Updated

LiveKit

Open-source WebRTC platform and framework for building realtime voice, video and AI agent applications.

38 makers' products we track use LiveKit. For voice agents it's the most chosen of 6 options: 38 of the 75 makers' products we know the voice agents of (51%). 27 open-source projects also declare it in their code.

Open sourceSelf-hostable

Profile checked

Ask your AI about this, with this page as the source:ChatGPT ↗Claude ↗Perplexity ↗

How makers use LiveKit

Makers' products we track use LiveKit for voice agents (38), most often alongside Vercel (42%), Next.js (39%), Stripe (34%).

What LiveKit is used for

Voice Agents · Open-source framework →Real-time voice and video in your own app, with an agents framework on top of its WebRTC infrastructure.Trade-off: More to learn and run than a hosted platform, unless you pay for LiveKit Cloud.
LiveKit38Vapi16Daily16Pipecat5Retell AI4Makers' products on each, for voice agents

LiveKit vs the alternatives makers chose

For voice agents, 38 of the 75 makers' products we know the choice of picked LiveKit (51%), the most of 6 options.

OptionMakers' productsOpen source
LiveKit38 51%Yes
Daily16 21%No
Vapi16 21%No
Pipecat5 7%Yes
Retell AI4 5%No
Layercode1 1%No

For voice agents: how many of the 75 makers' products we know the voice agents of chose each option.

Often paired with

Share of the 38 makers' products on LiveKit that show this choice.

Markets that build with it most

Product Hunt markets where LiveKit is in far more of the stacks we know than across every market (1%).

When to use LiveKit, and when not

Pick LiveKit if

  • Voice happens inside your web or mobile app, or you need video too. Voice Agents →
  • You want full control over every component of the pipeline, in Python. Voice Agents →

Something else fits better if

  • You want a hosted voice agent but need to swap providers and call your own functions: Vapi or ElevenLabs.
  • The agent answers or makes business phone calls, set up largely without code: Retell AI.
  • Response delay matters most and you're fine with one model doing the listening and talking: OpenAI API.
From each decision's guide, written from what makers' products chose and why.

How LiveKit itself is built

16 tools, from its own code, website and Product Hunt page.

Who uses it

38 makers' products, each linked to the source that shows it, and 27 open-source projects that declare it in their code. The best known on Product Hunt: Talo by Palabra.ai (2,141 followers), Hey Noah (1,535 followers), SpatialChat (1,270 followers), Slashy (1,259 followers), Interactpitch (918 followers). 1 of the makers' products is gone now (domain lapsed, up for sale or taken down); it chose LiveKit while live.

The maker says so 33Subprocessor list 5Declared in code 27How evidence is collected →
graph8
graph8Turn buyer signals into outbound that works

“We use LiveKit as the orchestrator for everything voice-related in our platform — from real-time conversations to AI-driven phone calls. It handles signaling, session management, and audio streaming across our voice AI and telephony systems. The flexibility and performance have been critical to delivering reliable, low-latency voice experiences. Thanks to the LiveKit team for building an infrastructure layer we can trust.”

Voice AgentsMaker says so · source ↗
Unify
UnifyWas an LLM router, one API in front of many models and providers that sent each prompt t…

“The best OS platform for building voice AI”

Voice AgentsMaker says so · source ↗
April
AprilVoice assistant app for iPhone that manages email and calendar by spoken commands, such…

“Very easy to set up and use, and has great pricing for startups”

Voice AgentsMaker says so · source ↗
Userology AI
Userology AIThe AI user research agent for busy product teams

“LiveKit lets us handle real-time audio/video and screen streaming for research sessions without fighting brittle infra, so we can focus on better participant experiences instead of WebRTC wizardry.”

Voice AgentsMaker says so · source ↗
Janus
JanusTransform into anyone live, on any device, in any platform

“We didn't want to focus on building our own RTC logic, we just wanted something that works! Livekit is exactly that, works like magic!”

Voice AgentsMaker says so · source ↗
Deeptrue
DeeptrueReal-Time AI Copilot for Global Meetings

“Enables low-latency, high-quality video infrastructure that powers our real-time translation.”

Voice AgentsMaker says so · source ↗
Firecoach AI
Firecoach AIFireCoach.ai lets sales teams build AI bots trained on their sales playbook, then uses t…

“Voice AI needs real-time, not near-real-time. LiveKit's open-source WebRTC gave us full pipeline control with sub-100ms latency. Daily.co and Dyte were too abstracted for what we needed.”

Voice AgentsMaker says so · source ↗
SigmaMind AI
SigmaMind AIPlatform to build enterprise-ready voice/chat agents

“open source libraries providing the building blocks to build reliable scalable voice infra.”

Voice AgentsMaker says so · source ↗
The Banana App
The Banana AppSpeak human - Where every word finds its way home

“LiveKit handles our real-time communication infrastructure, providing reliable peer-to-peer connections for voice calls across 80+ languages. Their WebRTC implementation ensures crystal-clear audio quality worldwide.”

Voice AgentsMaker says so · source ↗
Libretto
LibrettoDescript alternative for fast, unlimited editing

“Great library and infrastructure for building real time audio and video. Exceptional documentation and SDK support in various languages make LiveKit a great choice for live audio and video.”

Voice AgentsMaker says so · source ↗
Pinch
PinchSOTA real-time voice translation, anywhere

“LiveKit allowed us to build and scale a virtual meeting platform with a team of two. That's incredible!”

Voice AgentsMaker says so · source ↗
Mode AI
Mode AIAI Assistant in your pocket

“Here’s what made it stand out: Built for real-time AI (not just calls) – LiveKit handles audio, video, and data streams together, making it ideal for multimodal AI agents Low latency, high performance – powered by WebRTC + SFU architecture for smooth, scalable real-time communication Open-source & flexible – we can customize, self-host, and deeply integrate into our stack instead of being locked into rigid workflows Developer-first architecture – clean SDKs across platforms and faster iteration for complex use cases Handles infra complexity – abstracts the hardest parts of WebRTC while still giving us control”

Voice AgentsMaker says so · source ↗
Roark
RoarkTest, monitor, and improve your voice agents

“LiveKit is the invisible backbone for our real-time calls. Their infra just works: low-latency, rock-solid, and developer-friendly. Instead of reinventing media servers, we get to focus on building great products.”

Voice AgentsMaker says so · source ↗
Toby
Toby

“Toby is a voice interviewer, so the conversation has to feel live: no awkward gaps, and you can cut in mid-question like you would with a real person. LiveKit’s Agents framework handles the hard parts (WebRTC transport, turn detection, interruptions) out of the box, and it’s open source, so I’m not locked into one STT, LLM or TTS vendor. I could swap models without rebuilding the pipeline. As a solo builder shipping my first product, that let me spend my time on the interview experience instead of audio plumbing.”

Voice AgentsMaker says so · source ↗
Beyond Presence
Beyond PresenceHyper realistic interactive avatars that feel truly human

“We use LiveKit for managed video streaming infrastructure and also use LiveKit agents as basis for our conversational agents. WebRTC streaming is really hard and LiveKit provides a great developer-friendly managed solution for that.”

Voice AgentsMaker says so · source ↗
KnockKnock!
KnockKnock!Minimal circular video calls that start with a "door" knock

“WEBRTC through livekit was a non-intensive way for me to get up and running. I have some ideas about a possible agent to be added in the future - but for not just video/audio works seamlessly.”

Voice AgentsMaker says so · source ↗
Voistory
VoistoryGone · domain no longer registered, Oct 2026Talk it out: your journal with no writing

“Absolutely state of the art, high quality and responsive team for our varied needs!”

Voice AgentsMaker says so · source ↗
Chikka.ai
Chikka.aiUncover User Insights with Intelligent AI Voice Interviewer

“The best open source platform for voice to voice communications! It really helps Chikka to become what it is today.”

Voice AgentsMaker says so · source ↗
Langfinity
LangfinityAI-powered real-time voice translation for 100+ languages

“Livekit has an amazing developer experience with pre-built React components and incredibly easy to implement real-time state management. Support through their slack has been very helpful.”

Voice AgentsMaker says so · source ↗
LightTwist
LightTwistRecord & stream your show in a realistic virtual studio

“We're using LiveKit for WebRTC and we've been able to integrate deeply to do things like get very accurate timestamps.”

Voice AgentsMaker says so · source ↗

Open source: a project that declares LiveKit as a dependency in its public code — verifiable, but not necessarily a live product.

What its projects tell coding agents

15 of the 20 open-source products built with LiveKit that were worked on in the last 180 days keep instruction files for coding agents — 75%, against 53% of all the projects we read. AGENTS.md is in 13, CLAUDE.md in 8.

899words in the median file
pnpmthe package manager most named, in 3 of 14 files
64%say how to test a change
Named more in these files than in other projects' — in how many of the 14:
What AGENTS.md files say about other tools →What open-source products tell their coding agents →

Alternatives to LiveKit

All alternatives by situation →

Questions makers ask about LiveKit

Is LiveKit good for production?

38 makers' products we track run on it, and 1 of them have since gone (the product, not necessarily because of LiveKit).

What is LiveKit used for?

Open-source WebRTC platform and framework for building realtime voice, video and AI agent applications. Makers' products we track use it for voice agents (38).

What are the alternatives to LiveKit?

For voice agents, the other options makers' products we track chose most are Daily (16), Vapi (16), Pipecat (5), Retell AI (4), Layercode (1). Open source or self-hostable among them: Pipecat. Each alternative, with the situation it fits, is on the LiveKit alternatives page.

When should you use LiveKit?

Voice happens inside your web or mobile app, or you need video too (voice agents). You want full control over every component of the pipeline, in Python (voice agents). Something else fits better if: you want a hosted voice agent but need to swap providers and call your own functions, pick Vapi or ElevenLabs; the agent answers or makes business phone calls, set up largely without code, pick Retell AI.

Is LiveKit open source or self-hostable?

Open source, and you can self-host it. source ↗

Can AI coding agents work with LiveKit?

No llms.txt, official MCP server or CLI found yet.

Who uses LiveKit?

38 makers' products we track, each with a source, and 27 open-source projects declare it in their code. The best known of them on Product Hunt: Talo by Palabra.ai (2,141 followers), Hey Noah (1,535 followers), SpatialChat (1,270 followers), Slashy (1,259 followers), Interactpitch (918 followers). source ↗