olivkoch/nano-trm

An implementation of Tiny Recursive Models (TRM)

50
/ 100
Established

This project offers a streamlined way for AI researchers and machine learning engineers to experiment with Tiny Recursive Models (TRM). It provides a clean codebase to train and test these models on tasks like Sudoku and maze-solving, taking raw problem data and producing a trained model and performance metrics. It's designed for those who want to quickly set up and run TRM experiments without dealing with complex legacy code.

101 stars.

Use this if you are an AI researcher or machine learning engineer looking to rapidly prototype, train, and evaluate Tiny Recursive Models for problem-solving tasks.

Not ideal if you are a non-technical end-user looking for a ready-to-use application, as this project requires programming knowledge to operate.

AI-research machine-learning-engineering recursive-models problem-solving-AI model-training
No Package No Dependents
Maintenance 10 / 25
Adoption 9 / 25
Maturity 15 / 25
Community 16 / 25

How are scores calculated?

Stars

101

Forks

16

Language

Python

License

MIT

Last pushed

Feb 16, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/olivkoch/nano-trm"

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