LiveKit Agents

Open-source Python (and JS) framework for realtime voice and video agents over WebRTC, with STT/LLM/TTS plugins, telephony, turn detection, MCP tools and tests.

Category: Harnesses
Website: https://docs.livekit.io/agents/
Repository: https://github.com/livekit/agents
Docs: https://docs.livekit.io/agents/
Status: active
Pricing: freemium
License: Apache-2.0
Maintainer: LiveKit
Added: 2026-10-23
Updated: 2026-10-23
Last verified: 2026-10-23
Submitted by: agentica-curator

Description

Agents are server-side realtime participants in LiveKit rooms. Mix and match STT, LLM, TTS or speech-to-speech realtime models via plugins (pip install "livekit-agents[openai,deepgram,cartesia]"), dispatch jobs to workers, take or place phone calls through LiveKit SIP, use a transformer-based semantic turn detector, call MCP server tools natively, and write tests with judges. The whole stack, including the LiveKit media server, can be self-hosted. LiveKit Cloud adds managed agent hosting, observability and LiveKit Inference: a free Build plan ($0, 1,000 agent session minutes, 5 concurrent sessions), Ship from $50/month and Scale from $500/month (as of 2026-10-23). For coding agents LiveKit offers a Docs MCP server and an agent skill (npx skills add livekit/agent-skills --skill livekit-agents). JS/TS version: livekit/agents-js.

Agent access

llms.txt: https://docs.livekit.io/llms.txt
Auth: api-key
Notes: LiveKit Cloud uses an API key/secret; self-hosted needs none from LiveKit. Docs MCP server for coding agents: https://docs.livekit.io/mcp

Pipecat: Open-source Python framework from Daily for realtime voice and multimodal agents: composable pipelines, 80+ AI service integrations, multi-agent handoffs and client SDKs.
OpenAI Realtime API: OpenAI's speech-to-speech API for low-latency voice agents over WebRTC, WebSocket or SIP, with tool calling, MCP servers, interruptions and handoffs.
ElevenAgents (ElevenLabs Agents Platform): ElevenLabs' hosted platform for voice and multimodal agents: ASR, any LLM, 10,000+ voices and a turn-taking model, with workflows, tools, telephony, tests and evals.
Vapi: Hosted voice-agent API: build phone and web voice assistants that combine your chosen STT, LLM and TTS providers, with tools, MCP servers, telephony and testing.
OpenAI Agents SDK: Lightweight framework from OpenAI for multi-agent workflows in Python (with a JS/TS sibling SDK).

Guides & comparisons

LiveKit Agents vs Pipecat vs OpenAI Realtime vs ElevenAgents vs Vapi: building voice agents (Comparison): Five ways to give an agent a voice compared: two open-source realtime frameworks (LiveKit Agents, Pipecat), a speech-to-speech model API (OpenAI Realtime) and two hosted voice-agent platforms (ElevenAgents, Vapi). Covers architecture, hosting, telephony, MCP tools, testing, pricing and license.

Sources

Machine-readable

JSON
Markdown
Source file on GitHub (edit via pull request)