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 addresses the problem of fragmented context when using multiple AI agents. Instead of repeating project backgrounds, preferences, and progress to every new tool (like Claude Code, Cursor, or DeepSeek Harness), Memmy provides a shared, structured memory layer that allows different agents to remember the same user and maintain task continuity across different platforms.

How it works

Memmy operates as a local memory service and agent runtime that sits between the user and various AI tools. It captures local AI collaboration history and converts it into structured memory. It provides a "Memory Skill" and hooks/plugins that can be installed into supported agents, allowing them to search, add, and retrieve knowledge from a centralized local store. It also includes its own Agent runtime capable of organizing information and continuing unfinished tasks.

Who it’s for

It is designed for developers and power users who use a variety of AI coding assistants and agents and want a unified memory system to avoid context loss when switching tools.

Highlights

  • Cross-Agent Continuity: Enables a seamless transition between tools like DeepSeek Harness, Claude Code, Codex, and Cursor by sharing project context.
  • Local Memory Service: Provides a dedicated CLI (memmy-memory) for managing knowledge and a local API for agent integration.
  • Flexible Deployment: Available as a desktop app, a CLI/TUI for Linux, or can be built from source.
  • BYOK Support: Allows users to bring their own model API keys for full control over the LLM provider.

Related

  • Project
    mem9-ai/mem9

    mem9 provides a persistent, searchable memory service for AI coding agents, offering hosted or self‑hosted deployments, multi‑agent sharing, hybrid vector/text search, smart ingest, and plugin integrations for major agent platforms.

  • Project
    MemoriLabs/Memori

    A persistent, structured memory layer for AI agents that captures conversations and and agent execution traces to eliminate session amnesia and reduce token costs.

  • Project
    doobidoo/mcp-memory-service

    A persistent, shared memory backend for AI agents that uses a knowledge graph and semantic search to maintain context across sessions.

  • 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
    NevaMind-AI/memU

    memU is a lightweight, agent‑driven personal memory system that records LLM session logs, turns useful interactions into reusable Markdown “skills”, and makes those skills searchable across sessions, agents, and devices. It works via small host‑adapter binaries (e.g., memu‑codex, memu‑claude‑code) that hook into agents’ session logs and instruction files. The core memory logic is ~500 lines of Python, storing embeddings in SQLite, Postgres, or an in‑memory store. Installation is a one‑message setup with an API key from memU Cloud (or self‑hosted). Once installed, agents automatically retrieve relevant skills before answering, and developers can feed custom conversations into memU via `memu memorize`. Licensed under Apache‑2.0.