livekit-agents

What it is and what it does

LiveKit Agents is a Python framework for building production-grade AI agents that operate in realtime audio and video environments. It integrates with LiveKit rooms (a WebRTC infrastructure) to connect agents to live participants, handle multimodal input, and orchestrate responses through language models like openai. The framework abstracts away the complexity of managing async I/O, protocol buffers, and agent lifecycle, letting you focus on defining agent behavior through instructions and callbacks.

The package ships with 31 runtime dependencies spanning async HTTP clients, audio/video codecs (av), LLM integrations (openai), observability (opentelemetry-api, opentelemetry-exporter-otlp, opentelemetry-sdk), and LiveKit's own protocol and inference libraries. It targets Python 3.10–3.14 and is designed for scenarios where agents need to respond to live voice or video in a room, making it suitable for customer support bots, meeting assistants, or interactive voice applications.

Use it for:

• Build a voice assistant that joins a LiveKit room and responds to participant speech in real time
• Create a multimodal agent that processes both audio and video feeds to understand context and generate responses
• Deploy a customer support bot that handles live calls or video meetings with AI-driven conversation
• Integrate openai's Realtime API into a LiveKit application for low-latency voice interactions
• Monitor and observe agent behavior using opentelemetry-api and prometheus-client in production

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

A framework for building realtime multimodal and voice AI agents that connect to LiveKit rooms and handle audio/video interactions with language models.

Yes. The package is actively maintained with no known vulnerabilities, uses a permissive Apache-2.0 license, and installs with low friction. It is well-positioned for production voice and video AI agents if you are building realtime AI applications. The large dependency footprint (31 packages) is justified by the breadth of functionality; verify compatibility with your environment before committing.

Install

livekit-agents on PyPI

pip install livekit-agents

uv add livekit-agents

poetry add livekit-agents

Installing livekit-agents

Before you install

Low friction installation with a pure-Python wheel. The package is actively maintained with a recent release and 13002 repository stars, indicating a mature project with community adoption.

License in practice

Apache-2.0 permissive license allows commercial use, modification, and distribution with minimal restrictions—suitable for most production deployments.

Quickstart

pip install livekit-agents

from livekit import agents
from livekit.agents import AgentSession, Agent
from livekit.plugins import openai

async def entrypoint(ctx: agents.JobContext):
    await ctx.connect()
    session = AgentSession(llm=openai.realtime.RealtimeModel(voice="coral"))
    await session.start(room=ctx.room, agent=Agent(instructions="You are a helpful voice AI assistant."))

agents.cli.run_app(agents.WorkerOptions(entrypoint_fnc=entrypoint))

Requires Python 3.10 or later; LiveKit server and credentials must be configured via environment variables.

Verify before relying

• Whether livekit-local-inference and livekit-blingfire are optional or required for all use cases
• Performance characteristics and latency guarantees for realtime interactions
• Compatibility of the 31 runtime dependencies with your existing environment

Package facts

Evidence: livekit_agents-1.6.10-py3-none-any.whl

Keywords: AI, agents, audio, livekit, realtime, video, webrtc

Tags

More Artificial Intelligence packages

Further reading