Aim – AI-assisted verifiable SQL migration generator

Name: Aim – AI-assisted verifiable SQL migration generator
Availability: InStock
Author: alecthomas

by alecthomas·Apr 1, 2026·2 points·0 comments

Visit Project View on HN

AI Analysis

●●●BangerBig BrainSolve My ProblemShip It

Verifies AI-generated migrations against real ephemeral databases before writing them to disk.

Strengths

•Ephemeral database verification loop catches hallucinations before they hit production.
•Supports multiple engines like PostgreSQL and MySQL via Docker automatically.
•Normalizes DDL snapshots to ensure accurate schema comparison regardless of formatting.

Weaknesses

•Author admits it is fresh and not yet battle-tested for production.
•Requires Docker running locally for non-SQLite engines, adding setup overhead.

Post Description

This is pretty fresh and definitely not battle tested, but seems to work pretty well in my local testing. Do NOT just blindly apply the output of this to a production database :)

From the README:

AIM creates two ephemeral databases: one by loading schema.sql (the desired state), and one by replaying all existing migrations (the current state). It dumps a stable, normalized DDL representation from each.

An LLM reads both schemas and produces UP and DOWN SQL migration statements.

AIM applies the generated UP migration to a fresh ephemeral database and checks that the result exactly matches schema.sql. It then applies DOWN and checks that the original state is restored. If either check fails, AIM feeds the diff back to the LLM and retries.