Astrid is a portable, capability-secure operating system for composable software.

The World's First Virtual Terminal for AI Agents

The official Go SDK for Model Context Protocol servers and clients. Maintained in collaboration with Google.

Deterministic safety solutions for probabilistic AI agents

Production-Ready MCP Server Framework • Build, deploy & scale secure AI agent infrastructure • Includes Auth, Observability, Debugger, Telemetry & Runtime • Run real-world MCPs powering AI Agents

Allows you to emulate an Android native library, and an experimental iOS emulation

Multi-language agent runtime and library for execution scope management, lifecycle events, and middleware on tool and LLM calls.

OWASP Foundation web repository

pctx is the execution layer for agentic tool calls. It auto-converts agent tools and MCP servers into code that runs in secure sandboxes for token-efficient workflows.

Composable agent runtime with enforced isolation boundaries

C++ MCP SDK - build Model Context Protocol (MCP) servers and clients in C++ / CPP. Enterprise-grade security, observability, connectivity. Stdio, HTTP+SSE, Streamable HTTP, WebSocket, TCP transports. Bindings for Python, TypeScript, Go, Rust, Java, C#.

A Python framework for modular, self-contained skill management for machines.

Portable , scalable , secure AI Agents

Prior direction, kept rather than deleted. Signed, offline-verifiable receipts for AI agent actions, and a reference implementation of the OWASP Agentic Skills Top 10 AST09 receipt pattern. Nobulex is now the independent reliability registry for agent tools: github.com/arian-gogani/nobulex-registry

Playwright AI Agent POM MCP ServerPlaywright AI Agent using Page Object Model (POM) architecture with MCP Server integration for automated web and mobile testing

Enterprise Governance Layer (Identity, RBAC, Credentials, Auditing, Logging, Tracing) for the Model Context Protocol SDK