Persistent Memory
Agents that remember. Store facts, preferences, and context across conversations — per agent or shared across your entire system.
Live Demo
Watch memory in action
As the conversation flows, the agent stores facts and recalls them later to give personalized, context-aware responses.
Memory Types
Two layers of memory
Agent Memory
Private to each agent. Store facts, learned patterns, and preferences that only this agent needs. Perfect for specialization.
Shared Memory
Accessible by all agents in the system. Share knowledge, coordinate state, and build collective understanding across your agent team.
Storage
Pluggable backends
Choose where memory lives. Start simple with in-memory or file storage, then scale to any backend you need.
In-Memory
Fast, ephemeral storage for development and testing. Data lives in Python dicts.
File System
Persist memory to JSON files on disk. Survives restarts with zero setup.
SQLite
Lightweight relational storage. Great for structured queries and local production use.
Custom
Implement the CacheStore interface for Redis, PostgreSQL, MongoDB, or any storage you need.
Architecture
Context management
Three layers work together to give agents the right context at the right time, without exceeding token limits.
Agents that remember
Give your agents context that persists. No more starting from scratch.