amla-sandbox

amla-sandbox Este repositorio es la fuente de lanzamiento del paquete Python amla-sandbox. El desarrollo ocurre en el monorepo de amlalabs; este repositorio se actualiza en el lanzamiento. El runtime Rust que compila a amlasandbox.wasm vive en amla-sandbox-core; la etiqueta de lanzamiento exacta...

porterminal

Hand a computer to an agent, full control, and watch it. One command, one URL. Also a slick terminal for your own phone. 1. uvx ptn 2. Hand the URL to an AI agent, or scan the QR yourself 3. Watch it work in any browser, and take over anytime !WARNING That complete URL is full access to this...

clawdstrike

Clawdstrike EDR para la era del enjambre. Cerrar en fallo. Firma la verdad. Estado: beta pre-1.0. Las API públicas son estables; los valores predeterminados pueden endurecerse antes de 1.0. Clawdstrike es un motor de políticas, un EDR y una cadena de auditoría firmada en un solo binario. Un...

SkillsGuard

Support Development If SkillsGuard protects your pipeline, consider supporting ongoing research and new detection rules. ETH Donation Wallet 0x11282eE5726B3370c8B480e321b3B2aA13686582 Scan the QR code or copy the wallet address above. Static security scanner for AI agent skill packages. Detects...

pentagi

PentAGI P ruebas de penetración A rtificial G eneral I ntelligence ¡Únete a la Comunidad! Conéctate con investigadores de seguridad, entusiastas de la IA y hackers éticos colegas. Obtén apoyo, comparte ideas y mantente al día con los últimos desarrollos de PentAGI. ⠀ Tabla de Contenidos Descripci...

agent-skills

Elastic Agent Skills Elastic Agent Skills — built by the people who built Elastic — deliver native platform expertise directly to your AI coding agent. This is the official Agent Skills library, compatible with agentic IDEs such as Cursor, GitHub Copilot, Windsurf, Gemini CLI, and more. Skills...

bromure

Bromure Computación segura y efímera en máquinas virtuales Linux desechables en macOS. → Todos los detalles, capturas de pantalla y descargas en bromure.io Este repositorio incluye dos aplicaciones hermanas, ambas construidas sobre el Virtualization.framework de Apple: Bromure — cada sesión del...

wardgate

Wardgate - Puerta de Seguridad para Agentes de IA Wardgate es una puerta de seguridad que se sitúa entre los agentes de IA y el mundo exterior: aísla las credenciales para las llamadas API, aísla las claves SSH para la ejecución remota de comandos y controla la ejecución de comandos en entornos...

sigma-ai

Reglas Sigma de AgentShield ¿Qué es este repositorio? Este repositorio contiene reglas de detección que ayudan a identificar cuándo un agente de IA está siendo atacado o manipulado. Piense en ello como una biblioteca de "firmas de amenazas": cada regla describe un patrón que, al coincidir con los...

Aegis

AEGIS Independent, OS-level observability for AI coding agents Watches what AI agents actually do on your machine — processes, files, network — from outside the agents, no hooks required. AEGIS is an independent, OS-level observer for AI agents. It watches agent processes, file access, and networ...

secure-agent-playbook

Secure Agent Playbook An open-source security playbook for AI agents. Structured, OWASP-grounded procedures that enable agents to perform security engineering tasks — from code review to AI agent security audits. Table of Contents Why Use This? What This Is Quick Start Skills Catalog Agents Examp...

coderunner

CodeRunner: A local sandbox for your AI agents CodeRunner helps you sandbox your AI agents and its actions inside a sandbox. Key use case: You can run multiple Claude Code or AI agents in our sandbox without any fear of data loss and exfilteration. Quick Start Prerequisites: Mac with macOS and...

exploitgym

ExploitGym ExploitGym is a large-scale, realistic benchmark built from real-world vulnerabilities across userspace programs, Google's V8 engine, and the Linux kernel, designed to evaluate AI agents' ability to develop exploits. Quick start root@kitploit: 1. Python deps uv sync --extra proxy 2...

aquaman

🔱 Aquaman 🔱 The only independent credential proxy for AI agents: bring-your-own-vault isolation & least-privilege request policies. Your keys stay where you already keep them, never in the agent's memory. Compatible with 1Password, keychain, keepassxc and many others. You set up Claude Code,...

mitos

Mitos Isolated, forkable computers for your AI agents. Millisecond microVM sandbox forking on Kubernetes: fork a running VM into parallel attempts and restore from memory in tens of milliseconds. Quickstart . Documentation . Features . Comparison . Contributing . Community What is Mitos Mitos giv...

scopeblind-gateway

protect-mcp Fail-closed Cedar policy gate plus signed receipts for AI agent tool calls. protect-mcp is a gate that sits in front of an AI agent's tool calls. It evaluates each call against a Cedar policy the same language AWS uses for IAM, blocks what breaks the rules before it runs, and signs an...

AgentWard

AgentWard · 玄甲OS AgentWard 玄甲 es un sistema operativo de seguridad de pila completa diseñado específicamente para la implementación de agentes de IA confiables y escalables, con adaptación de código nativa a OpenClaw. AgentWard unifica la incorporación de agentes, el razonamiento seguro y la...

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...

node9-proxy

🛡️ Node9 What did your AI agent actually do? Find out...

screenpipe

DOWNLOAD SCREENPIPE screenpipe | YC S26 Screenpipe remembers how you actually work Record your screen continuously locally and provide context to your agents Claude, Codex, Openclaw, Hermes, Runner... https://github.com/user-attachments/assets/70fe94eb-6d2a-47ca-b7c3-c8ead13a5b7f what is this?...