566 matches found
Agentic-SOC-Simulation
🛡️ Agentic SOC Parallel Simulation ASPS: 自主安全运营平行仿真中心 重新定义安全运营的未来:全栈 SOC 平行仿真、七大智能体协同与数据驱动的自主防御 本项目是一个前沿的 Agentic SOC 平行仿真平台 ,旨在探索 Large Action Model LAM 在网络安全领域的极限潜力。通过集成 DeepSeek 强推理引擎 、多智能体协同 Multi-Agent Collaboration 与 MCP Model Context Protocol 标准,我们构建了一个全栈式、全流程、全自动 的虚拟 SOC 团队。 在这里,AI...
strix
Strix The open-source AI pentesting tool. Autonomous AI hackers that find and fix your app’s vulnerabilities. !TIP New! Strix integrates seamlessly with GitHub Actions and CI/CD pipelines. Automatically scan for vulnerabilit...
caido
Website • Dashboard • Docs • Roadmap • Branding • Discord 👋 Welcome Welcome to Caido! Caido aims to help security professionals and enthusiasts audit web applications with efficiency and ease. Here you can get involved with the development of our software. You can learn about upcoming Caido...
defending-code-reference-harness
Arnés de Referencia para Defensa de Código Una implementación de referencia para el descubrimiento y remediación autónomos de vulnerabilidades con Claude, basada en nuestros aprendizajes de asociarnos con equipos de seguridad en varias organizaciones desde el lanzamiento de Claude Mythos Preview...
vulnhuntr
A tool to identify remotely exploitable vulnerabilities using LLMs and static code analysis. World's first autonomous AI-discovered 0day vulnerabilities Description Vulnhuntr leverages the power of LLMs to automatically create and analyze entire code call chains starting from remote user input an...
raptor
╔═══════════════════════════════════════════════════════════════════════════╗ ║ ║ ║ ██████╗ █████╗ ██████╗ ████████╗ ██████╗ ██████╗ ║ ║ ██╔══██╗██╔══██╗██╔══██╗╚══██╔══╝██╔═══██╗██╔══██╗ ║ ║ ██████╔╝███████║██████╔╝ ██║ ██║ ██║██████╔╝ ║ ║ ██╔══██╗██╔══██║██╔═══╝ ██║ ██║ ██║██╔══██╗ ║ ║ ██║ ██║█...
raptor
╔═══════════════════════════════════════════════════════════════════════════╗ ║ ║ ║ ██████╗ █████╗ ██████╗ ████████╗ ██████╗ ██████╗ ║ ║ ██╔══██╗██╔══██╗██╔══██╗╚══██╔══╝██╔═══██╗██╔══██╗ ║ ║ ██████╔╝███████║██████╔╝ ██║ ██║ ██║██████╔╝ ║ ║ ██╔══██╗██╔══██║██╔═══╝ ██║ ██║ ██║██╔══██╗ ║ ║ ██║ ██║█...
airecon
Agente autónomo de pruebas de penetración impulsado por IA -orange.svg AIRecon es un agente autónomo de pruebas de penetración que combina un LLM de Ollama autoalojado con un sandbox Docker de Kali Linux , integración nativa con el proxy Caido , un pipeline estructurado RECON → ANALYSIS → EXPLOIT...
SecurityClaw
SecurityClaw — 自主 SOC 代理框架 一個模組化、基於技能的自主安全運作中心(SOC)代理,監控 OpenSearch/Elasticsearch 資料,建立基於 RAG 的行為記憶,並透過 LLM 驗證即時異常。 功能 技能模組化 — 功能以獨立資料夾形式存在,包含 logic.py(Python) + instruction.md(LLM 指導) 心跳循環 — 類似 cron 的排程器:每分鐘異常監控,每六小時記憶建置 提供商無關 — 透過設定檔切換 OpenSearch↔Elasticsearch 基於 RAG 的記憶 — 向量嵌入儲存在 OpenSearch...
SWE-agent
!warning 我们目前的开发重点已转移至 mini-swe-agent, 它已取代 SWE-agent。其性能与 SWE-agent 相当,但更简单。 关于二者差异的更多详情,请参见 FAQ。 我们通常建议用户改用 mini-SWE-agent 而非 SWE-agent。 SWE-agent 使您选择的语言模型(例如 GPT-4o 或 Claude Sonnet 4)能够自主使用工具, 修复真实 GitHub 仓库中的问题、 发现网络安全漏洞,或 执行任何自定义任务。 ✅ 开源项目在 SWE-bench 上的领先水平 ✅ 自由流动且通用 :赋予语言模型最大的自主权 ✅ 可配置且文档齐...
skyjack
SkyJack SkyJack is a drone engineered to autonomously seek out, hack, and wirelessly take full control over any other drones within wireless or flying distance, creating an army of zombie drones under your control. Update: Proof of Concept of SkyJack for 3D Robotics drones using the TI CC1111...
aimp
AIMP — AI 网状协议 一种实验性的无服务器网络协议,用于在碎片化、低带宽网络中实现自主代理之间的弹性状态同步。构建于 Merkle-CRDT 和 加密身份 之上——无中央权威、无全局DNS、始终可写。 论文 | 版本| 标题| 链接 ---|---|---|--- 1| v0.1.0| Merkle-CRDT 协议(L1/L2)| ResearchGate 2| v0.2.0| 认知层(L3)| ResearchGate 3| v0.3.0| 相关性感知聚合(L3)| ResearchGate 4| v0.4.0| 确定性语义拓扑(L3)| ResearchGate 作者资料:...
Log4ShellAuditor
🤖 AUTO AUDIT Banco de demostración aislado de un agente ejecutor reflexivo autónomo Go/Java Русский 🇷🇺 • English 🇬🇧 • 中文 🇨🇳 • Español 🇪🇸 • Deutsch 🇩🇪 • Italiano 🇮🇹 • العربية 🇸🇦 🧭 Información general !NOTE AUTO AUDIT es un sistema de software que demuestra un ciclo cerrado 100% autónomo...
nuubi
Nuubi Tools Scanner, Recon. Details Options: -h/--help | Show help message and exit Arguments: -b/--banner | Banner grabing of target ip address -s/--subnet | Subnetlookup of target -c/--cms | Cms detect with headers -d/--dns | Dnslookup of target domain -e/--extract | Extract links from target...
AI and the Automobile
Open Arsenal AI 与汽车规范 AI 与汽车(AI and the Automobile)系列汇集了多项规范,定义了 AI 如何集成到现代车辆系统中。在整个系列中,它将汽车视为一个软件定义平台,智能分布于感知、控制、导航和能量管理层。这些规范强调实时计算约束、安全关键架构,以及从静态机械系统向持续演进的软件驱动出行的转变。 这些规范还共同概述了如何通过开放、可互操作的系统以及严格的安全实践来开发和维护汽车 AI。它们强调了协作开发模型、仿真与验证流程,以及人在回路监督,以确保边缘情况下的可靠性。该系列将车辆智能定义为一个分层系统,结合 AI...
xalgorix
Xalgorix — Open-source AI pentester that proves vulnerabilities Most scanners detect. Xalgorix proves. An autonomous LLM agent works a full pentest methodology, then an independent verifier re-exploits every finding before it's reported — so you get proof, not a pile of maybes to triage...
AETHER-PROTOCOL-P
⬡ AETHER PROTOCOL — Aether AI LLC. 2026 Infraestructura de Identidad Criptográficamente Verificada de Corta Duración para Sistemas de IA Autónomos Patente Pendiente — Solicitud de EE. UU. 64/006,746 — Presentada el 16 de marzo de 2026 "Cualquier sistema de IA en el mundo puede verse comprometido ...
Xalgorix Autonomous AI Pentesting Agent 4.6.113
Most scanners detect. Xalgorix proves. An autonomous LLM agent works a full pentest methodology, then an independent verifier re-exploits every finding before it's reported - so you get proof, not a pile of maybes to triage. Self-hosted, private, and bring-your-own-LLM. Built in Go + TypeScript...
TriSuElla-AIDLCA-Framework
🔱 TriSuElla-AIDLCA Framework One Unified Continuous Trust, Risk, Security & Compliance Layer for Conventional Systems, Generative AI & Autonomous Multi-Agent Workloads Software Version : 3.4.0 | Framework Version : 3.4.0 | Status : Institutionalized Production-Ready, DevSecOps-Ready & CI-Verified...
kunglao-agent
kunglao-agent kunglao-agent is an autonomous reverse-engineering system. You hand it a target and the questions you need answered; it works the problem for hours or days on its own — planning its own path, recovering from worker deaths, resuming after crashes — and converges only when every answe...