
worldmonitor
Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational…

Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational…

Self-hostable AI SOC that fuses security alerts, auto-triages via agentic AI, runs MITRE ATT&CK investigations, and logs every agent decision in a…

Autonomous AI pentesting agents — real-time reconnaissance, vulnerability detection, and exploitation orchestration. Go + TypeScript.

Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and…

L'agent qui grandit avec vous

Agent de hacking autonome pour Red Team

Testez vos prompts, agents et RAGs. Red teaming / tests d'intrusion / scan de vulnérabilités pour l'IA. Comparez les performances de GPT, Claude,…

Open-source AI penetration testing tool to find and fix your app’s vulnerabilities.

Open-source AI agent firewall that scans HTTP, MCP, A2A, and WebSocket traffic for exfiltration, SSRF, and prompt injection, emitting verifiable…

Un dépôt pour jailbreaker divers LLM, principalement Claude

Open security scanner and self-hosted control plane for AI, MCP, and cloud. One evidence model — run scans in your environment, centralize findings,…

Installable Claude Skills providing expert-level compliance guidance for 30+ frameworks including ISO 27001, SOC 2, FedRAMP, GDPR, HIPAA, NIST CSF,…

AI-powered penetration testing assistant for automating recon, note-taking, and vulnerability analysis.

Les fichiers sources et les outils nécessaires pour construire les jeux de cartes OWASP Cornucopia dans différentes langues

Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at…

Desktop monitoring and local security reviews for AI agents, with opt-in policy-controlled execution and MCP action tools. Windows primary;…

Une alternative légère à OpenClaw qui s'exécute dans des conteneurs pour la sécurité. Se connecte à WhatsApp, Telegram, Slack, Discord, Gmail et…

Exécutez des agents comme Hermes, LangChain Deep Agents et OpenClaw de manière plus sécurisée dans NVIDIA OpenShell avec managed inference.