Skip to main content
PraisonAI’s memory backends are pluggable — register your own adapter to store agent memory in any system.

​
Quick Start

1

Simple Usage

Use a built-in adapter via string to anchor the mental model:
from praisonaiagents import Agent

agent = Agent(
    name="assistant",
    instructions="Remember user preferences",
    memory="in_memory",  # Ephemeral dict-backed storage
)
agent.start("My favourite colour is blue")
2

With a Custom Adapter

Register your adapter, then point the agent at it:
from typing import Any, Dict, List, Optional
from praisonaiagents import Agent
from praisonaiagents.memory.adapters import register_memory_adapter


class RedisMemoryAdapter:
    def __init__(self, **kwargs):
        self._store: List[Dict[str, Any]] = []

    def store_short_term(self, text: str, metadata: Optional[Dict[str, Any]] = None, **kwargs) -> str:
        doc_id = str(len(self._store))
        self._store.append({"id": doc_id, "text": text, "metadata": metadata or {}})
        return doc_id

    def search_short_term(self, query: str, limit: int = 5, **kwargs) -> List[Dict[str, Any]]:
        hits = [e for e in self._store if query.lower() in e["text"].lower()]
        return hits[:limit]

    def store_long_term(self, text: str, metadata: Optional[Dict[str, Any]] = None, **kwargs) -> str:
        return self.store_short_term(text, metadata, **kwargs)

    def search_long_term(self, query: str, limit: int = 5, **kwargs) -> List[Dict[str, Any]]:
        return self.search_short_term(query, limit, **kwargs)

    def get_all_memories(self, **kwargs) -> List[Dict[str, Any]]:
        return list(self._store)


register_memory_adapter("redis", RedisMemoryAdapter)

agent = Agent(
    name="assistant",
    memory={"provider": "redis"},
)

​
How It Works

When Memory initialises, it resolves the provider through the adapter registry — the only code path for backend setup since PR #2060 removed orphaned legacy _init_* methods.

​
Built-in Adapters

AdapterRegistry nameBackendWhen to use
SqliteMemoryAdapter"sqlite"SQLite fileDefault persistent local storage
InMemoryAdapter"in_memory"Python dictTests, ephemeral workflows
Factory"chroma"ChromaDB (lazy)Vector search, local RAG
Factory"mongodb"MongoDB (lazy)Document store, Atlas Vector Search
Factory"mem0"Mem0 cloud (lazy)Managed graph / cloud memory
Heavy backends register as factories in praisonaiagents.memory.adapters.factories so optional dependencies load only when requested.

​
Register Your Own Adapter

Implement MemoryProtocol — at minimum: store_short_term, search_short_term, store_long_term, search_long_term, and get_all_memories. 
from praisonaiagents.memory.adapters import register_memory_adapter, get_memory_adapter

register_memory_adapter("my_backend", MyAdapter)
adapter = get_memory_adapter("my_backend")
Then use it from an agent: 
agent = Agent(memory={"provider": "my_backend"})

​
Common Patterns

Async adapter — implement AsyncMemoryProtocol (astore_short_term, asearch_short_term, etc.) when your backend is async-native. Lazy-loaded heavy backend — use register_memory_factory(name, create_fn) so imports like chromadb or pymongo happen inside the factory, not at package import time. Extending an existing adapter — subclass SqliteMemoryAdapter or wrap InMemoryAdapter and register under a new name.

​
Best Practices

Register adapters with register_memory_adapter or register_memory_factory instead of monkey-patching Memory internals.
Sync methods satisfy MemoryProtocol; add AsyncMemoryProtocol methods if your store supports non-blocking I/O.
Implement close() on adapters that hold clients (MongoDB, ChromaDB). Session.close() calls memory.close_connections() which forwards to the adapter.
from praisonaiagents.memory.adapters import list_memory_adapters
print(list_memory_adapters())  # ['sqlite', 'in_memory', 'mem0', 'chroma', 'mongodb', ...]

Memory Concepts

Provider strings, short-term vs long-term, and configuration basics.

Memory Cleanup

Session teardown and adapter close() lifecycle.

MongoDB Memory

Atlas Vector Search and use_vector_search configuration.

Memory Troubleshooting

ImportError and fallback behaviour when providers are missing.