setup-gbrain

Install the gbrain CLI, initialize a PGLite or Supabase brain, and register an MCP.

Updated May 11, 2026
One-click install
npx skills add https://github.com/cloudofgeorge/AI-hands --skill setup-gbrain-cloudofgeorge
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: setup-gbrain
Source: https://github.com/cloudofgeorge/AI-hands/tree/main/skills/gstack/setup-gbrain
Command: npx skills add https://github.com/cloudofgeorge/AI-hands --skill setup-gbrain-cloudofgeorge

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Set up gbrain end-to-end by installing the CLI, initializing a local PGLite or Supabase brain, and registering an MCP to enforce per-remote trust policies.

Core Features & Use Cases

  • Install the gbrain CLI and verify environment.
  • Initialize a local PGLite or Supabase brain for memory and state persistence.
  • Register an MCP and capture per-remote trust policy for secure, multi-machine workflows.
  • Support Path 4 remote MCP setups.

Quick Start

Run the setup-gbrain workflow to install the CLI, initialize a brain, and register your MCP for this machine.

Frequently Asked Questions about setup-gbrain

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I set up local AI memory for my agent using gbrain?

You need the gstack CLI installed on your machine to run the gbrain setup workflow. The process automates gbrain CLI installation, brain initialization, and MCP registration for local state storage.

How do I configure per-remote trust policies for a local AI memory MCP?

Configuring per-remote trust policies is handled during MCP registration in the setup workflow. This enforces secure, multi-machine workflows by capturing trust policies for trusted remotes and centralized artifact syncing.

Can I use Supabase instead of PGLite for local AI brain initialization?

Yes, you can initialize either a local PGLite or a Supabase brain for memory and state persistence. The setup workflow supports both backends depending on your project's persistence requirements.

Does gbrain setup support remote MCP connections for multi-machine workflows?

Yes, gbrain setup supports Path 4 remote MCP setups to enable multi-machine workflows. This allows agents to access persistent context and centralized artifact syncing across trusted remote connections.

Why does my agent need persistent context and centralized artifact syncing?

Persistent context and centralized artifact syncing are needed when an agent operates across ongoing projects or new machine setups. gbrain provides this by initializing a local brain and registering an MCP to store local state.