# Memsy

> Persistent memory for AI agents and applications — official SDKs for Python and Node.js, plus the raw HTTP API.

## Documentation

- [Actors and Sessions](https://docs.memsy.io/docs/actors-and-sessions): How actor_id and session_id control grouping and retrieval.
- [Async Client (Python)](https://docs.memsy.io/docs/async-client): AsyncMemsyClient mirrors the Python sync client method-for-method.
- [Async Processing](https://docs.memsy.io/docs/async-processing): Why ingest returns before processing completes — and how to poll.
- [Console Memories](https://docs.memsy.io/docs/console-memories): Browse and inspect stored memories via client.memories.
- [Error Handling](https://docs.memsy.io/docs/error-handling): The typed exception hierarchy and how to catch each case.
- [Events and Memories](https://docs.memsy.io/docs/events-and-memories): The mental model — raw events in, extracted memories out.
- [FAQ](https://docs.memsy.io/docs/faq): Answers to questions we hear most often.
- [Memsy Docs](https://docs.memsy.io/docs): Persistent memory for AI agents and applications. Official SDKs for Python and Node.js, plus the raw HTTP API.
- [Ingesting Events](https://docs.memsy.io/docs/ingesting-events): Batch size, metadata, timestamps, scoping — everything beyond the quickstart.
- [Installation](https://docs.memsy.io/docs/installation): Install the Memsy SDK for your language — Python or Node.js — or call the HTTP API directly.
- [Onboarding Hierarchy](https://docs.memsy.io/docs/onboarding): Create orgs, roles, and teams to scope memory extraction and retrieval.
- [Quickstart](https://docs.memsy.io/docs/quickstart): Sign up, install Memsy, and run your first ingest + search in under five minutes.
- [Retries and Timeouts](https://docs.memsy.io/docs/retries): Auto-retry on 429, how to tune it, and when to back off yourself.
- [Searching Memory](https://docs.memsy.io/docs/searching-memory): Natural-language queries, thresholds, scoping, and score interpretation.
- [Sign Up & Get an API Key](https://docs.memsy.io/docs/signup): Create an account, provision an organization, and generate your first API key.
- [Usage and Rate Limits](https://docs.memsy.io/docs/usage-and-rate-limits): Track plan consumption from response headers automatically.
- [MemsyControlClient](https://docs.memsy.io/docs/reference/node/control-client): The Node.js MemsyControlClient — control-plane endpoints (api/) for identity, billing, keys, usage, events, and Pro interest.
- [Errors](https://docs.memsy.io/docs/reference/node/errors): The Node SDK exception hierarchy — what gets thrown and how to catch it.
- [MemsyClient](https://docs.memsy.io/docs/reference/node/memsy-client): The Node.js MemsyClient — constructor, methods, and return shapes. Async-only, Promise-based, ESM + CJS.
- [Models & Types](https://docs.memsy.io/docs/reference/node/models): Request and response type definitions for the Node SDK.
- [Sub-resources](https://docs.memsy.io/docs/reference/node/resources): orgs, roles, teams, and memories — sub-resources on the Node MemsyClient.
- [AsyncMemsyClient](https://docs.memsy.io/docs/reference/python/async-memsy-client): Async HTTP client — mirrors MemsyClient method-for-method.
- [MemsyControlClient](https://docs.memsy.io/docs/reference/python/control-client): Control-plane client for billing, API keys, usage, and account management.
- [Exceptions](https://docs.memsy.io/docs/reference/python/exceptions): Every error class the SDK can raise.
- [MemsyClient](https://docs.memsy.io/docs/reference/python/memsy-client): Synchronous HTTP client — constructor, methods, parameters, exceptions.
- [Models](https://docs.memsy.io/docs/reference/python/models): Request and response dataclasses exposed by the SDK.

## Links

- [GitHub](https://github.com/memsy-io/memsy)
- [Support](mailto:cloudops@memsy.io)