MemTensor/memmy-agent

🍙 A personal AI agent & local memory hub for all AI agents, gives every AI one shared, fully controlled memory and persistent context — all AI remember the same you. Now supports Claude Code, Codex, OpenClaw and Hermes Agent etc.

What it solves

Memmy provides a shared, persistent memory layer for AI agents. It solves the problem of context loss when switching between different AI tools (such as Claude Code, Cursor, or DeepSeek Harness), ensuring that project background, user preferences, and progress are maintained across different agents.

How it works

Memmy acts as a local memory service and agent runtime. It captures AI collaboration history and transforms it into structured memory. This memory is then made available to other agents via hooks, plugins, or a dedicated CLI/TUI. It can be deployed as a desktop app or as systemd services on Linux, and it supports a Bring Your Own Key (BYOK) mode for model API access.

Who it’s for

Developers and power users who use multiple AI coding assistants or agents and want a unified memory across their entire AI toolset.

Highlights

  • Cross-Agent Continuity: Allows users to move between different AI agents without losing context.
  • Local Memory Service: Provides a CLI (memmy-memory) to search, add, and OpenAI-compatible API access for memory retrieval.
  • Broad Compatibility: Works with a wide range of agents including Claude Code, Cursor, Codex, and DeepSeek Harness.
  • Extensible Infrastructure: Planned expansions to include browser activity and local documents as memory sources.

Related

  • 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
    MemMachine/MemMachine

    An open-source long-term memory layer for AI agents that enables persistent storage and recall of user preferences and conversational context across sessions.

  • Project
    MemTensor/MemOS

    A memory operating system for LLMs and AI agents that provides persistent, multi-modal long-term memory and unified management tools.

  • 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
    rtk-ai/icm

    A permanent, unified memory layer for AI agents that allows multiple AI tools to share a single persistent knowledge base via a SQLite database.