Skip to content

Redis Agent Memory Server

Give your AI agents persistent memory and context that gets smarter over time.

Transform your AI agents from goldfish 🐠 into elephants 🐘 with Redis-powered memory that automatically learns, organizes, and recalls information across conversations and sessions.

What is Redis Agent Memory Server?

Redis Agent Memory Server is a production-ready memory system for AI agents and applications that:

  • 🧠 Remembers everything: Stores conversation history, user preferences, and important facts across sessions
  • 🔍 Finds relevant context: Uses semantic search to surface the right information at the right time
  • 📈 Gets smarter over time: Automatically extracts, organizes, and deduplicates memories from interactions
  • 🔌 Works with any AI model: REST API and MCP interfaces compatible with OpenAI, Anthropic, and others

Why Use It?

  • Never lose conversation context across sessions
  • Provide personalized responses based on user history
  • Build agents that learn and improve from interactions
  • Scale from prototypes to production with authentication and multi-tenancy
  • Drop-in memory solution with REST API and MCP support
  • Works with existing AI frameworks and models
  • Production-ready with authentication, background processing, and vector storage
  • Extensively documented with examples and tutorials

Quick Example

from agent_memory_client import MemoryAPIClient

client = MemoryAPIClient(base_url="http://localhost:8000")

# Store a user preference
await client.create_long_term_memories([{
    "text": "User prefers morning meetings and hates scheduling calls after 4 PM",
    "memory_type": "semantic",
    "topics": ["scheduling", "preferences"],
    "user_id": "alice"
}])

# Later, search for relevant context
results = await client.search_long_term_memory(
    text="when does user prefer meetings",
    limit=3
)

print(f"Found: {results.memories[0].text}")
# Output: "User prefers morning meetings and hates scheduling calls after 4 PM"

Core Features

🧠 Two-Tier Memory System

Working Memory (Session-scoped)

  • Current conversation state and context
  • Automatic summarization when conversations get long
  • TTL-based expiration (1 hour default)

Long-Term Memory (Persistent)

  • User preferences, facts, and important information
  • Semantic search with vector embeddings
  • Advanced filtering by time, topics, entities, users
  • Semantic similarity: Find memories by meaning, not just keywords
  • Advanced filters: Search by user, session, time, topics, entities
  • Query optimization: AI-powered query refinement for better results
  • Recency boost: Time-aware ranking that surfaces relevant recent information

✨ Smart Memory Management

  • Automatic extraction: Pull important facts from conversations
  • Contextual grounding: Resolve pronouns and references ("he" → "John")
  • Deduplication: Prevent duplicate memories with content hashing
  • Memory editing: Update, correct, or enrich existing memories

🚀 Production Ready

  • Multiple interfaces: REST API, MCP server, Python client
  • Authentication: OAuth2/JWT, token-based, or disabled for development
  • Scalable storage: Redis (default), Pinecone, Chroma, PostgreSQL, and more
  • Background processing: Async tasks for heavy operations
  • Multi-tenancy: User and namespace isolation

Get Started

Ready to give your AI agents perfect memory?

New to memory systems?

Start with our quick tutorial to understand the basics and see immediate results.

🚀 Quick Start Guide

Ready to integrate?

Jump into the Developer Guide for memory patterns and integration strategies.

🧠 Developer Guide

What's New in v0.10.0

  • 🧠 Query Optimization

    AI-powered query refinement with configurable models for better search accuracy

    Learn More →

  • 🔗 Contextual Grounding

    Resolve pronouns and references in extracted memories for clearer context

    Learn More →

  • ✏️ Memory Editing

    Update and correct existing memories through REST API and MCP tools

    Learn More →

  • 🕐 Recency Boost

    Time-aware memory ranking that surfaces relevant recent information

    Learn More →

  • 🧠 Memory Strategies

    Configurable memory extraction: discrete facts, summaries, preferences, or custom prompts

    Learn More →

Community & Support

Ready to transform your AI agents? Start with the Quick Start Guide and build smarter agents in minutes! 🧠✨