A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎，预测万物

Example A2A agent implementations with security best practices and input validation

Security checklist and audit tools for MCP (Model Context Protocol) server deployments

The repo is finally unlocked. enjoy the party! The fastest repo in history to surpass 100K stars ⭐. Join Discord: https://discord.gg/5TUQKqFWd Built in Rust using oh-my-codex.

NanoMind: Embedded Intelligence Layer for AI Security Tools

Agent Trust Protocol (ATP) — an open standard for verifiable trust assertions about AI agents

AI Agent Kill Chain: A systematic framework for attacking and defending autonomous AI agent systems. The MITRE ATT&CK equivalent for AI agents.

AI Agent Threat Matrix: A structured framework for classifying, detecting, and defending against attacks on AI agent systems

GitHub Action that automatically adds and updates OpenA2A trust score badges in your README

This is the development repository for the OpenFHE library. The current version is 1.5.1 (released on April 10, 2026).

Agent Governance Specification (AGS) — Behavioral safety framework for AI agents

GitHub Action: OpenA2A Registry trust gate for AI package dependencies

OpenA2A Registry trust query CLI

Homebrew tap for OpenA2A CLI

Turn any browser into your terminal & command your agents on the go.

AI Browser Guard - Protect users from AI agent takeover in browser sessions

Open-source security tools for AI agents. Find vulnerabilities, fix root causes, prove compliance.

An autonomous agent for deep financial research

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

Installable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill c…

Open Agent Security Benchmark — 222 attack scenarios, product-agnostic adapter interface, MITRE ATLAS mapped

Agent Runtime Protection - runtime security monitoring for AI agents

One command to keep secrets out of AI (LLMs). Works with Claude Code, Cursor, Copilot, Windsurf, and any AI coding tool.

Cryptography-as-a-Service Platform - "Life is hard but cryptography doesn't have to be"

A deliberately vulnerable AI agent platform for security testing and education. Like DVWA but for AI agents.

Security toolkit for AI agents - verify skills, harden setups, scan for exposures

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

Open Source version of Claude Cowork with 500+ SaaS app integrations

A comprehensive framework and assessment toolkit for measuring and improving Cloud Native security maturity across 8 critical business functions. Includes automated scoring, contextual recommendati…

Cryptography as a service. Post-quantum ready (ML-KEM, ML-DSA), FIPS 140-2/3 compliant, context-driven encryption with zero-config SDKs. "Life is hard but cryptography doesn't have to be."