Stars
AgentGuard: Zero-Trust Security Foundation for AI Agents
Security guard for AI agents — blocks malicious skills, prevents data leaks, protects secrets. 24 detection rules, runtime action evaluation, trust registry.
An AI red-team agent for authorized labs and web app pentesting workflows. Turns Claude Code / OpenCode / Codex into a structured recon → test → exploit → report workflow, with containerized tools …
Turn Claude Code into your offensive security research assistant. Specialized AI subagents for authorized penetration testing plan engagements, analyze recon, research exploits, build detections, a…
Open-source AI-augmented offensive security harness. 13+ autonomous agents, 150+ LLM providers, 5,300+ models, 7,600+ Ed25519-signed attack skills, 56+ built-in tools, 176+ MCP tools. MITRE ATT&CK,…
Claude Code skills collection for boosting productivity in work, learning, and investment research
Improving AI Systems with Self-Defense Mechanisms
Zero-dependency Web Application Firewall in Go. Single binary. Three deployment modes. Tokenizer-based detection.
Ethicore Engine™ is an AI safety, ethics, and compliance platform. This repo consists of the open-source components of Ethicore Engine™ - Guardian SDK; designed to protect your AI applications from…
expdb2015 / strix
Forked from usestrix/strixOpen-source AI agents for penetration testing
基于 AI Agent + MCP 工具链 + 渗透 Skill 编排， 配合大语言模型， 自然语言输入 → 自动完成「信息收集 → 漏洞发现 → 漏洞利用 → 报告生成」全流程。
🎨 Best DeepSeek Harness Design Plugin. The open-source Claude Design alternative. 🖥️ Local-first desktop app. 🖼️ Your coding agent becomes the design engine: prototypes, landing pages, dashboards, …
Bring any model to Codex, assign them any role, use them in /goal or any workflow.
A list of useful payloads and bypass for Web Application Security and Pentest/CTF
AI security toolkit for prompt injection detection, sensitive data protection, runtime monitoring, and threat intelligence for LLM and agent workflows.
针对于红队攻击思维做出的red team模式(破限项目，封号概不负责）##可自行适配其他Agent。项目问题请提issue
通用数字人系统是一个基于深度学习和WebRTC技术的智能交互平台，集成了Azure Avatar数字人渲染、语音识别合成、自然语言处理等技术。系统支持实时对话、知识问答和情感交互，可实现30FPS以上的流畅渲染和200ms以内的低延迟响应。核心功能包括基于GPT的智能对话、多语言及方言支持、知识库实时检索、表情情感同步等。采用FastAPI和LangChain框架开发，支持Docker一键部…
fay是一个帮助数字人（2.5d、3d、移动、pc、网页）或大语言模型（openai兼容、deepseek）连通业务系统的agent框架。
Open-source AI agent firewall for MCP security and agent egress. Scans mediated HTTP, MCP, A2A, and WebSocket traffic for exfiltration, SSRF, and prompt injection, and emits mediator-signed action …
MISP (core software) - Open Source Threat Intelligence and Sharing Platform
Self-hosted AI agent memory server with MCP, evidence provenance, typed claims, conflict detection, embeddings, recall, PostgreSQL, and pgvector
Create beautiful slides on the web using a coding agent's frontend skills
LEAKED SYSTEM PROMPTS FOR CHATGPT, CLAUDE, GEMINI, GROK, PERPLEXITY, CURSOR, LOVABLE, REPLIT, AND MORE! - AI SYSTEMS TRANSPARENCY FOR ALL! 👐
Bring projects, wikis, and teams together with AI. AppFlowy is the AI collaborative workspace where you achieve more without losing control of your data. The leading open source Notion alternative.
Codex plugin and Obsidian vault kit for turning anything into a knowledge system.
AI for Science 论文解读合集（持续更新ing），论文/数据集/教程下载：hyper.ai
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing…