Hey HN! After spending way too many nights debugging flaky AI tests, I built SteadyText. It's a simple python library for deterministic llm generations and embeddings.

We use it in production for:

  - Testing our AI features (zero flakes in 3 months)
  - CLI tools that need consistent outputs
  - Reproducible documentation examples

It's not for creative tasks - this is specifically for when you need AI to be boring and predictable. Think of it as the opposite of ChatGPT. The coolest part? It includes a Postgres extension. You can now do:

  SELECT steadytext_generate('explain this query: ...');

And it will always return the same explanation. :)

How it works:

  1. Greedy decoding- Always pick the highest probability token (no randomness)
  2. 8-bit quantization- Same numerics across all platforms

It's easy to get started:

  uv tool install steadytext
  echo Hello | st