Why Moss ​

Moss is a high-performance runtime for real-time semantic search. It delivers sub-10 ms retrieval, instant index updates, and zero infrastructure overhead. It runs wherever your intelligence lives—in-browser, on-device, or in the cloud—so search feels native and effortless.

Key Benefits ​

• Zero-Hop Latency — Answers from device memory in <10 ms with no internet delay
• Model-Agnostic — Works with any AI model, no vendor lock-in
• Offline-First, Cloud-Smart — Runs offline with cloud-powered sync and analytics
• Zero Infrastructure Overhead — Fully managed hybrid cloud and on-device retrieval

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 with no lag even on bad networks

Quick Start ​

npm install @inferedge/moss

pip install inferedge-moss

import { MossClient } from '@inferedge/moss'

const client = new MossClient(process.env.PROJECT_ID!, process.env.PROJECT_KEY!)
await client.createIndex('docs', [{ id: '1', text: 'Vector search in production' }], 'moss-minilm')

await client.loadIndex("docs")
const results = await client.query('docs', 'production search tips')

from inferedge_moss import MossClient, DocumentInfo

client = MossClient("$PROJECT_ID", "$PROJECT_KEY")
await client.create_index(
    "docs",
    [DocumentInfo(id="1", text="Vector search in production")],
    "moss-minilm",
)

await client.load_index("docs")
results = await client.query("docs", "production search tips")

For detailed setup instructions, credentials configuration, and more examples, see the Getting Started guide.

Next steps ​

📬 Contact ​

For queries, support, commercial licensing, or partnership inquiries, contact us: contact@usemoss.dev