Tidemind

What is Tidemind?

Tidemind is a living second brain that connects AI agents, notes, and other tools into a single knowledge graph. It provides a memory layer spanning all your tools via the MCP protocol, building a profile from all your data and delivering it to AI at the start of every conversation.

How to use Tidemind?

Download the desktop app or build from source (Node.js >= 18 required). Connect AI tools via MCP configuration (one-click in Settings or manual); import notes from Logseq, Obsidian, or Apple Notes. The MCP server exposes three tools: brain_prepare, brain_recall, and brain_digest.

Key features of Tidemind

• All memory in a single knowledge graph.
• Profile built from all data delivered to AI at conversation start.
• Graph-based recall that follows links between memories.
• Background metabolism that reinforces, crystallizes, and forgets memories.
• Local SQLite storage, exportable to Markdown anytime.
• Integrates with multiple AI tools and note systems.

Use cases of Tidemind

• Context-aware AI conversations across different tools (Claude, Cursor, Windsurf, etc.).
• Connecting notes from Obsidian, Logseq, and Apple Notes with AI interactions.
• Discovering hidden connections between past decisions and current problems.
• Building a personal knowledge graph that evolves and surfaces new insights over time.

FAQ from Tidemind

How is Tidemind different from Obsidian / Notion / Mem?

Tidemind is not a note-taking app—it is a memory layer that sits between your tools. It ingests notes from Obsidian, Logseq, and Apple Notes, plus conversations from AI tools, and weaves them into a single living knowledge graph. You keep using whatever tools you prefer; Tidemind connects them behind the scenes.

I already have a note system. Why do I need Tidemind?

Your notes are only one slice of your thinking. Tidemind captures all slices—AI conversations, decisions made in passing, preferences expressed across tools—and builds connections you wouldn’t make manually. It delivers this context to your AI automatically, so every conversation starts with full awareness of who you are.

Where is my data stored? Is it secure?

All data lives in a single SQLite file on your machine, exportable to Markdown anytime. No cloud, no vendor lock-in. You can go fully local with Ollama for privacy, use cloud models for quality, or mix both.

What are the runtime requirements?

Node.js >= 18 is the only hard requirement. Optional: an LLM provider (Anthropic, Vertex AI, or Gemini) for advanced features, and an embedding provider (Ollama, Vertex AI, or Gemini) for semantic search.

What MCP tools does Tidemind expose?

Three tools: brain_prepare (load memory context at conversation start), brain_recall (navigate and retrieve memories, optionally following links), and brain_digest (store new information, decomposing