Getting Started

This guide walks you through deploying Resonant Mind to Cloudflare Workers. You’ll have a working cognitive MCP server connected to Claude in under 10 minutes.

Prerequisites

• A Cloudflare account (free tier works)
• Node.js 18+ installed
• A Google AI Studio API key (free — for Gemini embeddings)

1. Clone and Install

git clone https://github.com/codependentai/resonant-mind.git
cd resonant-mind
npm install

2. Choose Your Storage Backend

Resonant Mind supports two storage options:

	D1 (Simpler)	Neon Postgres (Production)
What	Cloudflare’s built-in SQLite	Serverless Postgres with pgvector
Best for	Getting started, smaller deployments	Production, larger datasets
Vector search	Cloudflare Vectorize	pgvector (built into Neon)
Cost	Free tier available	Free tier available
Setup	Easier (all Cloudflare)	Moderate (Cloudflare + Neon)

D1 Setup (Recommended for Getting Started)

# Create the database
npx wrangler d1 create resonant-mind

# Create the vector index (for semantic search)
npx wrangler vectorize create resonant-mind-vectors --dimensions=768 --metric=cosine

# Create R2 bucket (for image storage)
npx wrangler r2 bucket create resonant-mind-images

Add the D1 and Vectorize bindings to wrangler.toml:

[[d1_databases]]
binding = "DB"
database_name = "resonant-mind"
database_id = "paste-your-database-id-here"

[[vectorize]]
binding = "VECTORS"
index_name = "resonant-mind-vectors"

Run the migration:

npx wrangler d1 migrations apply resonant-mind --remote

For Postgres setup, see the Deployment page.

3. Set Your Secrets

# Required: API key for authentication (pick any strong random string)
npx wrangler secret put MIND_API_KEY

# Required: Google Gemini key for embeddings (free at aistudio.google.com)
npx wrangler secret put GEMINI_API_KEY

4. Deploy

npx wrangler deploy

Verify it’s working:

curl https://resonant-mind.your-subdomain.workers.dev/health
# Returns: {"status":"ok","service":"resonant-mind"}

5. Connect to Claude

Claude Code (CLI)

Add to .mcp.json in your project root:

{
  "mcpServers": {
    "mind": {
      "type": "url",
      "url": "https://resonant-mind.your-subdomain.workers.dev/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_MIND_API_KEY"
      }
    }
  }
}

Claude.ai (Web & Mobile)

For Claude.ai’s MCP connector, use a secret URL path:

npx wrangler secret put MCP_CONNECTOR_SECRET

In Claude.ai, add an MCP integration with:

https://resonant-mind.your-subdomain.workers.dev/mcp/YOUR_CONNECTOR_SECRET

Other MCP Clients

Any client supporting HTTP MCP transport works. The endpoint is /mcp with Bearer token authentication.

6. Test It

Once connected, try these in Claude:

"Use mind_orient to wake up"
"Write an entity called 'My Project' with observations about what it does"
"Search my memories for anything about projects"
"How's the mind health looking?"

The mind_orient → mind_ground sequence is the recommended way to start each session. It loads identity context, recent activity, and active threads — grounding the AI in who it is and what’s happening.