Grepai Storage Postgres

Switches GrepAI from local GOB files to PostgreSQL with pgvector for vector storage. You want this when multiple people need to share the same codebase index or you're dealing with 10K+ files. Setup is straightforward with Docker for dev or managed services like Supabase for production. The main win is concurrent access without file locking issues, plus you get standard database tooling for backups and monitoring. Includes solid tuning guidance for IVFFlat indexes and SSL configuration. Migration from GOB is destructive (delete and reindex), so plan accordingly.

skills.sh installs: 560
GitHub stars: 20
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add yoanbernabeu/grepai-skills --skill grepai-storage-postgres --agent claude-code

Installs into .claude/skills of the current project.

Files

GrepAI Storage with PostgreSQL

This skill covers using PostgreSQL with the pgvector extension as the storage backend for GrepAI.

When to Use This Skill

Team environments with shared index
Large codebases (10K+ files)
Need concurrent access
Integration with existing PostgreSQL infrastructure

Prerequisites

PostgreSQL 14+ with pgvector extension
Database user with create table permissions
Network access to PostgreSQL server

Advantages

Benefit	Description
👥 Team sharing	Multiple users can access same index
📏 Scalable	Handles large codebases
🔄 Concurrent	Multiple simultaneous searches
💾 Persistent	Data survives machine restarts
🔧 Familiar	Standard database tooling

Setting Up PostgreSQL with pgvector

Option 1: Docker (Recommended for Development)

# Run PostgreSQL with pgvector
docker run -d \
  --name grepai-postgres \
  -e POSTGRES_USER=grepai \
  -e POSTGRES_PASSWORD=grepai \
  -e POSTGRES_DB=grepai \
  -p 5432:5432 \
  pgvector/pgvector:pg16