---
id: "action-build-postgres-db"
type: "action-item"
source_timestamps: ["00:13:00", "00:15:44"]
tags: ["infrastructure", "setup"]
related: ["entity-postgresql", "entity-pgvector", "entity-supabase"]
action: "Deploy a PostgreSQL database with pgvector enabled to store vector embeddings."
outcome: "A secure, user-owned database capable of semantic search."
speakers: ["Nate B. Jones"]
sources: ["s22-saas-replacement"]
sourceVaultSlug: "s22-saas-replacement"
originDay: 22
---
# Set up a PostgreSQL database with pgvector

## Action

Deploy a personal [[entity-postgresql]] database (e.g. via [[entity-supabase-d22]]) and enable the [[entity-pgvector]] extension.

## Why

This is the foundational, user-owned storage layer of the [[concept-open-brain-d22]]. Without it, every other step of [[framework-open-brain-architecture]] has nowhere to land. With it, the rest of the stack snaps into place.

Because the data lives in standard Postgres, it can be backed up, exported with `pg_dump`, and migrated between hosts. There is no proprietary SaaS layer between you and your own context — directly addressing [[claim-saas-memory-lock-in]].

## Outcome

A secure, user-owned database capable of [[concept-semantic-search]] and ready to be exposed to AI clients via [[action-connect-mcp]].