[NeurIPS '21] Adversarial Attacks on Graph Classification via Bayesian Optimisation (GRABNEL)

Get 10X more out of Claude Code, Codex or any coding agent

Academic Research Skills for Claude Code: research → write → review → revise → finalize

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

Gradient Bang is an online multiplayer universe where you explore, trade, battle, and collaborate with other players and with LLMs

Free educational content on reverse engineering and malware analysis from the FLARE team

Browser Harness | Self-healing harness that enables LLMs to complete any task.

The agent that grows with you

The guidelines on how to request access to MalGuise

A Binary Genetic Traits Lexer Framework

Harness Engineering 学习指南 — 从概念理解到独立实践的深度学习档案

Awesome Large Language Models for Vulnerability Detection

Crawlee—A web scraping and browser automation library for Node.js to build reliable crawlers. In JavaScript and TypeScript. Extract data for AI, LLMs, RAG, or GPTs. Download HTML, PDF, JPG, PNG, an…

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

Security Scanner for Agent Skills

輸入文字或圖片，LLM會找出適合的梗圖來回覆你

The repo is finally unlocked. enjoy the party! The fastest repo in history to surpass 100K stars ⭐. Join Discord: https://discord.gg/5TUQKqFWd Built in Rust using oh-my-codex.

Framework for AI agents to build and maintain an Obsidian wiki using Karpathy's LLM Wiki pattern

Attack and defend active directory using modern post exploitation adversary tradecraft activity

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search

Three LLMs debate to make better decisions than any single model. Inspired by EVA's MAGI supercomputer.

Local knowledge graph for Claude Code. Builds a persistent map of your codebase so Claude reads only what matters — 6.8× fewer tokens on reviews and up to 49× on daily coding tasks.

Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞

A Windows kernel driver viewer and manager built in Rust — real-time enumeration, signature verification, SCM operations, and multi-format exports with a modern dark-themed GUI.

A collective list of free APIs

🔐 AI decoding Trump's posts × stock market | AI 解碼川普推文 × 美股 | AIでトランプ投稿×株式市場を解読 — 31.5M models, 61.3% hit rate, open source

大语言模型(LLM)理论+代码教程，由浅入深，带你系统学习LLM的理论知识并从代码层面理解其如何实现。

BullshitBench measures whether AI models challenge nonsensical prompts instead of confidently answering them, created by Peter Gostev.