MemoriLabs/Memori

Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems. Built for enterprise, Memori works with the data infrastructure you already run, no rip-and-replace, and deploys across managed cloud, single-tenant cloud, VPC, and on-premises.

What it solves

Memori provides a persistent, structured memory layer for AI agents, preventing "session amnesia" where agents forget information between interactions. It allows agents to remember user preferences, project conventions, and execution outcomes (like tool calls and decisions) without requiring the developer to manually manage large prompt contexts or database schemas.

How it works

Memori integrates as a background layer that hooks into LLM interactions. It automatically captures and persists conversations and agent execution traces. It uses a system of attribution (linking memories to specific entities, processes, and sessions) to organize information. This structured memory is then recalled automatically or via explicit tools (like memori_recall) to provide context to the LLM during subsequent requests, significantly reducing the need for full-context prompting.

Who it’s for

  • AI Agent Developers: Those building agents using frameworks like LangChain, Pydantic AI, or Agno.
  • Software Engineers: Developers using AI coding assistants (Claude Code, Cursor, Warp) who want their tools to remember project-specific patterns.
  • Enterprise Teams: Organizations running high-volume agentic workflows that need to reduce token costs and improve accuracy by eliminating redundant agent discoveries.

Highlights

  • Framework Agnostic: Works with major LLMs (OpenAI, Anthropic, Gemini, etc.) and frameworks (LangChain, Pydantic AI, Agno).
  • BYODB Support: Offers a "Bring Your Own Database" option for those who prefer not to use Memori Cloud.
  • MCP Integration: Supports the Model Context Protocol (MCP), allowing it to be added to AI clients like Claude Code or Cursor with a single command.
  • Advanced Augmentation: Automatically tracks and enhances memories at the entity, process, and session levels, capturing attributes, facts, and relationships.
  • High Efficiency: Outperforms retrieval-based memory systems on the LoCoMo benchmark, using only a small fraction of the full-context footprint to maintain reasoning quality.

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
    RichmondAlake/memorizz

    A Python framework for building memory-first AI agents that use persistent episodic, semantic, and procedural memory to recall experience and learn new skills over time.

  • 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
    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.

  • Project
    redis/agent-memory-server

    A structured memory layer for AI agents that provides intelligent short-term session memory and persistent long-term context using a two-tier storage model.