#77th of 26 in Voice

agents

Python framework for realtime voice and multimodal agents on LiveKit WebRTC

Live demo ↗ Documentation ↗ Website ↗ Repository on GitHub ↗

Stars: 14.7k
License: Apache-2.0
Last commit: Oct 2026
Last release: Oct 2026
Language: Python

Missed the latest GitHub check; these facts may be older.

Overview

LiveKit Agents is a Python framework for building server-side agents that join LiveKit rooms as realtime participants. It wires together VAD, STT, LLM and TTS (or a realtime model API) through plugins, with tool calling, multi-agent handoff, job dispatch, SIP telephony and MCP tool support. A built-in test framework can run agent sessions and judge replies with an LLM.

Who it is for: Developers building realtime voice or phone agents in Python

Strengths

Mix STT, LLM, TTS or realtime APIs via plugins (OpenAI, Deepgram, Cartesia, Google)
Built-in job dispatch and AgentServer for scheduling sessions across processes
Telephony via LiveKit SIP for inbound and outbound calls
Test framework asserts on tool calls and uses LLM judges for replies

Weaknesses

Needs a LiveKit server (Cloud or self-hosted) and credentials beyond console mode
README examples default to LiveKit Inference, a LiveKit Cloud service
Turn detection models use the LiveKit Model License, not Apache-2.0
This repo is Python only; the JS/TS library is a separate repository

What it needs

no GPU
Needs LiveKit server or LiveKit Cloud, STT/LLM/TTS provider API keys or LiveKit Inference
Models: OpenAI, Deepgram, Cartesia, Google Gemini, OpenAI Realtime API

Also in Voice

See all 26

Also in Voice
Rank	Project	Score
1	voicestudioDesktop app for voice cloning, dubbing and dictation with local speech models66.4k starsAGPL-3.0	82 out of 100
2	whisper.cppC/C++ port of OpenAI Whisper for local speech-to-text transcription54.4k starsMIT	76 out of 100
3	buzzOffline desktop app for transcribing and translating audio with Whisper22k starsMIT	74 out of 100
#4	VoiceboxLocal voice studio for cloning, TTS, dictation and agent speech57.5k starsMIT	70 out of 100
#5	meetilyDesktop app that records, transcribes and summarizes meetings locally Live demo ↗ (opens in a new tab)31.7k starsMIT	66 out of 100

How to choose

Latency decides usability for voice agents; check the end-to-end numbers the project publishes.
Most quality models need a GPU; CPU-only setups are slower and limited to smaller models.
Check language coverage and whether models are downloaded at build or at first run.

Health

Releases: Not checked
Top contributor: Not checked
Security advisories: Not checked
Package advisories: Not checked
OpenSSF Scorecard: Not checked

Not read for this project yet: each refresh reads the facts of a few projects. Bots and coding-agent accounts are left out of the commit counts. Not part of the score: how we check.

License in plain words

Apache-2.0 Permissive

Use it at work: Yes
Change it and rebrand it: Yes
Sell it or host it for others: Yes

Your part: Keep the notices and mark the files you change. It also grants you the contributors’ patent rights.

A plain summary, not legal advice. Read the license on GitHub ↗ (opens in a new tab)

#7 of 26 in Voice on Archestack, as of 15 Oct 2026.

In your README

The badge updates twice a day.

[![Archestack](https://archestack.com/badge/livekit/agents.svg)](https://archestack.com/best-of-ai/projects/agents/)

How badges work

On your site or blog

A card with the rank, score and signals, in light or dark to match the reader.

<iframe src="https://archestack.com/embed/best-of-ai/agents/" title="agents on Archestack" width="400" height="270" style="border:0;max-width:100%" loading="lazy"></iframe>

Preview the card

Best of Open-Source AI on GitHub

Each review comes from the project's README and facts we check on GitHub. The fix form opens with agents filled in.