pymc-labs/alchemize

LLM-based, self-correcting transpiler. Supports JAX, PyTorch, Rust, PyMC, Stan.

36
/ 100
Emerging

This project helps you optimize your computational models, such as probabilistic programs or deep learning networks, for speed and efficiency. You provide a model written in languages like PyMC, Stan, JAX, or PyTorch, and it outputs a numerically validated, optimized version in Rust, or translates it between PyMC, Stan, JAX, and PyTorch. Scientists, statisticians, or machine learning engineers who need faster model execution or want to port models between different frameworks would use this.

Use this if you need to significantly speed up your existing computational models or port them between different programming frameworks while ensuring numerical accuracy.

Not ideal if you are working with very simple models that don't require performance optimization or if you prefer manual code translation for full control.

computational-modeling statistical-inference machine-learning-engineering performance-optimization scientific-computing
No Package No Dependents
Maintenance 13 / 25
Adoption 5 / 25
Maturity 11 / 25
Community 7 / 25

How are scores calculated?

Stars

10

Forks

1

Language

Rust

License

Apache-2.0

Category

coding-agent

Last pushed

Apr 01, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/pymc-labs/alchemize"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.