THE RETRIEVAL PROBLEM
Agents make dozens of lookups per task. At 100–500ms each, that's seconds of dead time on every turn, every user. And with a remote database, your context is only as fresh as your last sync job.
Your agent is only as fast as its retrieval.
How Moss Solves It
Moss runs search inside your agent runtime. Sub-10ms lookups, always-current data, without rebuilding your infra.
Connect Once
Push your data source (docs, knowledge bases, or live data) via our SDK or portal.
Moss Handles the Rest
We index, sync, and distribute a compact index wherever your agent runs: browser, edge, device, or cloud.
Search Every Critical Path
Your agent retrieves context locally, in under 10ms. No hops. No lag. No infra to manage.
Get Started in Minutes
Install Moss and start querying in just a few lines of code
import { MossClient, DocumentInfo } from '@inferedge/moss'
const client = new MossClient(process.env.MOSS_PROJECT_ID!,
process.env.MOSS_PROJECT_KEY!)
const documents: DocumentInfo[] = [
{ id: 'doc1', text: 'How do I track my order? Log into your account.',
metadata: { category: 'shipping' } }
]WHAT TEAMS BUILD WITH MOSS
If you're building voice AI, copilots, or multimodal apps where retrieval is on your critical path, Moss is built for you.
Voice Agents & Copilots
Sub-10ms context retrieval for real-time conversation. Your agent recalls, reasons, and responds without the pause.
Docs & Knowledge Search
Instant semantic search inside help centers, knowledge bases, and internal tools, without sending data to a third party.
On-Device & Edge Apps
A lightweight runtime that runs in browsers, mobile apps, and desktop tools. Works offline, syncs when connected.
AI-Native Platforms
Drop Moss into your agent framework or dev tool. Built-in A/B testing for embeddings. Zero infra to manage.
BUILT FOR PRODUCTION
You bring your data. Moss powers the retrieval layer, indexing, packaging, and distributing it automatically, so semantic search runs close to where intelligence happens.
Sub-10ms retrieval, anywhere
Answers from local memory, zero network hops. Browser, edge, on-device, or cloud.
Privacy by architecture
Data stays on-device by default. No round-trips to cloud databases. Compliance-friendly for regulated industries.
Drop-in SDKs, zero infra
JavaScript and Python. No clusters, no replicas, no DevOps. Install and ship.
Built-in experimentation
Compare embeddings and index configs on your own corpus. Measure what works before you ship.
FREQUENTLY ASKED QUESTIONS
Everything you need to know about Moss and real-time semantic search for AI agents.