Public repository for Agent Skills

An automated Attack-with-Defense platform where LLM-powered agents compete in real-time.

[!NEW!] OpenClaw Plugin for Agents to Become Clever and Token-Efficient!

Learn about a type of vulnerability that specifically targets machine learning models

[ACL 2026] PIArena: A Platform for Prompt Injection Evaluation

Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1

Agent Base is a source-level research project on coding agents. It compares Codex CLI, OpenCode, Gemini CLI, Kimi CLI, and SWE-agent across agent loops, tools, MCP integration, context/memory handl…

An agentic skills framework & software development methodology that works.

A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows

A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.

🌟 Open Source AI Agent Security Infrastructure — intercepts and blocks dangerous agent behaviors before they happen. Just one command! Join us to build safer Human-AI Symbiosis!

Zotero MCP: Connects your Zotero research library with Claude and other AI assistants via the Model Context Protocol to discuss papers, get summaries, analyze citations, and more.

🚀 A curated list of awesome resources focusing on Context Compression techniques for Large Language Models(LLMs).

Edit Banana: A framework for converting statistical formats into editable.

Automatically crawl arXiv papers daily and summarize them using AI. Illustrating them using GitHub Pages.

ArXiv 每日论文推送助手 自动抓取 ArXiv 最新 AI 论文，使用 DeepSeek 进行深度分析，并推送到飞书。

Elevate your AI research writing, no more tedious polishing ✨

Official PyTorch implementation of the paper "Dataset Distillation via the Wasserstein Metric" (ICCV 2025).

Repair malformed JSON from LLMs, APIs, logs, and user input in Python.

[USENIX Security 25] PatchAgent is a LLM-based practical program repair agent that mimics human expertise.

DoomArena is a Framework for Testing AI Agents Against Evolving Security Threats

Benchmark for LLM-based software engineering's ability evaluation on CVE repair.

MacOS Demo for Claude Computer Use

This is the repo for the paper "OS Agents: A Survey on MLLM-based Agents for Computer, Phone and Browser Use" (ACL 2025 Oral).

B站视频评论爬虫 Bilibili完整爬取评论数据，包括一级评论、二级评论、昵称、用户ID、发布时间、点赞数

Awesome-Jailbreak-on-LLMs is a collection of state-of-the-art, novel, exciting jailbreak methods on LLMs. It contains papers, codes, datasets, evaluations, and analyses.

A curated list of awesome synthetic data tools (open source and commercial).