longxudou
Follow
Stars
🚀 JIT Implementation: Code That Writes Itself
The Official Dropbox API V2 SDK for Python
Playwright is a framework for Web Testing and Automation. It allows testing Chromium, Firefox and WebKit with a single API.
Public Goods Game (PGG) Benchmark: Contribute & Punish is a multi-agent benchmark that tests cooperative and self-interested strategies among Large Language Models (LLMs) in a resource-sharing econ…
Make websites accessible for AI agents
Python tool for converting files and office documents to Markdown.
Multilingual WildBench for south-east Asian languages.
[ICLR 2025] Autoregressive Video Generation without Vector Quantization
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…
Dolomite Engine is a library for pretraining/finetuning LLMs
Computer gaming agents that run on your PC and laptops.
Training Large Language Model to Reason in a Continuous Latent Space
Letta (formerly MemGPT) is the stateful agents framework with memory, reasoning, and context management.
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?
AnchorAttention: Improved attention for LLMs long-context training
A GPU-accelerated cross-platform terminal emulator and multiplexer written by @wez and implemented in Rust
Official code for the paper Improving Language Plasticity via Pretraining with Active Forgetting, NeurIPS 2023
A simple, performant and scalable Jax LLM!
Re-implementation of pi0 vision-language-action (VLA) model from Physical Intelligence
Implementation of π₀, the robotic foundation model architecture proposed by Physical Intelligence
[ICLR 2025] LAPA: Latent Action Pretraining from Videos
Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, using the browser, and more with your permission every step of the way.
An agent benchmark with tasks in a simulated software company.
An amazing UI for OpenAI's ChatGPT (Website + Windows + MacOS + Linux)
StarCraft II Client - protocol definitions used to communicate with StarCraft II.