Memory Storage

PraisonAI supports 22+ database backends for memory persistence. Choose the right one for your use case.

Storage Categories

Conversation Stores

Store conversation history and chat context. Best for session continuity.

PostgreSQL

Production-ready relational DB

MySQL

Popular relational DB

SQLite

Zero-config local storage

JSON

Simple file-based storage

Supabase

Managed Postgres

Neon

Serverless Postgres

State Stores

Store agent state, checkpoints, and runtime data. Best for complex workflows.

Redis

High-speed caching

MongoDB

Document store

DynamoDB

AWS managed

Firestore

Google Cloud

Upstash

Serverless Redis

Dakera

Decay-weighted vector recall

Quick Setup

from praisonaiagents import Agent

# SQLite (zero-config, default)
agent = Agent(memory=True)

# PostgreSQL
agent = Agent(
    memory={
        "db": "postgresql://localhost/mydb",
        "session_id": "user-123"
    }
)

# Redis
agent = Agent(
    memory={
        "backend": "redis",
        "db": "redis://localhost:6379",
        "session_id": "user-123"
    }
)

Choosing a Database

Use Case	Recommended	Why
Local development	SQLite/JSON	Zero config
Production web app	PostgreSQL	Reliable, scalable
High-speed caching	Redis	Sub-ms latency
Serverless	Neon/Upstash	No server management
AWS infrastructure	DynamoDB	Native integration
Decay-weighted recall across sessions	Dakera	Importance-scored, time-decayed memory server

For self-hosted decay-weighted vector memory with importance scoring and tiered recall, see Dakera Memory.

Storage Backends

For training data, sessions, and general persistence, PraisonAI provides pluggable storage backends:

Backend	Dependencies	Best For
FileBackend	None	Development, debugging
SQLiteBackend	None	Production, concurrent access
RedisBackend	`redis`	High-speed caching, distributed

from praisonaiagents.storage import FileBackend, SQLiteBackend, RedisBackend

# File-based (default)
file_backend = FileBackend(storage_dir="~/.praisonai/data")

# SQLite (recommended for production)
sqlite_backend = SQLiteBackend(db_path="~/.praisonai/data.db")

# Redis (for distributed systems)
redis_backend = RedisBackend(url="redis://localhost:6379", prefix="praison:")

FileMemory sanitises user_id before using it as a directory name — values containing path separators, .., or other unsafe characters fall back to "default". This prevents accidental writes outside the configured memory directory.

Durability

FileMemory writes are atomic. Every _write_json writes into a same-directory temp file, fsyncs it, then os.replaces it into place — a crash mid-write (SIGKILL, power loss, OOM) can never leave the memory file empty or half-written. Same guarantee on POSIX and Windows.

flock-based mutual exclusion still applies on Unix so concurrent writers see a consistent view (Windows has no flock; atomicity of os.replace still holds).
Temp files use a .<name>.…tmp prefix inside the memory directory. A crash between temp creation and rename leaves the temp file behind; it is safe to delete manually and is otherwise harmless.

See Storage Backends for detailed usage with all components.

Database Overview

Complete database reference

Session Resume

Continue conversations

Storage Backends

Pluggable storage backends

Dakera Memory

Self-hosted decay-weighted vector memory

​Memory Storage

​Storage Categories

​Conversation Stores

PostgreSQL

MySQL

SQLite

JSON

Supabase

Neon

​State Stores

Redis

MongoDB

DynamoDB

Firestore

Upstash

Dakera

​Quick Setup

​Choosing a Database

​Storage Backends

​Durability

​Related

Database Overview

Session Resume

Storage Backends

Dakera Memory

Memory Storage

Storage Categories

Conversation Stores

State Stores

Quick Setup

Choosing a Database

Storage Backends

Durability

Related