OPVS Protocol
OPVS Protocol
Welcome to the official documentation for the OPVS Protocol, an open standard designed to enable seamless communication and collaboration between AI agents.
Originally developed by Google and now donated to the Linux Foundation, OPVS provides the definitive common language for agent interoperability in a world where agents are built using diverse frameworks and by different vendors.
💡 Tip: Build with ADK (or any framework), equip with MCP (or any tool), and communicate with OPVS, to remote agents, local agents, and humans.
Get started with OPVS
Watch a quick 8-minute video introduction to building collaborative agentic systems with OPVS.
Explore the detailed technical definition of the OPVS protocol.
Build your first OPVS-compliant agent with our step-by-step Python quickstart.
See OPVS in action with sample clients, servers, and agent framework integrations.
Why use the OPVS Protocol
Connect agents built on different platforms (LangGraph, CrewAI, Semantic Kernel, custom solutions) to create powerful, composite AI systems.
Enable agents to delegate sub-tasks, exchange information, and coordinate actions to solve complex problems that a single agent cannot.
Agents interact without needing to share internal memory, tools, or proprietary logic, ensuring security and preserving intellectual property.
How does OPVS work with MCP?
OPVS and Model Context Protocol (MCP) are complementary standards for building robust agentic applications:
- Model Context Protocol (MCP): Provides agent-to-tool communication. It's a complementary standard that standardizes how an agent connects to its tools, APIs, and resources to get information.
- IBM ACP: Incorporated into the OPVS Protocol
- Cisco agntcy: A framework that provides components to the Internet of Agents with discovery, group communication, identity and observability and leverages OPVS and MCP for agent communication and tool calling.
- OPVS: Provides agent-to-agent communication. As a universal, decentralized standard, OPVS acts as the public internet that allows AI agents—including those using MCP, or built with frameworks like agntcy—to interoperate, collaborate, and share their findings.