livekit-plugins-anthropic

What it is and what it does

This package is a plugin that bridges Anthropic's Claude language models into the LiveKit Agents framework, a server-side framework for building real-time voice and multi-modal AI agents. It acts as the LLM component in a larger agent pipeline that typically includes speech-to-text, text-to-speech, and voice activity detection. The plugin lets you drop Claude into an AgentSession alongside other LiveKit components to handle natural language understanding and generation in live conversations.

The package depends on anthropic, httpx, and livekit-agents, and is designed to work within LiveKit's ecosystem for building conversational agents that can see, hear, and understand. It's one of several model-provider plugins available in the LiveKit Agents ecosystem, allowing developers to choose Claude as their LLM backend for voice interactions, multi-agent handoffs, and tool-calling workflows.

Use it for:

• Build a voice assistant that uses Claude for reasoning and conversation, integrated with LiveKit's real-time WebRTC infrastructure.
• Create multi-agent workflows where Claude handles complex reasoning tasks while other agents manage user interaction or specialized functions.
• Deploy a telephony-integrated voice agent that accepts calls and uses Claude to understand and respond to callers in real time.
• Test and iterate on agent behavior using LiveKit's built-in test framework with Claude as the language model backend.

Worth the install?

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

Integrates Anthropic's Claude models into LiveKit's agent framework, enabling voice agents to use Claude for natural language understanding and generation in real-time conversations.

Yes, if you are building voice or multi-modal agents with LiveKit and want to use Claude as your LLM. The package is actively maintained, has no known vulnerabilities, installs with low friction, and integrates cleanly into the LiveKit Agents framework. Install it only if you have already chosen LiveKit Agents as your agent platform and Anthropic as your model provider; it is not a standalone tool.

Install

livekit-plugins-anthropic on PyPI

pip install livekit-plugins-anthropic

uv add livekit-plugins-anthropic

poetry add livekit-plugins-anthropic

Installing livekit-plugins-anthropic

Before you install

Low friction installation as a pure Python wheel. The package is actively maintained with a release from 2026-08-13, and the parent LiveKit Agents framework has strong community presence with 13003 repository stars.

License in practice

Apache-2.0 permissive license allows commercial use, modification, and distribution with minimal restrictions—suitable for proprietary applications.

Quickstart

pip install livekit-plugins-anthropic

from livekit.plugins import anthropic
from livekit.agents import AgentSession

session = AgentSession(
    llm=anthropic.LLM(model="claude-3-5-sonnet"),
    # combine with STT, TTS, and other components
)

Requires Python 3.10 or later; Anthropic API key must be set in environment or passed explicitly.

Verify before relying

• Which specific Claude models are supported by version 1.6.10 and their performance characteristics.
• Whether the plugin supports streaming responses or only batch inference.
• Pricing or rate-limit behavior when used with LiveKit Inference versus direct Anthropic keys.

Package facts

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

Keywords: ai, audio, livekit, realtime, video, voice, webrtc

Tags

More Artificial Intelligence packages

Further reading