Search

Run JavaScript from AI agents, plugins, and workflows in a separate Node.js process with strict safety limits.

Run Claude Code and the REA reverse-engineering MCP server in rootless Podman or a libkrun microVM per command, with an egress proxy, a mount policy and self-tests.

CLI tool to discover, select, and install agent skills based on project requirements

A framework for managing agent trust, such as public vs. private computers.

AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.

Universal Zero-Refusal Agent Framework - 40+ jailbreak templates (T1-T119), 1128 curated skills, executable framework-core, installer untuk Hermes/Claude/Codex/opencode. Verified.

Yad companion (Part B, the brain). Pairs with the Yad Chrome extension for real-browser automation, or runs standalone with Playwright and your own Ollama instance. No cloud copy of your accounts.

Enterprise cybersecurity AI agent system — 7 specialized agents with LLM orchestrator and 5-layer architecture

Run AI coding agents (Claude Code, OpenCode) safely inside sandboxed Docker containers with audit logging

TradeOS AI is an enterprise-grade, AI-powered trading platform purpose-built for professional traders and investment firms. It streamlines the full trade lifecycle—from data ingestion and strategy design to backtesting, execution, and reporting—across crypto, forex, and traditional markets. With no-code/low-code tools, customizable AI agents, multi-exchange integrations, risk controls, and real-time analytics, TradeOS AI enables rapid strategy deployment and end-to-end workflow automation. Desig

Proof-Carrying Authority tool guard for Pydantic AI (verify a PCActn before each tool runs)

面向安全靶场的自主渗透 Agent：ReAct 双层架构 · 三层记忆 · 可自我扩展的 pentool 工具注册表，内核为 600 行 TypeScript nano-pi

ARCA — Local RL-powered Autonomous Cyber Pentesting Agent with LangGraph

Entropy0 Trust Control Plane tool for LangChain agents — evaluate domains and URLs before your agent fetches content from them.

FortifyOS runtime protection for LangChain and LangGraph agents — zero code changes required.

Read-only scanner for prompt-injection and LLM anti-analysis text in files before agent review

Trust & governance layer for OpenAI Agents SDK — policy enforcement, trust-gated handoffs, and hash-chained audit trails

Local, private, uncensored AI research workstation for Linux: a self-hosted LLM with an autonomous deep-research agent, anonymous web search, encrypted DNS, and Tor egress - fully ephemeral, no telemetry, no cloud.

AI model: golf-mcp/golf-prompt-guard

Multi Agent Protocol Language Engine - Advanced Multi-Agent Communication Protocol Framework