Build with Redis Agent Memory
API reference, SDK examples, and language-specific guides for building with Redis Agent Memory.
Everything you need to start building with Redis Agent Memory — REST API reference, SDK examples, and language-specific guides.
What you can build
Redis Agent Memory gives your agents a two-tier memory layer available via REST API and Python SDK:
- ●Session memory — Store the current conversation as a sequence of events. Query by session ID to reconstruct context for the next agent turn.
- ●Long-term memory — Automatically extract and persist important facts, preferences, and patterns from session events. Search semantically to retrieve what's relevant.
- ●Multi-session recall — Retrieve memories across sessions and users using semantic search, with filtering by session, owner, namespace, topic, and memory type.
- ●Direct memory writes — Bulk-create long-term memories from external sources without going through a session, for importing existing knowledge.
REST quickstart
Follow the Redis Cloud Agent Memory REST quickstart to create a service and run complete curl commands for session memory and long-term memory.
After you finish the quickstart, review the Agent Memory API examples and API reference.
Language guides
The guides below show how to implement agent memory patterns directly using Redis client libraries without the managed Agent Memory service.
Use these guides if you prefer to self-host, want full control over the implementation, or use a language that doesn't have an Agent Memory SDK.
For the managed service, follow the Redis Cloud REST quickstart.
Step-by-step examples for building agent memory into your application using your preferred Redis client library:
Set up authentication
Redis Cloud API requests require an Agent Memory API key and a Store ID. Send the key as a bearer token in the Authorization header, and include the Store ID in the request path.
The Redis Cloud REST quickstart shows how to get these values and use them in a request.