A security-focused library OS supporting kernel- and user-mode executionLiteBox A security-focused library OS NoteThis project is currently actively evolving and improving. While we are working toward a stable release, some APIs and interfaces may change as the design continues to mature. You are welcome to explore and experiment, but if you need long-term stability, it may be best to wait for a stable release, or be prepared to adapt to updates along the way. LiteBox is a sandboxing library…
Fully autonomous AI hacker to find actual exploits in your web apps. Shannon has achieved a 96.15% success rate on the hint-free, source-aware XBOW Benchmark.NoteShannon Lite achieves a 96.15% success rate on a hint-free, source-aware XBOW benchmark. → Shannon is your fully autonomous AI pentester. Shannon’s job is simple: break your web app before anyone else does. The Red Team to your vibe-coding Blue team. Every Claude (coder) deserves their Shannon. Website • Discord 🎯 What is Shann…
Visualize, collaborate, and evolve the software architecture with always actual and live diagrams from your codeArchitecture as a code Visualize, collaborate on, and evolve your software architecture with always up-to-date, live diagrams generated from your code. docs - playground - demo What is LikeC4? Why "like"? LikeC4 is a modeling language for describing software architecture and tools to generate diagrams from the model. LikeC4 is inspired by C4 Model and Structurizr DSL, b…
Simple Rust VPN Client / ServerANet: Сеть Друзей ANet — это инструмент для организации приватного, защищенного информационного пространства между близкими людьми. Мы строим цифровые мосты там, где обычные пути недоступны. Это не сервис. Это технология для связи тех, кто доверяет друг другу. Особенности В основе проекта лежит собственный транспортный протокол ASTP (ANet Secure Transport Protocol), разработанный с фокусом на: Приватность: Полное сквозное шифрование (ChaCha20Poly1305 / X25519)…
the easiest way to run natural language-described workflows automatically Natural language Agent, 24/7 in cloud sandbox Documentation / Website / Discord VM0 runs natural language-described workflows automatically on schedule in remote sandbox environments. ⭐ Star us on GitHub, it motivates us a lot! ⭐ 🔥 What you GET Cloud sandbox, run Claude Code in isolated claude sandbox 24/7 Skill Native, Compatible with 35,738+ skills in skills.sh, and 70+…
Project management system for Claude Code using GitHub Issues and Git worktrees for parallel agent execution.Claude Code PM Claude Code workflow to ship faster better using spec-driven development, GitHub issues, Git worktrees, and multiple AI agents running in parallel. 中文文档 (Chinese Documentation) Stop losing context. Stop blocking on tasks. Stop shipping bugs. This battle-tested system turns PRDs into epics, epics into GitHub issues, and issues into production code – with fu…
Skills Catalog for CodexAgent Skills Agent Skills are folders of instructions, scripts, and resources that AI agents can discover and use to perform at specific tasks. Write once, use everywhere. Codex uses skills to help package capabilities that teams and individuals can use to complete specific tasks in a repeatable way. This repository catalogs skills for use and distribution with Codex. Learn more: Using skills in Codex Create custom skills in Codex Agent Skills open standard Installing …
AI review promptsReview Prompts for AI-Assisted Code Review AI-assisted code review prompts for Linux kernel and systemd development. Works with Claude Code and other AI tools. Quick Start Install Kernel Prompts Only cd kernel/scripts ./claude-setup.sh Install systemd Prompts Only cd systemd/scripts ./claude-setup.sh Install Both cd kernel/scripts && ./claude-setup.sh cd ../systemd/scripts && ./claude-setup.sh Available Commands Project Review Debug Verify Kernel /krev…
The best ChatGPT that $100 can buy.nanochat nanochat is the simplest experimental harness for training LLMs. It is designed to run on a single GPU node, the code is minimal/hackable, and it covers all major LLM stages including tokenization, pretraining, finetuning, evaluation, inference, and a chat UI. For example, you can train your own GPT-2 capability LLM (which cost ~$50,000 to train in 2019) for only $73 (3 hours of 8XH100 GPU node) and then talk to it in a familiar ChatGPT-like web UI.…