rahilp/second-brain-cloudflare

One memory layer, every AI tool. Store anything once — recall it in Claude, ChatGPT, Cursor, or any MCP client. Self-hosted on Cloudflare's free tier.

What it solves

Many AI tools (like Claude, ChatGPT, and Cursor) have isolated memories. Users often find themselves repeating the same project context, preferences, and decisions to different AI assistants. Second Brain provides a single, persistent, and user-controlled memory layer that can be shared across all these different AI platforms.

How it works

The project runs as a Cloudflare Worker in the user's own account, ensuring the data remains under their control. It uses a vector-based approach to retrieve memories by meaning (semantic search) rather than just exact keywords.

It integrates with various sources to capture information automatically:

  • AI Clients: Connects via the Model Context Protocol (MCP) to tools like Claude and ChatGPT.
  • External Apps: Syncs with Notion, Google/Outlook/iCloud calendars, and Gmail/iCloud email.
  • Local Tools: Includes a CLI, a browser extension, an Obsidian plugin, and iOS shortcuts.

Who it’s for

Users who use multiple AI assistants and want a unified knowledge base that follows them across different tools, as well as people who prefer to self-host their memory data on their own cloud infrastructure (Cloudflare).

Highlights

  • Cross-Platform Memory: One shared memory for Claude, ChatGPT, Cursor, and other MCP-compatible tools.
  • Semantic Recall: Retrieves information based on meaning, allowing for natural language queries.
  • Broad Integration Ecosystem: Automatic syncing with Notion, Email, and Calendars.
  • User-Owned Data: Deployed to the user's own Cloudflare account to avoid platform lock-in.
  • Visual Memory Graph: A dashboard that allows users to explore how memories cluster and connect visually.
  • Automated Insights: Weekly analysis that identifies changes or conflicts between memories written at different times.

Related

  • Project
    AVIDS2/memorix

    A local-first shared memory layer for AI coding agents that persists project context, design decisions, and Git history across different sessions and tools.

  • Project
    NateBJones-Projects/OB1

    An infrastructure layer that provides a unified, persistent memory database with vector search, allowing multiple AI tools and agents to share a single, consistent context of the user.

  • 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
    itechmeat/open-second-brain

    An Obsidian-native memory layer for AI agents that stores knowledge as plain Markdown files, allowing users to own and transparently manage their agent's long-term memory.

  • Project
    GeminiLight/MindOS

    A local-first knowledge base that provides a shared memory and durable context for humans and multiple AI agents via MCP and Skills.