REAL-TIME SEMANTIC SEARCH FOR
A search runtime for voice agents, copilots, and multimodal apps. Sub-10ms lookups, zero infrastructure. Built in Rust and WebAssembly.
Plug-and-play Semantic Search across every surface
Get real-time retrieval inside apps, browsers, and enterprise agents — with centralized management, analytics, and scale built in.
$Trusted by 500+ teams at
HOW IT WORKS
Three steps from your data to sub-10ms retrieval. No infrastructure to manage.
Connect Your Data
Push docs, knowledge bases, or chat history to Moss via our SDK or portal.
Moss Indexes & Distributes
We build a compact index and deploy it wherever your agent runs — browser, edge, device, or cloud.
Query in <10ms
Your agent retrieves context locally. Zero network hops. Zero infrastructure to manage.
5-LINE INTEGRATION
Get started with Moss in seconds
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' } }
]WHO IS IT FOR?
Moss is for developers building conversational, voice, and multimodal AI - experiences where every millisecond shapes how human the interaction feels.
For real-time, offline-capable assistance.
Superfast search without sending data to others.
Tiny engine (<20kB) that fits anywhere.
Keeps code local, great for security audits.
Combine speed with optional analytics and rollouts.
COMMON USE CASES
Where teams are putting Moss to work today...
Copilot Memory
Recall user context instantly, even offline.
Docs Search
Fast, private search inside help centers.
Desktop Productivity
Smart search in note apps or IDEs without sending data online.
AI-Native Apps
Sub-10ms search on phones and AI-PCs — no lag even with bad network.
HOW WE DELIVER?
You bring your data. Moss powers the retrieval layer - indexing, packaging, and distributing it automatically, so semantic search runs close to where intelligence happens. It enables your application to:
Run instantly, anywhere
Moss brings real-time semantic search to any environment - inside browsers, apps, or your own infrastructure - with sub-10 ms retrieval and no setup overhead.
Stay personal and private
Each user’s data can be embedded, searched, and updated locally, so experiences feel faster and more personal without sending data to the cloud.
Scale effortlessly
A simple cloud dashboard manages analytics, policies, and updates - giving teams visibility and control without maintaining infrastructure.
Get smarter over time
Moss continuously improves search quality and syncs enhancements automatically. Built-in A/B testing for embeddings makes it easy to compare and tune indexes for the best retrieval results.