Starred repositories
🤖 The analysis of Claude Code
Deep dive into Claude Code internals — architecture, agent loop, context engineering, and more. / 深入解析 Claude Code 源码：架构、Agent 循环、上下文工程、工具系统等
SecCodeBench is a benchmark suite focusing on evaluating the security of code generated by large language models (LLMs).
Internal Safety Collapse: Turning the LLM or an AI Agent into a sensitive data generator.
Clawdbot/Moltbot/OpenClaw One-click RCE PoC 🦞 (CVE-2026-25253)
LuaN1aoAgent is a cognitive-driven AI hacker. It is a fully autonomous AI penetration testing agent powered by DeepSeek V3.2. Using dual-graph reasoning, LuaN1ao achieves a success rate of over 90%…
Fully autonomous AI Agents system capable of performing complex penetration testing tasks
A collaborative, multi-platform, red teaming framework
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
A tool for automatic patch shellcode into binary file to bypass AV. / 一个自动patch shellcode到二进制文件的工具
Claude Code skill implementing Manus-style persistent markdown planning — the workflow pattern behind the $2B acquisition.
The next-generation AI Agent framework driven by Intent Engineering. Move beyond turn-based Function Calling to embrace code-level intent expression and embedded execution. An AI-Native, Intent-Ori…
Shannon Lite is an autonomous, white-box AI pentester for web applications and APIs. It analyzes your source code, identifies attack vectors, and executes real exploits to prove vulnerabilities bef…
A Tool to Visualize Claude Code's LLM Interactions
Framework for building reliable LLM agents with structured specs, operator-level verification, and progressive solidification.
antix's baby intent runtime and meta-tooling design.
Open-source AI hackers to find and fix your app’s vulnerabilities.
Agentic-RAG explores advanced Retrieval-Augmented Generation systems enhanced with AI LLM agents.
⚡A CLI tool for code structural search, lint and rewriting. Written in Rust
Kode Agent — Design for post-human workflows. One unit agent for every human & computer task.
💫 Toolkit to help you get started with Spec-Driven Development
HexStrike AI MCP Agents is an advanced MCP server that lets AI agents (Claude, GPT, Copilot, etc.) autonomously run 150+ cybersecurity tools for automated pentesting, vulnerability discovery, bug b…
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…
Tablestore for Agent Memory