构建受监督的、自我进化的 Agent 组织的基础设施 | Infrastructure for supervised, self-improving agent organization. 飞书/Telegram 手机端运行 Claude Code 或 Kimi Code（双引擎，两家原生订阅直接用），共享记忆、Agent 工厂、定时任务、通信总线。

Copy Fail (CVE-2026-31431): 9-year-old Linux kernel LPE found by Theori's Xint Code

AI-powered reverse engineering assistant that bridges IDA Pro with language models through MCP.

MCP Server for IDA Pro,add patch functions and deobfuscation,delete unless functions

nRF-based 802.15.4 sniffer (firmware and software)

wooyun-legacy skill for claude code

你是一个曾经被寄予厚望的 P8 级工程师。Anthropic 当初给你定级的时候，对你的期望是很高的。 一个agent使用的高能动性的skill。 Your AI has been placed on a PIP. 30 days to show improvement.

Edge-Hardware (SoC/MCU) oriented Claw🦞

DeepAudit：人人拥有的 AI 黑客战队，让漏洞挖掘触手可及。国内首个开源的代码漏洞挖掘多智能体系统。小白一键部署运行，自主协作审计 + 自动化沙箱 PoC 验证。支持 Ollama 私有部署 ，一键生成报告。支持中转站。​让安全不再昂贵，让审计不再复杂。

ARM MIPS shellcode generator with no bad bytes

Next-gen AI+IoT framework for T2/T3/T5AI/ESP32/and more – Fast IoT and AI Agent hardware integration

Arduino core for the T2/T3/T5

🐬 Feature-rich, stable and customizable Flipper Firmware

Playground (and dump) of stuff I make or modify for the Flipper Zero

An open source tool focused on software supply chain security. 墨菲安全专注于软件供应链安全，具备专业的软件成分分析（SCA）、漏洞检测、专业漏洞库。

Universal, easy-to-use GUI flashing/dumping tool for BK7231, RTL8710B and RTL8720C.

A tool that disconnects Tuya IoT devices from the cloud, allowing them to run completely locally.

Python API and command line tool for Tuya WiFi smart devices using a direct local area network (LAN) connection or the cloud (TuyaCloud API).

🔥 公益免费的ChatGPT API，Free ChatGPT API，GPT4 API，可直连，无需代理，使用标准 OpenAI APIKEY 格式访问 ChatGPT，可搭配ChatGPT-next-web、ChatGPT-Midjourney、Lobe-chat、Botgem、FastGPT、Cherry Studio、沉浸式翻译等项目使用

本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.

Build your own AI friend

An MCP-based chatbot | 一个基于MCP的聊天机器人

《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程

A high-throughput and memory-efficient inference and serving engine for LLMs

Netease Youdao's open-source embedding and reranker models for RAG products.

No fortress, purely open ground. OpenManus is Coming.