Lists (4)
Starred repositories
Implements harmful/harmless refusal removal using pure HF Transformers
Universal and Transferable Attacks on Aligned Language Models
𝐍𝐈𝐖 𝐀𝐩𝐩𝐫𝐨𝐯𝐚𝐥 𝐢𝐧 𝐎𝐧𝐞 𝐖𝐞𝐞𝐤 [Latex Template]
ResearchStudio: Our AI co-author, from research problem to final publication.
Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
BLUE: Toward Better Language Use in Efficient Vision-Language-Action Models for Autonomous Driving
Open-source autoresearch powered by autonomous coding agents. Run Claude Code, OpenCode, and Codex with grading, shared knowledge, and multi-agent evolution. Accepted at COLM 2026.
Official AHE code — Agentic Harness Engineering: observability-driven automatic evolution of coding-agent harnesses (concurrent w/ meta-harness). NexAU-AHE reaches 84.7% ± 2.1 pass@1 on Terminal-Be…
My Python scripts to make high-quality figures for publications in top AI conferences and journals.
Claude code environment for laywers
arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv
Minimal AI coding agent (~1,000 lines of Python) inspired by Claude Code. Works with any LLM. Think NanoGPT for coding agents. Formerly NanoCoder.
claude-code full original source code from source maps
[ICML'26] AgentWebBench: Benchmarking Multi-Agent Coordination in Agentic Web
ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works…
Use this skill to enable Claude Code to communicate directly with your Google NotebookLM notebooks. Query your uploaded documents and get source-grounded, citation-backed answers from Gemini. Featu…
A general purpose scientific writer
The batteries-included agent harness.
Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent with full horsepowe…
Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 175,000+ scientists worldwide. 163 ready-to-use validated skills plus 100+ scientific databases covering bio…
Build your agent from 200,000+ skills via skill RETRIEVAL & ORCHESTRATION
A community collection of OpenClaw use cases for making life easier.
An efficient reasoning method that searches the optimal reasoning path to enhance LLMs.
[CVPR 2026🔥] 🧑🎨 OmniLottie, an open-sourced multi-modal instructed vector animation generator that produces Lottie JSONs.
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)
An Open-source RL System from ByteDance Seed and Tsinghua AIR
Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning