livekit-agents
A powerful framework for building realtime voice AI agents
Decision gist · record as of 2026-08-14
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.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.10 or later; LiveKit server and credentials must be configured via environment variables.
- 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 · maintenance · safety
Apache-2.0 (permissive) — Apache-2.0 permissive license allows commercial use, modification, and distribution with minimal restrictions—suitable for most production deployments.
last release 2026-08-13 (1 days) · last repo commit 2026-08-14 · 13,002 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 4,478,869 downloads/mo, #2,294 on PyPI
Alternatives
Verify before relying
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))- 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
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 on it.
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
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.
Requires Python 3.10 or later; LiveKit server and credentials must be configured via environment variables.
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))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
| License | Apache-2.0 permissive |
| Python support | Supports the current Python release <3.15,>=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 31 packagesaiofilesaiohttpavcertificlickcoloramadocstring-parsereval-type-backportjson-repairlivekit-apilivekit-blingfirelivekit-local-inferencelivekit-protocollivekitnest-asyncionumpyopenaiopentelemetry-apiopentelemetry-exporter-otlpopentelemetry-sdkprometheus-clientprotobufpsutilpydanticpyjwtpyyamlsounddevicetypertypes-protobuftyping-extensions |
| Maintenance | Actively maintained 1 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 4,478,869 / month, #2,294 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Intended Audience :: DevelopersLicense :: OSI Approved :: Apache Software LicenseProgramming Language :: Python :: 3Programming Language :: Python :: 3 :: OnlyProgramming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.14Topic :: Multimedia :: Sound/AudioTopic :: Multimedia :: VideoTopic :: Scientific/Engineering :: Artificial Intelligence |
Evidence: livekit_agents-1.6.10-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “realtime multimodal agents”
- livekit-agentsA framework for building realtime multimodal and voice AI agents that…
- livekit-plugins-openaiIntegrates OpenAI's Realtime, Responses, LLM, TTS, and STT APIs into…
- livekit-plugins-elevenlabsIntegrates ElevenLabs text-to-speech into the LiveKit Agents…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also livekit-plugins-anam · daily-python · lance-context · livekit-plugins-assemblyai · livekit-protocol · livekit-api · livekit · livekit-plugins-rime · livekit-plugins-anthropic · livekit-plugins-xai