Memsy Docs

Memsy turns the raw events your AI app produces — user messages, assistant replies, tool results — into structured, searchable long-term memory.

This site documents the Memsy HTTP API and the official client libraries. Code examples throughout the docs are tabbed for Python, Node.js, and cURL — pick the language you work in.

pip install memsy

npm install @memsy-io/memsy

# No install — call the API directly with any HTTP client.
curl -H "Authorization: Bearer $MEMSY_API_KEY" "$MEMSY_BASE_URL/health"

Quickstart

Memsy Studio

Try Memsy in the dashboard — drop text or documents in and watch them become memory, no code required.

Core Concepts

Events, memories, actors, sessions, and the async processing model.

Cookbooks

Runnable end-to-end recipes — Next.js, FastAPI, Slack, and tool-calling agents.

Python Reference

Every public class, method, and model in the Python SDK — with typed parameter tables.

Node Reference

The Node.js SDK API surface — MemsyClient, error classes, and types.

What the SDKs do

Ship events to Memsy with a single ingest() call (batched, async on the server).
Retrieve semantically relevant memories with search().
Surface usage, rate-limit, and plan information on every response.
Map HTTP errors to strongly-typed exceptions (AuthenticationError, RateLimitExceeded, MemsyAuthError, …).
Retry rate-limited requests automatically with exponential backoff.

What they do not do

The SDKs are thin HTTP clients. They do not run memory extraction, embeddings, or vector search locally — all processing happens on the Memsy platform.