When Agent Becomes the Scientist – Building Closed-Loop System from Hypothesis to Verification

An innovative open-source Code Interpreter with (GPT,Gemini,Claude,LLaMa) models.

AI Coding assistant for large and complex codebases.

Open-Source LLM Coders with Co-Evolving Reinforcement Learning

A set of LLM coding context enhancement solutions.

AlgoTune is a benchmark made up of 155 math, physics, and computer science problems. The goal is write code that solves each problem, and is faster than existing implementations.

Automated LLM Coding Tournaments. There can be only one (winning code solution from the competing AIs)

LLM-driven software development helper.

LLM prompts to generate Fortran code

Python script that uses LLMs on Groq to create Fortran programs, iterating with compiler error messages until they compile and run without error

Python script that uses LLMs on Groq to create C++ programs, iterating with compiler error messages until they compile

Python script that uses OpenAI LLMs to create Fortran programs, iterating with compiler error messages until they compile

Python script that uses LLMs on Groq to create Python programs, iterating until they run to completion