Similar or complementary options to evaluate include Ollama, anthropic-skills, Continue.
Aug 20, 2026