Integrations

Works with Your Stack

Drop-in sub-10ms semantic search for the frameworks and platforms you already use. Install the SDK, create an index, and start querying in minutes.

Agent Framework

LangChain

LangChain is the most popular framework for building LLM-powered applications.

DSPy

DSPy replaces hand-written prompts with compiled, optimized LLM programs.

AI SDK

Vercel AI SDK

The @moss-tools/vercel-sdk package exposes Moss operations as standard AI SDK tools.

Voice Platform

LiveKit

LiveKit provides real-time audio and video infrastructure for voice agents.

Pipecat

Pipecat is an open-source framework for building voice and multimodal agents.

VAPI

VAPI provides hosted voice agent infrastructure with support for custom knowledge bases via webhooks.

ElevenLabs

ElevenLabs provides conversational AI agents with speech synthesis.

Docs Platform

VitePress

The vitepress-plugin-moss package adds real-time semantic search to any VitePress documentation site.

Protocol

MCP Server

The @moss-tools/mcp-server package exposes Moss as a Model Context Protocol server, giving AI coding assistants like Claude Desktop, Cursor, and VS Code direct access to your knowledge base.

Web Framework

Next.js

Moss integrates with Next.js using Server Actions for a clean client-server search pattern.

Eliminate latency from your AI stack

<10 ms retrieval for voice AI, copilots, and real-time systems.

Test performance Talk to an Engineer

No credit card requiredDeploy in minutesProduction ready