Stars
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
verl: Volcano Engine Reinforcement Learning for LLMs
Tips and resources to prepare for Behavioral interviews.
RepoMaster: The open-source AI agent that masters GitHub. It turns any code repository into a powerful tool, achieving a new level of autonomous task-solving. An open alternative to Claude-Code.
Coding problems used in aider's polyglot benchmark
Qwen3-Coder is the code version of Qwen3, the large language model series developed by Qwen team.
[EMNLP'25] AutoSDT is a fully automatic pipeline to collect data-driven scientific coding tasks to train co-scientist models.
A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discovery (EMNLP'24)
AIDE: AI-Driven Exploration in the Space of Code. The machine Learning engineering agent that automates AI R&D.
Lightweight coding agent that runs in your terminal
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
🤗 smolagents: a barebones library for agents that think in code.
An Illusion of Progress? Assessing the Current State of Web Agents
SGLang is a high-performance serving framework for large language models and multimodal models.
A bibliography and survey of the papers surrounding o1
[ICLR'25] ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery
A curated list of papers on LLMs and agents for scientific research and development
[CVPR 2025] Boosting Generative Novel View Synthesis with Sparse and Unposed Images
Let your Claude able to think
SWE-bench: Can Language Models Resolve Real-world Github Issues?
Astro template to help you build an interactive project page for your research paper
DAMO-ConvAI: The official repository which contains the codebase for Alibaba DAMO Conversational AI.
We release a general framework for prompting LLMs to manipulate software in a closed-loop manner.