Skip to main content

Real-time retrieval for conversational AI

Sub-10 ms retrieval for voice agents, copilots, and multimodal apps.

Quick StartQuick Start

Quick Start

Call the Moss model in minutes, then ground it in your own index.

Core ConceptsCore Concepts

Core Concepts

Learn how indexes, hybrid search, and real-time updates work under the hood.

IntegrationsIntegrations

Integrations

Connect Moss to LiveKit, Pipecat, LangChain, Vercel AI SDK, and more.

SDK ReferenceSDK Reference

SDK Reference

Full API reference for the Python and TypeScript SDKs, with code examples.

API ReferenceAPI Reference

API Reference

Explore every REST endpoint with authentication, request parameters, and responses.

Voice AgentsVoice Agents

Voice Agents

Build voice agents that retrieve context during the conversation.