[!TIP]
We just released livekit-agents 1.5.0. Check the release note and migration guide here.
LiveKit Agents for Node.js
The Agent Framework is designed for building realtime, programmable participants that run on
servers. Use it to create conversational, multi-modal voice agents that can see, hear, and
understand.
This is a Node.js distribution of the LiveKit Agents framework,
originally written in Python.
Features
- Flexible integrations: A comprehensive ecosystem to mix and match the right STT, LLM, TTS, and Realtime API to suit your use case.
- Extensive WebRTC clients: Build client applications using LiveKit's open-source SDK ecosystem, supporting all major platforms.
- Exchange data with clients: Use RPCs and other Data APIs to seamlessly exchange data with clients.
- Semantic turn detection: Uses a transformer model to detect when a user is done with their turn, helps to reduce interruptions.
- MCP support: Native support for MCP. Integrate tools provided by MCP servers with one line of code.
- Open-source: Fully open-source, allowing you to run the entire stack on your own servers, including LiveKit server, one of the most widely used WebRTC media servers.
Installation
The framework includes a variety of plugins that make it easy to process streaming input or generate
output. For example, there are plugins for converting text-to-speech or running inference with
popular LLMs.
- Install
pnpm if you haven't already:
npm install -g pnpm
To install the core Agents library as well as plugins, run:
pnpm install @livekit/agents
Currently, only the following plugins are supported:
Docs and guides
Documentation on the framework and how to use it can be found here
Recommended starter app
Kickstart a complete voice AI pipeline (LLM, STT, TTS) with the LiveKit Agents Starter for Node.js:
It includes a ready-made assistant, multilingual turn detection, background noise cancellation, metrics/logging, and a production-ready Dockerfile. Start fast, then tailor it with your preferred models and plugins.
Core concepts
- Agent: An LLM-based application with defined instructions.
- AgentSession: A container for agents that manages interactions with end users.
- entrypoint: The starting point for an interactive session, similar to a request handler in a web server.
- Worker: The main process that coordinates job scheduling and launches agents for user sessions.
Usage
Checkout the quickstart guide
Simple voice agent
以上為 README 的開頭部分。其餘內容請閱讀原文。 檢視完整 README ↗
