setup

Provisions a GBrain database and injects AGENTS.md for initial setup.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Set up GBrain from scratch by provisioning the database, injecting AGENTS.md, and performing the initial import and health checks.

Core Features & Use Cases

  • Auto-provision Supabase or Postgres with pgvector to host a ready-to-use brain.
  • Inject brain-first lookup via AGENTS.md and initiate the first import, including health checks and patching workflow.
  • Phase-based setup with guided prerequisites, migrations, auto-update checks, and live sync configuration.

Quick Start

Run gbrain init --non-interactive --url '<connection_string>' to provision a new brain and start the first import.

Frequently Asked Questions about setup

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

FAQPage Schema
How do I auto-provision a Supabase or Postgres database for GBrain?

You can provision a Supabase or Postgres database for GBrain by running gbrain init --non-interactive --url '<connection_string>' to auto-configure pgvector and start the first import.

What prerequisites are needed to set up a GBrain brain?

Setting up a GBrain brain requires a working Postgres database with pgvector installed, a git-backed Markdown brain, and an OpenAI API key to generate embeddings.

How does AGENTS.md injection work during GBrain setup?

During setup, AGENTS.md is automatically injected to enable brain-first lookup, ensuring agents query the configured Markdown brain before performing other actions.

Can I use Supabase instead of a local Postgres database to host my brain?

Yes, GBrain setup supports onboarding new deployments across both Supabase and local Postgres backends, as long as pgvector is enabled for embedding storage.

What does the initial GBrain import and health check process involve?

The initial import processes your git-backed Markdown brain, generates embeddings using your OpenAI API key, and runs health checks to verify database connectivity and configuration.

Why do I need pgvector enabled to bootstrap a GBrain brain?

Pgvector is required because GBrain stores generated text embeddings from your OpenAI API key directly in your Postgres or Supabase database to perform similarity searches.