redis/agent-memory-server

Fast and flexible memory for agents and AI applications using Redis

What it solves

Redis Agent Memory provides a persistent, structured memory layer for AI agents, eliminating the need for teams to build custom infrastructure for session handling, extraction, retrieval, and lifecycle management of agent context.

How it works

It employs a two-tier memory model:

  1. Session Memory: Maintains active conversation state, history, and metadata with configurable time-to-live (TTL) controls for retention.
  2. Long-term Memory: Stores extracted facts and learned patterns as text and vector embeddings for semantic retrieval.

As new events are written to working memory, the system automatically extracts important information and promotes it to long-term memory in the background to avoid slowing down the agent's live loop.

Who it’s for

Developers and teams building AI agents who need a managed service or a reference implementation to handle complex context compounding across turns, sessions, channels, and agents.

Highlights

  • Two-Tier Architecture: Combines short-term session state with long-term semantic memory.
  • Automatic Extraction: Background promotion of key information from session to long-term memory.
  • REST and MCP Interfaces: Provided in the open-source reference implementation (V0).
  • Redis-backed Semantic Search: Enables efficient retrieval of relevant past interactions.
  • Managed Service Option: Available as part of Redis Iris for production-ready API key management and memory schemas.

Related

  • Project
    mem9-ai/mem9

    A persistent memory layer for AI agents that enables shared context and recall across sessions, machines, and different agent runtimes.

  • Project
    TencentCloud/TencentDB-Agent-Memory

    A shared memory server and management hub that allows AI agents to persist and share experience, skills, and project knowledge across different sessions and frameworks.

  • Project
    sopaco/cortex-mem

    A Rust-based long-term memory framework for AI agents that uses a three-tier hierarchical architecture and a virtual filesystem to provide persistent, context-aware interactions.

  • Project
    MemoriLabs/Memori

    A persistent, structured memory layer for AI agents and LLMs that automatically captures and recalls user preferences and agent actions to reduce token costs and maintain context across sessions.

  • Project
    beilusaiying/always-accompany

    A multi-purpose AI agent framework focused on context and attention mechanisms, providing layered memory and dynamic retrieval for long-term companionship, coding, and work.