Agents

Introduction

The Agents framework enables developers to create voice AI agents that can see, hear, and speak in real-time. It is a fully open-source platform designed for building server-side agentic applications.

Key Features:

• Real-time Interaction: Build agents that can interact with users in real-time using voice.
• Flexible Integrations: Mix and match various STT, LLM, TTS, and Realtime APIs to suit your use case.
• Open-source: Fully open-source, allowing you to run the entire stack on your own servers.
• Extensive WebRTC Support: Utilize LiveKit's SDK ecosystem for building client applications across major platforms.
• Telephony Integration: Seamlessly make and receive calls using LiveKit's telephony stack.
• Semantic Turn Detection: Reduce interruptions by detecting when a user has finished speaking.

Benefits:

• Customizable: Tailor agents to specific needs with dynamic tool creation and extensive plugin support.
• Community Driven: Actively developed with contributions welcomed from the community.
• Comprehensive Documentation: Detailed guides and examples to help you get started quickly.

Highlights:

• Supports various voice AI applications, including restaurant ordering, storytelling, and more.
• Easy installation and setup with pip for Python users.
• Active community and support through GitHub and LiveKit's Slack community.