Moss - Real-time Semantic Search for Conversational AI

Moss ships official SDKs for six platforms. They share one conceptual API (create or load an index, then query) and one index format, so you can build in one and query from another.

Python

Async Python SDK. pip install moss

JavaScript

Node.js server-side SDK. npm install @moss-dev/moss

Swift (iOS)

On-device iOS SDK via Swift Package Manager.

Elixir

Elixir SDK on Hex. {:moss, "~> 1.0"}

Browser

In-browser / WebAssembly SDK. npm install @moss-dev/moss-web

C

Native C library (libmoss).

Capabilities

Everything the SDKs can do. Pick a language above for install and quickstart; follow a link below for the details. Links below go to the Python pages; each topic has a JavaScript equivalent under the JavaScript SDK.

Capability	What it does	Learn more
Index management	Create, add, update, delete, get, and list indexes	Indexing
Load and query	Load an index into memory and run semantic search	Load and query
Hybrid search	Blend semantic and keyword scoring with `alpha`	Hybrid search
Metadata filtering	Narrow results with `$eq`, `$in`, `$near`, `$and`/`$or`, and more	Metadata filtering
Custom embeddings	Bring your own vectors with `model_id="custom"`	Custom embeddings
Multi-index search	Query across several loaded indexes in one call	Multi-index search
Real-time sessions	Local-first indexing during a live interaction	Sessions
Cross-agent handoff	Resume a session across agents, channels, and devices	Sessions
Hydration and sync	Hydrate from the cloud, auto-refresh, and push updates	Keeping indexes fresh

Models

moss-minilm (default) - fast, lightweight, good for edge and offline
moss-mediumlm - higher accuracy with reasonable performance
moss-litelm - the on-device default on iOS
custom - bring your own embedding vectors

Samples

Runnable end-to-end examples live in the moss repo, with parallel JavaScript and Python projects you can adapt by swapping in your own data.