Docs/Getting Started

Introduction to Recall

Build AI applications with persistent, intelligent memory that scales from development to production.

What is Recall?

Recall is a hybrid memory system designed specifically for AI applications, particularly Large Language Models (LLMs) and agents. It provides a sophisticated memory layer that combines:

  • Redis Cache for lightning-fast memory retrieval (sub-millisecond response times)
  • Mem0 Cloud for persistent, searchable long-term memory
  • Intelligent synchronization between cache and cloud storage
  • Priority-based caching to keep important memories instantly accessible

Key Features

Hybrid Architecture

Seamlessly combines local Redis caching with cloud persistence, giving you the best of both worlds - speed and reliability.

Intelligent Caching

Automatically manages cache based on usage patterns, priority levels, and access frequency to optimize performance.

Simple Integration

Drop-in replacement for existing memory systems with a clean, intuitive API that works with any AI framework.

Production Ready

Built for scale with automatic failover, health monitoring, and comprehensive error handling.

Why Recall?

The Problem

Traditional AI memory systems force you to choose between:

  • Speed: Local storage is fast but volatile and doesn't scale
  • Persistence: Cloud storage is reliable but adds latency
  • Complexity: Managing both systems manually is error-prone

The Solution

Recall automatically manages a hybrid memory system that:

  • Serves frequently accessed memories from cache in under 1ms
  • Persists all memories to the cloud for reliability
  • Synchronizes changes automatically
  • Handles failures gracefully with automatic fallback

Core Concepts

Memory

A memory is a piece of information stored with metadata including:

  • Content (text, structured data, embeddings)
  • User association
  • Priority level (low, medium, high, critical)
  • Timestamps and access patterns
  • Custom metadata

Cache Layers

Recall uses a multi-tier caching strategy:

  • Hot Cache: Most frequently accessed memories (Redis)
  • Warm Storage: Recent or important memories (Mem0)
  • Cold Storage: All historical memories (Cloud)

Synchronization

Automatic bi-directional sync ensures:

  • New memories are cached and persisted
  • Cache misses are filled from cloud
  • Updates propagate to all layers
  • Consistency is maintained

Use Cases

AI Assistants

Give your AI assistants long-term memory about user preferences, conversation history, and learned behaviors.

Customer Support Bots

Remember customer issues, preferences, and resolution history across all interactions.

Personalization Engines

Build recommendation systems that remember and learn from every user interaction.

Knowledge Management

Create intelligent knowledge bases that remember facts, relationships, and context.

Architecture Overview

Claude Desktop
MCP Protocol
r3 Server
Redis(L1 Cache)
Mem0 Cloud(L2 Storage)
<5ms
Cache Hit
~200ms
Cache Miss
~10ms
First Store

Quick Example

Python
1from recall import RecallClient
2

3# Initialize with simple configuration
4client = RecallClient(
5    redis_url="redis://localhost:6379",
6    mem0_api_key="your-api-key"
7)
8

9# Store a memory
10client.add("User prefers dark mode interfaces",
11          user_id="user123",
12          priority="high")
13

14# Retrieve memories (served from cache if available)
15memories = client.search("user interface preferences",
16                        user_id="user123")
17

18# Memories are automatically cached for fast access
19# and persisted to cloud for reliability

Next Steps

Chatbot with MemoryQuick Start