NemoClaw

NVIDIA NemoClaw: Reference Stack for Sandboxed AI Agents in OpenShell NVIDIA NemoClaw is an open source reference stack for running always-on AI agents more safely inside NVIDIA OpenShell sandboxes. It provides guided onboarding, a hardened blueprint, routed inference, network policy, and lifecyc...

phantom-brain

PHANTOM BRAIN v0.9 Offline AI-powered pentesting analysis tool with real hardware integration Local LLM analysis via Ollama for WiFi, Sub-GHz, NFC/RFID and WPA2 captures — no internet required, no cloud APIs, 100% offline. The main LLM runs on a Windows PC. The Raspberry Pi acts as a lightweight...

claude-code-guardrails

We have since built a dedicated product to help developers manage AI permissions better, which we intend to make open source. Check it out atstoplight.ai. Claude Code Guardrails settings.json works if: You're fine editing JSON and killing Claude Code sessions every time policy changes Your securi...

ws4-secure-design-agentic-systems

CoSAI Workstream 4: Secure Design Patterns for Agentic Systems This repository is for the work of the CoSAI Workstream 4, Secure Design Patterns for Agentic Systems. CoSAI is an OASIS Open Project and an open ecosystem of AI and security experts from industry leading organizations dedicated to...

distributed-system-testing

Distributed Systems Testing Skills Two skills for AI coding agents that design and run claim-driven tests for distributed and stateful systems. Together they produce a structured Markdown test plan and a findings report with 10-state verdicts and an explicit SUT / harness / checker / environment...

The Quantum Ad-List

The Quantum Ad-List Next-Generation AI-Powered Ad & Tracker Blocking 📜 Table of Contents 1. Legal & Ethical Notice 2. Project Overview Maintainers Technical Architecture Motivation Security & Privacy 3. Installation Hosts File Integration Ad-Blocker Compatibility Pi-hole Integration 4. Issue...

asterion-network-minotaur

Ethical network security auditor — 50+ checks across SMB, RDP, LDAP, SSH, Kerberos and more, with AI-powered CVE analysis and OWASP/CIS/NIST compliance mapping. Quick Start · Documentation · Docker · AI Features · Star on GitHub In Action Local scan · 127.0.0.1 ·...

jadx-ai-mcp

JADX-AI-MCP Part of Zin MCP Suite ⚡ Fully automated MCP server + JADX plugin built to communicate with LLM through MCP to analyze Android APKs using LLMs like Claude — uncover vulnerabilities, analyze APK, and reverse engineer effortlessly. ⭐ Contributors Thanks to these wonderful people for thei...

numasec

numasec The open source AI security agent. Give your terminal a security brain. Run security workflows with your local tools, agents, runbooks, findings, evidence, replay and reports. npm install -g numasec Demo | Why | What it feels like | Try it | What it does | Commands | Architecture | Roadma...

tealtiger

TealTiger AI Agent Security & Governance SDK Deterministic governance, guardrails, cost tracking, and policy management for LLM applications. Open source. TypeScript + Python. Works with any provider...

authproof-sdk

AuthProof SDK AuthProof is a cryptographic delegation protocol for agentic AI. Most protocols in this space enforce against an operator-defined policy -- giving the operator authority to expand or reinterpret the user's original intent after the fact. AuthProof is built around a different trust...

veilgate

VeilGate VeilGate is an open-source deception proxy for teams that want to raise the cost of automated security probing without putting fragile block rules in front of real users. It sits in front of a web application, scores each request, and chooses one of three outcomes: Real : forward clean...

Decepticon

Decepticon — Autonomous Red Team Agent "Another AI hacker? Let us guess — it runs nmap and writes a report."...

on-device-browser-agent

Local Browser - On-Device AI Web Automation Launching support for runanywhere-web-sdk soon in our main repo: please go check it out: https://github.com/RunanywhereAI/runanywhere-sdks A Chrome extension that uses WebLLM to run AI-powered web automation entirely on-device. No cloud APIs, no API key...

argus-wp-watcher

Ethical WordPress vulnerability scanner — real-time CVE correlation, OWASP mapping, AI-powered analysis, and consent-based testing. Quick Start · Documentation · Docker · AI Features · Star on GitHub...

PANO

PANO - Platform for Analysis and Network Operations PANO is a powerful OSINT investigation platform that combines graph visualization, timeline analysis, and AI-powered tools to help you uncover hidden connections and patterns in your data. Getting Started • Features • Documentation • Contributin...

fas-judgement-oss

FAS Judgement Prompt Injection Attack Console Test your AI's defenses before someone else does. Install | Game Mode | Leaderboard | Demo Target | Features | Elite | Contributing Why Judgement?...

meta-ai-support-prompt

Meta AI Support Assistant System Prompt Extracted system prompt from Meta's AI Support Assistant on June 1, 2026. Files system-prompt.md — Extracted system prompt ⚠️ Disclaimer & Legal Notice Purpose This repository is published strictly for educational and authorized security research purposes...

redai

RedAI A terminal workbench for AI-driven vulnerability discovery and live validation. Most "AI security" tools stop at flagging code that looks vulnerable. RedAI goes further: after scanner agents produce candidate findings, validator agents work inside a live environment — a running instance of...

buyer-eval-skill

Buyer Eval — The Rotten Tomatoes of B2B Software A free, open-source Claude skill that evaluates B2B vendors by talking to their AI agents, cross-referencing every claim against independent sources, and scoring what's verified vs. what's just optimistic marketing. New in v3.5 — Vendor questions a...