LiveKit Agents

What is LiveKit Agents?

LiveKit Agents is an open-source (Apache 2.0) framework, from real-time infrastructure company LiveKit, for building voice AI agents that listen, think and speak in real time. Founded in 2021 by Russ d’Sa and David Zhao as a free, open-source WebRTC project for streaming real-time audio and video, LiveKit evolved into the infrastructure layer behind some of the industry’s highest-profile voice AI products, it powers OpenAI’s ChatGPT Advanced Voice Mode, and its named customers include xAI, Salesforce and Tesla. The company has raised $181.3M total, including a $100M Series C led by Index Ventures (with Salesforce Ventures) in January 2026 that valued it at $1B. Unlike this category’s other three listed platforms, all closed-source, API-metered SaaS you can only consume, LiveKit Agents is a framework you can fully self-host and inspect, with a managed LiveKit Cloud layer available if you’d rather not run the infrastructure yourself.

What does LiveKit Agents do?

You write agent code in Python or TypeScript using the open-source Agents SDK, wiring together a speech-to-text, LLM and text-to-speech pipeline (or a realtime speech-to-speech model) from a large plugin ecosystem, Deepgram, AssemblyAI, OpenAI, Anthropic, ElevenLabs, Cartesia and others, or route them through LiveKit’s own managed "Inference" gateway for one unified, credit-billed interface. The framework handles the real-time plumbing itself: turn detection, interruption handling, background-noise and voice filtering, and native SIP trunking for real phone calls, plus multi-agent handoffs. Deploy your own code to LiveKit Cloud (managed infrastructure, autoscaling, observability) or run it entirely on your own servers, the framework and SDKs are identical either way.

Key features

• Open-source Agents SDK: Apache 2.0-licensed Python/TypeScript framework (11.5k+ GitHub stars); fully self-hostable, no vendor lock-in.
• Provider-agnostic pipeline: Plug in Deepgram, AssemblyAI, OpenAI, Anthropic, ElevenLabs, Cartesia and more, or use LiveKit’s own managed Inference gateway.
• Built-in real-time plumbing: Turn detection, interruption handling, background-voice/noise filtering and native SIP telephony out of the box.
• LiveKit Cloud (optional): Managed deployment, autoscaling and observability if you don’t want to run your own infrastructure.

What are LiveKit Agents's use cases?

• Custom enterprise voice agent: A platform team builds a bespoke phone agent on its own chosen models, self-hosted for full data control.
• Voice agent inside an existing product: A team already using LiveKit’s real-time media infrastructure adds a voice agent without adopting a second vendor’s stack.

What does LiveKit Agents integrate with?

• Speech & LLM providers — Deepgram, AssemblyAI, OpenAI, Anthropic, ElevenLabs, Cartesia and more via plugins, or LiveKit’s own managed Inference gateway
• Telephony — native SIP trunking for inbound/outbound PSTN calls
• Deployment — self-hosted on your own infrastructure, or LiveKit Cloud (managed)
• Model Context Protocol (MCP) — first-class support for connecting agents to external MCP servers over HTTP or stdio

Why use LiveKit Agents?

• The only genuinely open-source, self-hostable option in this category, full code visibility and no vendor lock-in.
• Proven at serious production scale: powers OpenAI’s ChatGPT Advanced Voice Mode plus xAI, Salesforce and Tesla.
• A real free tier (1,000 agent-session minutes/month, no credit card) even though the company is valued at $1B.

Pros & cons

LiveKit Agents pricing

$0/month

• Build$0 / /month
• Ship$50 / /month starting
• Scale$500 / /month starting
• EnterpriseCustom

See current pricing on livekit.com ↗Compare LiveKit Agents alternatives →

LiveKit Agents review

LiveKit Agents is the one genuinely open-source, self-hostable option among this category’s voice agent platforms, an Apache 2.0 framework, not a closed API you can only rent. That openness comes from a company with real weight behind it: a $1B valuation on $181.3M raised, and infrastructure serious enough that OpenAI runs ChatGPT’s Advanced Voice Mode on it alongside customers like xAI, Salesforce and Tesla. The tradeoff is real: unlike Vapi, Retell AI, Bland AI or ElevenLabs Conversational AI, there is no hosted dashboard that gets you a working agent in an afternoon, you write and deploy code, choosing and wiring your own STT/LLM/TTS providers (or LiveKit’s managed Inference gateway) yourself. Pick LiveKit Agents if engineering ownership, self-hosting or avoiding vendor lock-in matter more than a fast, no-code start; skip it if you want a turnkey agent live without writing code.

The open-source pick in this category, real engineering ownership and no vendor lock-in, at the cost of assembling the pipeline yourself.

Frequently asked questions