setup

Set up a GBrain environment with Supabase or Postgres and pgvector.

5|1|Updated Apr 15, 2026
One-click install
npx skills add https://github.com/GYF0311/lorekit --skill setup-gyf0311
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: setup
Source: https://github.com/GYF0311/lorekit/tree/main/brain/skills/setup
Command: npx skills add https://github.com/GYF0311/lorekit --skill setup-gyf0311

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It helps you deploy and verify a working GBrain “brain” end-to-end without getting tripped up on Postgres connectivity, schema setup, sync correctness, or unsafe configuration steps.

Core Features & Use Cases

  • Guided Supabase or Postgres + pgvector provisioning: supports Supabase connection via the correct Session Pooler (and explicitly avoids Supabase anon keys), so the environment is correctly reachable.
  • Automated first import and knowledge graph backfill: imports Markdown repos, proves search works, starts embeddings, and runs link/timeline extraction to make the brain useful immediately.
  • Verified health checks and mandatory live sync: enforces “doctor first” troubleshooting plus a live-sync configuration step and verification so answers don’t silently go stale.

Quick Start

Ask the AI to run the setup flow end-to-end by prompting you for the required Postgres connection string and then verifying it with gbrain doctor.

Frequently Asked Questions about setup

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

FAQPage Schema
How do I set up a Supabase database with pgvector for an agent knowledge base?

To set up a Supabase database with pgvector, you must use the correct Session Pooler connection string, explicitly avoid anon keys, and initialize the schema to establish persistent state for agent configuration.

Why does my Supabase Postgres connection fail when configuring a knowledge base?

Supabase Postgres connection failures often happen when using the Transaction Pooler instead of the Session Pooler, or by incorrectly applying Supabase anon keys, which prevents proper database topology initialization.

What is the best way to verify a Postgres and pgvector environment for live sync?

The best way to verify a Postgres and pgvector environment is to run the mandatory gbrain doctor --json command, which checks topology, ensures live synchronization is active, and prevents silently stale answers.

Can I import Markdown repositories directly into a pgvector database for search?

Yes, you can import Markdown repositories directly into a pgvector database, which automatically starts embeddings, runs link extraction, and backfills the knowledge graph to prove search works immediately.

Does agent configuration require mandatory live synchronization with a self-hosted Postgres database?

Yes, agent configuration requires mandatory live synchronization with a self-hosted Postgres or Supabase database to configure the brain-first lookup protocol and ensure knowledge base answers do not silently go stale.