livekit/agents

Health v2 · maintenance only

Adoption not part of the score

14870 stars · 3970 forks observed · 2026-10-21

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

LiveKit Agents is an open-source framework for building realtime, multimodal voice AI agents that run as programmable participants in LiveKit WebRTC rooms. It provides pluggable STT/LLM/TTS pipelines, turn detection, job scheduling, telephony integration, MCP tool support, and a built-in test framework.

Use cases

• build a realtime voice assistant
• create an AI phone call agent
• build a customer service voice bot
• stream speech-to-text and text-to-speech in an agent pipeline
• add a voice interface to an LLM chatbot
• build a multimodal agent that can see and hear
• run voice agents on my own servers

When to choose

• you need low-latency, realtime voice or video AI agents over WebRTC
• you want to mix and match STT, LLM, and TTS providers in one pipeline
• you need telephony (SIP) integration for inbound/outbound calls
• you want an open-source, self-hostable voice agent stack with job scheduling and testing built in

When to avoid

• you only need text-based chatbots without realtime audio or video
• you want a fully managed, no-code solution rather than writing Python or Node.js code
• your project doesn't use or can't deploy LiveKit's WebRTC infrastructure

Facets

framework · maturity active

agent-framework speech-recognition tts llm-inference websocket rpc testing chatbot large-language-models speech-processing developer-tools python cross-platform self-hosted cloud voice-ai webrtc realtime-agents telephony stt turn-detection mcp multimodal ai-agents real-time voice nodejs docker

Member repositories

For agents

markdown · JSON · MCP: product_card(name="livekit/agents")