AIDE: AI-Driven Exploration in the Space of Code. The machine Learning engineering agent that automates AI R&D.
-
Updated
Feb 12, 2026 - Python
AIDE: AI-Driven Exploration in the Space of Code. The machine Learning engineering agent that automates AI R&D.
A code generator for array-based code on CPUs and GPUs
SuperSonic, a new open-source framework to allow compiler developers to integrate RL into compilers easily, regardless of their RL expertise.
AlgoTune is a NeurIPS 2025 benchmark made up of 154 math, physics, and computer science problems. The goal is write code that solves each problem, and is faster than existing implementations.
A Knowledge-grounded framework for Autonomous ML/AI Program Synthesis and Optimization
Production-Grade Autoresearch. Ideal for GPU kernels, ML model development, feature engineering, prompt engineering, and other optimizable code.
AI code generation and improvement
The Intelligent Code Refactoring Transformer for Python
A practical showcase of AI-assisted coding using PStruc and ChatGPT, highlighting iterative development and project optimization across three versions with detailed documentation of changes.
A compiler for a simple language
Compiler Design Experiments
This is a pure compiler based language developed using Python.
CodeOpt: A framework for optimizing code performance using Two-Stage Sampling, Few-Shot Learning, and Iterative Self-Reflection with support for Genetic Algorithm Inspired Chain-of-Thought (GA-COT).
A Python-based toy compiler built from scratch, featuring a recursive-descent parser, AST, IR, and ARMv6 code generation with optimizations.
The AI Developer's Assistant aims to enhance developer productivity by analyzing code snippets, identifying bugs, suggesting optimizations, generating unit tests, and debugging log files.
A FastAPI-based web tool for comprehensive performance analysis and endpoint testing of code, featuring execution time tracking, memory usage, and detailed profiling.
Field-theoretic dual track python subset. Curvature, phase, and domain-driven optimization. Deterministic and interpretable.
Boost Python's performance using Cython – a bridge between Python's simplicity and C's efficiency. Explore and learn how Cython accelerates code execution.
ASC Homework 1-3
Add a description, image, and links to the code-optimization topic page so that developers can more easily learn about it.
To associate your repository with the code-optimization topic, visit your repo's landing page and select "manage topics."