MemoryIQ
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MemoryIQsearch my brain for project updates"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MemoryIQ
One Brain. Every AI.
AI-powered shared memory platform. Capture thoughts from anywhere, search by meaning, share knowledge across all your AI tools.
Key Features
Semantic Search — vector-powered search using pgvector
Shared Brains — collaborative knowledge bases with member roles
MCP Protocol — connect any MCP-compatible AI tool
Smart Curation — AI detects conflicts and flags stale knowledge
Multi-Source Capture — web UI, API, MCP
Auto-Metadata — AI classifies, tags, and links thoughts
Related MCP server: Cairn
Tech Stack
Framework: Next.js 16 (App Router)
Language: TypeScript
Auth: Clerk
Database: Neon Postgres + pgvector
ORM: Drizzle
AI: OpenRouter + OpenAI (fallback)
MCP: @modelcontextprotocol/sdk
Styling: Tailwind CSS + shadcn/ui
Local Development
git clone <repo-url>
cd memoryiq
cp .env.example .env.local # Fill in your keys
npm install
npx drizzle-kit migrate
npm run devEnvironment Variables
Variable | Description |
NEXT_PUBLIC_CLERK_PUBLISHABLE_KEY | Clerk publishable key |
CLERK_SECRET_KEY | Clerk secret key |
CLERK_WEBHOOK_SECRET | Clerk webhook signing secret |
DATABASE_URL | Neon pooled connection string |
DATABASE_URL_UNPOOLED | Neon direct connection (for migrations) |
OPENROUTER_API_KEY | OpenRouter API key |
OPENAI_API_KEY | OpenAI API key (fallback) |
NEXT_PUBLIC_APP_URL | App URL (e.g., https://memoryiq.ai) |
MCP Integration
Connect your AI tools using your brain's MCP URL:
Claude Desktop
{
"mcpServers": {
"memoryiq": {
"url": "https://your-app.vercel.app/api/mcp?key=YOUR_BRAIN_KEY",
"transport": "http"
}
}
}Cursor
{
"mcpServers": {
"memoryiq": {
"url": "https://your-app.vercel.app/api/mcp?key=YOUR_BRAIN_KEY"
}
}
}VS Code Copilot
{
"github.copilot.chat.mcpServers": {
"memoryiq": {
"url": "https://your-app.vercel.app/api/mcp?key=YOUR_BRAIN_KEY"
}
}
}Find your brain key in Dashboard → Brains → [Brain] → MCP Connection.
Deployment
Recommended: Vercel + Neon
Push to GitHub
Import project in Vercel
Add environment variables
Deploy
Database Migrations
npx drizzle-kit generate # Generate new migration
npx drizzle-kit migrate # Run migrationsThis server cannot be deployed
Maintenance
Related MCP Connectors
Your memory, everywhere AI goes. Build knowledge once, access it via MCP anywhere.
Cross-vendor AI memory over MCP. One semantic store, readable and writeable from every MCP client.
Shared, governed long-term memory for AI agents across tools and sessions via MCP and REST.
One memory, every AI. A shared, user-owned markdown memory your AI clients read and write over MCP.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to persistently store and semantically search shared knowledge via MCP tools.2MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI tools to query a user's private, locally stored memories (notes, documents) with source citations, using the MCP protocol.5 npmMIT
- AlicenseNot gradedqualityAmaintenanceEnables semantic search and retrieval of archived AI conversations from multiple providers via the MCP protocol, allowing thread continuation and integration with MCP-capable tools.10MIT
- AlicenseNot gradedqualityBmaintenanceEnables personal cross-tool memory by exposing a searchable episodic archive of AI sessions and a curated, high-trust semantic facts layer through MCP tools and resources.MIT