The Linux Foundation has incorporated the open source agentgateway project into its organization. This AI-native proxy has been built from the ground up for AI environments, unlike existing solutions that have been adapted later. The project supports important protocols such as A2A and MCP.
Under the wing of the Linux Foundation, agentgateway will have room for organic growth. Neutral governance prevents dependence on individual suppliers. This model has proven itself in other successful open source projects.
Solo.io originally developed the project and is now transferring it to the Linux Foundation. This step guarantees vendor-neutral governance. It also gives the project the opportunity to grow under open source leadership.
Developing gateway solutions for AI environments is proving difficult with traditional techniques. Existing gateways were designed before AI agents became popular. These legacy systems cannot support modern AI protocols without major modifications.
The agentgateway represents a new approach. It is the first data plane built from scratch for AI agents. The project provides governance and security for three key interaction types: agent-to-agent, agent-to-tool, and agent-to-LLM.
A2A and MCP support
The agentgateway project supports two crucial communication protocols. Agent2Agent (A2A) was also recently made available to the Linux Foundation. In addition, the system works with Model Context Protocol (MCP).
These protocols enable effective communication between AI systems. A2A facilitates direct interactions between different agents. MCP ensures consistent context exchange when working with language models.
Major companies are showing interest in the technology. AWS, Cisco, Huawei, IBM, Microsoft, Red Hat, Shell, and Zayo are participating in early developments. This participation indicates broad industry support for AI-native infrastructure.
The source code is available on GitHub, and developers can ask questions via Discord. This accessibility should contribute to broad adoption and community involvement.
Tip: How the Model Context Protocol is taking the AI world by storm