The only gateway for your entire AI strategy

Secure, connect, and observe your entire AI ecosystem, from LLMs to agents, through a single point of control: agentgateway.

Get started

Invested in open source

We are deeply committed to the open-source community, creating and leading foundational projects that define the future of AI and cloud-native connectivity.

“We are excited to welcome the agentgateway project to the Linux Foundation, ensuring that best practices for agentic workflows remain free and open to all. Agentgateway complements emerging specifications like A2A and MCP, and offers scalable, specification-aligned infrastructure for agent communication thereby empowering customers and developers to build robust agentic workflows across platforms.”

Mitch Connors

CNCF Ambassador

“I'm excited to see Solo.io donate the agentgateway project to the Linux Foundation. Open sourcing an AI-native connectivity solution that understands MCP and A2A is a big win for the community. It helps us scale AI responsibly, with the security, flexibility, and governance we need in the real world.”

Rob Hansen

Director, digital product engineering and platforms

"The future won’t be built by standalone agents, MCP servers or LLMs — it’s shaped by their interconnection and ability to work together seamlessly. To unlock their full potential, we must apply policies, ensure control and maintain clear visibility into their interactions.

This is where agentgateway plays a pivotal role — bridging not only agent-to-agent (A2A) communication but also agent-to-MCP servers, filling a critical gap in the ecosystem. I look forward to seeing the project’s continued momentum within the Linux Foundation.”

John Roese

Global chief technology officer & chief AI officer

“AI agents are rapidly transforming how enterprises work and innovate. To adopt them responsibly at scale, organizations need open and interoperable gateways that provide governance, visibility, and security.

Agentgateway delivers the foundation enterprises need. I’m excited to see the community come together to accelerate the open foundation our customers need to scale AI on cloud platforms like CoreWeave.”

Chen Goldberg

Senior vice president of engineering

“Building reliable AI agents is a challenge, especially when every step involves non-deterministic calls to LLMs, tools, and autonomous agents. Agentgateway’s integration with OpenTelemetry provides a robust foundation for observability, allowing us to treat each request-response pair as an evaluable unit. This capability is crucial for ensuring system-level accuracy and trustworthiness, paving the way for a true ‘AI mesh' that empowers teams to scale, secure and optimize their AI workflows.”

Sathish Krishnan

Executive director/distinguished engineer, cloud & AI

"Agentic AI demands purpose-built infrastructure, not just another software layer. This requires rethinking compute, storage, and data movement from the ground up, so retrofitting legacy systems doesn't work.

The agentgateway project is a solid step toward that future. We're happy to see it hosted by the Linux Foundation, where open source and community can drive the adoption and longevity that AI infrastructure requires."

Jon Alexander

Senior vice president of cloud technology

“The rapid evolution of the AI landscape demands robust, vendor-neutral infrastructure for how agents communicate with each other and with external tools. Without it, we risk stifling innovation and adoption.

The agentgateway project, hosted by the Linux Foundation, is a crucial step in creating that common ground. We are excited to partner with Solo.io and support a community-driven foundation for the future of interoperable AI."

Jim Bugwadia

Creator and CEO

“One of the biggest open security problems today is how to do MCP security effectively. While there are a lot of problems in this space that the community doesn't know how to address, the agentgateway project provides a first step toward addressing some of the important issues with basic role-based access control and visibility of actions to MCP servers.

I look forward to seeing how this project adapts and evolves to handle the complex, evolving threats in this space under open source governance.”

Justin Cappos

NYU professor and creator of the TUF, Uptane and in-toto projects

Your infrastructure will crumble under AI workloads

Built from the ground up to meet the unique requirements of AI and agentic protocols, agentgateway supports the evolving protocols that legacy gateways can't, giving you a future-proof foundation for agentic connectivity.

Engineered for AI connectivity

AI Gateway

LLM consumption

Keep provider keys safe and LLM access tightly controlled.

LLM provider keys are high-value targets - sharing them across teams increases the blast radius from compromise and creates unnecessary risk. Agentgateway enterprise secures keys in centralized storage, integrates with enterprise IAM, and supports multiple auth protocols (API Key, JWT, OAuth/OIDC) to secure access and implement fine-grained authorization.

Stop malicious prompts and prevent data leaks before they happen.

Without guardrails, LLMs can be manipulated into harmful or unsafe behavior. Agentgateway enterprise enforces inline protections on prompts and responses, integrates with provider moderation endpoints, and allows custom semantic guardrails via extensions.

Know exactly how, when, and where your LLMs are being used.

Treating LLMs as just another API call limits your ability to monitor critical context-specific telemetry on LLM performance, activity, and cost reporting. Agentgateway enterprise provides real-time logging, detailed consumption metrics, and end-to-end tracing with OpenTelemetry, enabling precise visibility into model behavior and cost.

Prevent runaway usage and keep budgets under control.

LLM workloads can spiral quickly, leading to unexpected costs or LLM provider throttling, potentially leading to intermittent outages and availability issues.. Agentgateway enterprise applies request and token-based rate limits to apply backpressure on clients to prevent hitting provider rate limits or overrun budget allocations — ensuring predictable, sustainable consumption.

One API for every model, provider, and version.

Changing your model or provider should not require expensive and time consuming changes to application logic. Agentgateway enterprise standardizes LLM access with a uniform API, allowing for seamless transition between models and providers to optimize for performance, availability, and pricing.

Inference Gateway

LLM Serving

One API for every model, provider, and version.

Existing gateway solutions lack context awareness for routing requests to specific models. Agentgateway enterprise delivers context-aware model routing that understands request metadata and dynamically directs traffic to the right model, including fine-tuned model instances.

Isolate fine-tuned models by use case.

Fine-tuned models amplify business value, but they often break traditional routing patterns. Agentgateway enterprise supports intelligent routing to fine-tuned models, ensuring that specific users and use cases are routed to the optimal model to satisfy their request.

Maximize GPU utilization with intelligent workload placement.

Accelerated infrastructure is expensive and can be underutilized when routing with traditional ingress gateways. Agentgateway enterprise allows you to route to defined inference pools that map to underlying infrastructure. Integration with llm-d allows for smart routing across prefill and decode stages — isolating compute and memory-bound operations to extract maximum efficiency from GPUs.

Lower latency, faster responses, more responsive clients.

Long response times and token delays frustrate users and waste resources. Agentgateway enterprise uses real-time inference metrics to route requests to models with available capacity, reducing latency and time-to-first-token while improving overall responsiveness.

Make sure critical workloads always go first.

When model capacity is maxed out, standard ingress treats all requests equally — putting critical LLM integrations at risk. Agentgateway enterprise supports priority scheduling, enabling organizations to set policies by use case and model so mission-critical requests are always served first.

Agent Gateway

MCP and A2A

Establish uniform and comprehensive tool server security.

The landscape of MCP tool server security is mixed at best, creating an environment ripe for exploit and attack when integrating with community tool servers. Agentgateway enterprise mitigates these risks by sandboxing tool servers, enforcing strong authentication, authorization, and policy, and integrating with enterprise IAM.

Thousands of tool servers, centralized registry and discovery.

With tens of thousands of community MCP tool servers available, coming to terms with which tools you have available can be an integration nightmare. Agentgateway enterprise federates all tool servers into a central tools registry that appears as a single, virtualized MCP tool server to clients.

Expose the right tools to the right agents and clients.

When presented with too many tools, the quality of agent performance degrades substantially. Following a principle of least privilege, agents and MCP clients should only see the tools they need to perform their job. Agentgateway enterprise selectively exposes tools based on policy, dynamically adjusting discovery and access so agents only see the tools they’re authorized to use. This minimizes confusion while isolating tool servers for security and stability.

Gain full visibility into every agent and tool interaction.

Debugging agent-to-agent or agent-to-tool behavior in a world of tool sprawl is time consuming and error prone. Agentgateway enterprise centralizes telemetry collection and reporting to deliver deep metrics, logging, and tracing for every interaction - eliminating the need to dig into individual tool server implementations for answers.

Instantly turn existing REST APIs into agent-ready tools.

Most enterprises already have valuable APIs, but custom development is costly to integrate them into MCP. Agentgateway enterprise automatically imports and exposes REST APIs as tools using their OpenAPI definition, giving agents secure, observable, and governed access instantly without additional coding.