Search

More Filters

Show More
Add Listing
Go Back

agents

0
New
Multi-Agent Platforms & Frameworks
Report

Report Abuse

Basic Information

LiveKit Agents is a Python framework for building realtime, programmable participants that run on servers. It is intended for developers who need to create conversational, multi-modal voice agents that can hear, speak, transcribe, and optionally perceive media. The repository provides core abstractions such as Agent, AgentSession, entrypoint handlers, and Worker processes to manage live user interactions and concurrent sessions. It integrates speech-to-text, text-to-speech, large language models, and Realtime APIs so agents can be composed from modular plugins. The project includes examples for voice agents, multi-agent handoffs, transcribers, video avatars, telephony callers, and text-only bots. Documentation, example code, and runtime modes for local testing, development with hot reload, and production deployment are included to help teams iterate and operate agents connected to LiveKit servers or self-hosted deployments.

Links

Stars
7061
App URL
https://github.com/livekit/agents
Github Repository
https://github.com/livekit/agents/blob/main/README.md

Categorization

App Details

Features
The README highlights a feature set focused on realtime conversational and multimodal workflows. Flexible integrations allow mixing STT, LLM, TTS, and realtime models via plugins for providers like Deepgram, OpenAI, ElevenLabs, Silero, and others. Built-in job scheduling and dispatch APIs manage task distribution and connect end users to agents. Extensive WebRTC client support enables cross-platform clients. Telephony integration works with LiveKit"s SIP stack for inbound and outbound calls. Data exchange is supported via RPCs and Data APIs. Semantic turn detection reduces interruptions. Native MCP support enables tool integration from MCP servers. A builtin test framework and judge utilities help validate LLM-driven behavior. The project is open-source and installable via pip with optional provider extras and includes many runnable examples and guides.
Use Cases
This framework helps teams build and operate reliable realtime AI agents by providing reusable building blocks and integrations that combine speech, language, and realtime media. Developers can spin up voice or text agents, route multi-user rooms, and orchestrate multi-agent handoffs using provided session and worker abstractions. Telephony and WebRTC client support simplify deploying agents that interact with phones or browser/mobile clients. The integrated dispatch and scheduling features let services connect end users to agents at scale. Builtin testing facilities and example scenarios reduce risk from nondeterministic LLM outputs. The plugin ecosystem and documentation make it easier to swap model providers and add tools, and multiple run modes support local testing, development with hot reloading, and production deployment to LiveKit or self-hosted servers.

Categories

Content Creation (5042)
Monetization & Business (2246)
Development Tools (1407)
Marketing & Social Media (1403)
Education & Career (1380)
Multi-Agent Platforms & Frameworks (1009)
Health & Life (957)
AI Resources (920)
Agents & Automation (778)
Data & Analytics (764)
Productivity Tools (679)
Writing & Editing (666)

Similar Listings

listing image

virtual lab

0 (0 review)
listing image

mnemo

0 (0 review)
listing image

EdgeChains

0 (0 review)
listing image

RAG Agents Accelerator

0 (0 review)
listing image

LLM Zero to Hundred

0 (0 review)

Featured Listings

Tags

Please fill the required fields*