Search

A read-only security skill for evaluating repositories, packages, MCP servers, plugins, and installation commands recommended by AI agents.

Claude Code agent for analyzing Google Cloud Run instances — resource waste, performance, pricing, traffic, and security

MindPal Device Agent SDK - Build intelligent device agents with plugin architecture, secure handshake, and multimodal capabilities

AI-powered video conversations for any website platform. Lightweight, secure, and platform-agnostic integration with AI video presenters.

Core engine for AI agent — LLM orchestration, tool execution, MCP, skill routing, security, and memory pipeline.

Zenii - A lightweight, secure, local-first fully-autonomous AI agent for desktop, CLI, and daemon. Rust + Tauri.

A lightweight, security-first AI chat CLI and autonomous coding agent for local Ollama models by Ethern Myth.

Lightweight, secure Docker agent with REST and WebSocket APIs for container management and real-time monitoring, built with FastAPI.

An open AI Agent Skill for building robust, secure, and production-ready React.js applications across all frameworks.

Install init-web globally for planning React/Vite web apps with package supply-chain security guidance.

Provide a safe phishing drill platform for security training, host monitoring, and desktop screenshots to assess user awareness

.NET implementation of the Agent2Agent (A2A) protocol to enable secure, interoperable communication between autonomous agents across frameworks and vendors.

A provider-agnostic AI agent runtime exploring tool execution, context engineering, observability, evaluation, durability, and security.

local-first agent runtime. one binary. memory, sandboxing, observation, security, package management. agents run on top.

🛡️ Security scanner for AI agents. Finds vulnerabilities in MCP servers, agent configs, and tool setups. Written in Rust.

Independent, source-backed handbook for DeepSeek AI's official DeepSeek Harness (dsh): agents, plugins, security, troubleshooting, and runbooks.

The ReAct loop, tools, context engineering, memory, planning, MCP, evals and security — built from scratch in dependency-free TypeScript.

Local-first, durable coding-agent runtime with a shared CLI/Web kernel, tool orchestration, recovery, security and verification.

An extensible desktop AI workspace that connects models and agents to local files, applications, and system tools through secure, installable plugins.

Next-Generation Non-Custodial M-of-N MPC Security & x402 USDC Payment Infrastructure for Autonomous AI Agents