Official codebase for "SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution"

MLGym A New Framework and Benchmark for Advancing AI Research Agents

A high-performance algorithmic trading platform and event-driven backtester

📦 Repomix (formerly Repopack) is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for when you need to feed your codebase to Large Language Models (LLMs) o…

This repo contains the dataset and code for the paper "SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?"

SWE-bench [Multimodal]: Can Language Models Resolve Real-world Github Issues?

[FSE-2024] Towards AI-Assisted Synthesis of Verified Dafny Methods

Clean, minimal, accessible reproduction of DeepSeek R1-Zero

A new version of Soot with a completely overhauled architecture

A GitHub app to automatically review Python code style over Pull Requests

Pythoness: use natural language to define Python functions.

Catalog Of Math Problems Formalized In Lean

A holistic framework to enable the design, development, and evaluation of autonomous AIOps agents.

Limbo is a project to build the modern evolution of SQLite.

Easy flamegraphs for Rust projects and everything else, without Perl or pipes <3

The official repo of Doop, the declarative pointer analysis framework.

Zopfli Translated Code

A Rust compiler front-end for IDEs

Real-time monitor and web admin for Celery distributed task queue

Cross-platform Rust rewrite of the GNU coreutils

(forkable) universal json ingester

Creusot helps you prove your code is correct in an automated fashion.

Commit0: Library Generation from Scratch

A constant throughput, correct latency recording variant of wrk

Modern HTTP benchmarking tool

Interface with the rustc compiler for the purpose of program verification