Open Brain
Open Brain — The infrastructure layer for your thinking. One database, one AI gateway, one chat channel — any AI plugs in. No middleware, no SaaS.
What is Open Brain?
Open Brain is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to open brain — the infrastructure layer for your thinking. one database, one ai gateway, one chat channel — any ai plugs in. no middleware, no saas.
Open Brain — The infrastructure layer for your thinking. One database, one AI gateway, one chat channel — any AI plugs in. No middleware, no SaaS.
This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Open Brain — The infrastructure layer for your thinking. One
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx ob1Configuration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Open Brain
Open Brain (OB1) is a local-first infrastructure layer that gives all your AI tools a single shared persistent memory through one PostgreSQL database with vector search. Rather than each AI client maintaining its own context window, OB1 acts as a unified knowledge base that Claude, ChatGPT, Cursor, and other clients can all read from and write to over a standard MCP connection. It also includes Slack and Discord capture integrations, an AI gateway with OpenRouter API rotation, and edge function deployment — all self-hosted with no SaaS dependency.
Prerequisites
- Node.js 18+ or Bun for running the MCP server
- A Supabase project (self-hosted or cloud) with PostgreSQL and row-level security enabled for the vector database backend
- An OpenRouter API key or direct API keys for the LLM providers you want to use
- Approximately 45 minutes for initial setup following the repository's setup guide
- An MCP-compatible client such as Claude Desktop, Claude Code, Cursor, or ChatGPT
Clone the OB1 repository
Clone the Open Brain repository which contains the MCP server, database migrations, Slack/Discord capture integrations, and example recipes.
git clone https://github.com/NateBJones-Projects/OB1.git
cd OB1Configure environment variables
Create a .env file from the example and fill in your Supabase connection details and LLM API keys. OB1 uses Supabase for vector storage with row-level security.
cp .env.example .env
# Edit .env and set:
# SUPABASE_URL=https://your-project.supabase.co
# SUPABASE_ANON_KEY=your_supabase_anon_key
# SUPABASE_SERVICE_ROLE_KEY=your_service_role_key
# OPENROUTER_API_KEY=your_openrouter_api_keyRun database migrations
Apply the Supabase migrations to create the knowledge graph tables, vector search indexes, and row-level security policies.
npx supabase db push
# or follow the manual SQL migration steps in docs/setup.mdStart the MCP server
Launch the OB1 MCP server. It will listen for connections from your MCP clients.
npx ob1Add OB1 to your MCP client configuration
Edit your claude_desktop_config.json to point at the OB1 MCP server so Claude can read and write to your shared brain.
{
"mcpServers": {
"ob1": {
"command": "npx",
"args": ["ob1"]
}
}
}Open Brain Examples
Client configuration
Claude Desktop configuration entry for the Open Brain MCP server.
{
"mcpServers": {
"ob1": {
"command": "npx",
"args": ["ob1"]
}
}
}Prompts to try
Use these prompts to store and retrieve knowledge through your Open Brain instance.
- "Remember that our main database is PostgreSQL 16 running on db.internal:5432"
- "What do you know about our infrastructure from previous conversations?"
- "Search my brain for anything related to the onboarding process"
- "Store a note: the Q3 product roadmap focuses on mobile and API v2"
- "What meetings or decisions have been captured from our Slack channel this week?"Troubleshooting Open Brain
Vector search returns no results despite stored memories
Ensure the pgvector extension is enabled in your Supabase project (run CREATE EXTENSION IF NOT EXISTS vector; in the SQL editor) and that the migration that creates the vector indexes has been applied successfully.
Row-level security errors when the MCP server tries to write memories
Use the SUPABASE_SERVICE_ROLE_KEY (not the anon key) when the MCP server needs write access. Confirm the RLS policies in the migrations allow inserts from the service role.
npx ob1 exits immediately with a missing module error
Run npm install in the cloned OB1 directory first, then try npx ob1 again. If the package is not on npm, run the server directly with node dist/index.js after building with npm run build.
Frequently Asked Questions about Open Brain
What is Open Brain?
Open Brain is a Model Context Protocol (MCP) server that open brain — the infrastructure layer for your thinking. one database, one ai gateway, one chat channel — any ai plugs in. no middleware, no saas. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Open Brain?
Follow the installation instructions on the Open Brain GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Open Brain?
Open Brain works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Open Brain free to use?
Yes, Open Brain is open source and available under the NOASSERTION license. You can use it freely in both personal and commercial projects.
Open Brain Alternatives — Similar Knowledge & Memory Servers
Looking for alternatives to Open Brain? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.
MemPalace
★ 52.6kA local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically
Kratos
★ 25.7k🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.
Context Mode
★ 15.4kAn MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm
Memu
★ 13.7kMemory for 24/7 proactive agents like OpenClaw.
MemOS
★ 9.3kMemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u
Everos
★ 5.4kBuild, evaluate, and integrate long-term memory for self-evolving agents.
Browse More Knowledge & Memory MCP Servers
Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Open Brain in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Open Brain?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.