GeminiLight/MindOS

MindOS is a Human-AI Collaborative Mind System, where human thinks and agents act. Globally sync your mind for all agents: transparent, controllable, and evolving symbiotically.

What it solves

MindOS creates a shared, local-first knowledge base that acts as a "second brain" for both humans and AI agents. It eliminates the need to repeatedly provide the same context, profiles, or project details to different AI tools, breaking memory silos between various agents.

How it works

MindOS stores knowledge as local plain-text Markdown files for privacy and ownership. It uses a Model Context Protocol (MCP) server and packaged "Skills" to provide supported AI agents (like Claude Code, Cursor, and Gemini CLI) with a standardized path to access and update this shared knowledge base. It also includes a GUI workbench for humans to organize notes and a YAML-based workflow engine for executing repeatable agent tasks.

Who it’s for

Users who work with multiple AI agents and want a persistent, synchronized memory across all of them, as well as those who prefer local-first, transparent knowledge management.

Highlights

  • Cross-Agent Sync: Uses MCP and Skills to share durable context across different AI tools.
  • Local-First: Knowledge is stored in plain text for privacy and full user control.
  • Human-AI Co-creation: Allows humans to distill conversations and corrections into reusable SOPs and instructions for agents.
  • Integrated Tooling: Includes a desktop app, a web clipper for capturing web content, and an Agent Inspector for auditing tool calls.
  • Workflow Orchestration: Supports YAML-defined workflows to automate repeatable agent processes.

Related

  • Project
    MemTensor/memmy-agent

    A personal memory infrastructure that allows different AI agents to share a unified, structured memory of user preferences and project history.

  • Project
    BAI-LAB/MemoryOS

    MemoryOS is a memory management system for AI agents that uses a hierarchical storage architecture to maintain short, mid, and long-term personalized memory for more coherent interactions.

  • Project
    Intuition-Lab/personal-model

    A local-first long-term memory runtime for macOS that creates an evidence-linked personal model of a user's work patterns and goals to provide grounded context for AI coding agents via MCP.

  • Project
    Fergana-Labs/stash

    A persistent knowledge base and shared memory layer for AI agents that connects to various data sources and records session transcripts to maintain context across runs.

  • Project
    aayoawoyemi/Ori-Mnemos

    An open-source persistent memory infrastructure for AI agents that uses a local knowledge graph of markdown files to implement cognitive-inspired retrieval and learning.