LiveKit
ActiveDescription
Open source real-time audio/video infrastructure for AI agents. WebRTC transport, agent framework, SIP telephony, and real-time transcription.
Key Features
- Scalable distributed WebRTC SFU (Selective Forwarding Unit) architecture
- Full-featured client SDKs for JavaScript, Swift, Kotlin, Flutter, Unity, React Native, and Rust
- Production-ready with JWT authentication, end-to-end encryption, and SVC codecs (VP9, AV1)
- Advanced features: speaker detection, simulcast, selective subscription, and moderation APIs
- Agents framework for building real-time multimodal AI applications with backend participants
- Easy deployment via single binary, Docker, or Kubernetes with multi-region support
Use Cases
💡 Build real-time video/audio conferencing applications
💡 Create AI voice assistants and real-time multimodal agents
💡 Implement live streaming with RTMP/WHIP/HLS ingestion
💡 Build spatial audio experiences and multiplayer interactions
💡 Integrate real-time communication into existing products via WebRTC
Tags
Categories
Quick Start
1. Install: go install github.com/livekit/livekit/cmd/livekit-server@latest
2. Start server: livekit-server --dev
3. Get API key/secret from server logs
4. Install client SDK: npm install livekit-client
5. Connect: new Room().connect(wsUrl, token)