Discover and explore top open-source AI tools and projects—updated daily.
librefangRust-based agent operating system for autonomous AI
Top 94.0% on SourcePulse
Summary
LibreFang is an open-source agent operating system built in Rust, designed for autonomous AI agents that operate continuously and proactively. It targets developers and power users needing a robust platform for deploying AI agents for tasks like monitoring and lead generation, offering a departure from traditional, prompt-driven chatbot frameworks. Website Live Demo
How It Works
Architected with a modular kernel across 24 Rust crates, LibreFang enables autonomous "Hands" (capability packages) to run independently on schedules or 24/7. Key components include orchestration, agent runtime with WASM sandboxing, a comprehensive API, diverse messaging adapters, and persistence mechanisms, prioritizing performance and extensibility. Docs
Quick Start & Requirements
Installation is available via a shell script (curl -fsSL https://librefang.ai/install.sh | sh), Cargo (cargo install --git https://github.com/librefang/librefang librefang-cli), or Homebrew (brew install librefang). Docker images and cloud deployment integrations (Fly.io, Render, Railway) are also provided. A Tauri 2.0 native desktop application is available.
Highlighted Details
/v1/chat/completions) and 140+ other REST/WS/SSE endpoints.Maintenance & Community
LibreFang is a community fork with open governance and a merge-first PR policy, emphasizing community contributions. The project boasts extensive test coverage ("2,100+ tests") and high code quality ("Zero clippy warnings"). Community engagement is fostered through Discord. Contributing Discord
Licensing & Compatibility
Released under the permissive MIT License, allowing broad compatibility with commercial use and integration into closed-source applications.
Limitations & Caveats
The OpenFang Protocol (OFP) wire protocol is plaintext by design. While it uses HMAC-SHA256 mutual authentication and per-message HMAC with nonce replay protection, frame contents are not encrypted. Secure cross-network federation requires implementing additional security layers like private overlay networks or service-mesh mTLS. Comparison
1 day ago
Inactive
TransformerOptimus
e2b-dev
Significant-Gravitas