The LLM Gateway for Secure, Governed AI Access
agentgateway is an LLM gateway that secures and governs access to every LLM provider your teams use, with zero-trust security, audit logs, and the cost and policy controls a compliance-ready platform needs.
Capability comparison
agentgateway is the only AI gateway with full marks in all 3 categories
Why Teams Choose Us
“We can’t tell which teams are calling which LLM providers, or what it’s costing us.”
agentgateway sits in front of every LLM call, so you can see, control, and audit provider access and spend instead of trusting it blindly.
“Every cloud vendor has their own LLM gateway, and none of them work outside that one cloud.”
agentgateway is open source and self-hosted, so it runs anywhere Kubernetes does, not just inside one vendor’s walled garden.
“Security and finance won’t sign off on LLM access without audit logs and cost controls.”
agentgateway gives you audit logs, cost controls, and zero-trust security on every LLM call by default, so compliance is built in rather than bolted on after the fact.
Trust & compliance
SOC 2
Certification supports security and procurement review for regulated Kubernetes environments
OSS roots
Build on Envoy, Istio, Cilium, and Gateway API foundations for open source service mesh adoption.
CNCF maintainer status
keeps Solo.io engineers close to the projects shaping cloud native mesh standards.
FIPS builds
provide FIPS 140-2 validated options for service mesh security requirements.
Published SLAs
Define support expectations for enterprise service mesh operations.
Customer references
include production outcomes from teams running large-scale Kubernetes networking.
Frequently Asked Questions
What is an LLM gateway?
What is an LLM gateway?
An LLM gateway is the single entry point that manages, secures, and governs traffic between your applications and the LLM providers they call, centralizing access control, cost visibility, and audit logging. agentgateway is Solo's open source, AI-native LLM gateway, along with support for MCP tools and agent-to-agent (A2A) communication.
How does agentgateway control LLM costs and access?
How does agentgateway control LLM costs and access?
agentgateway gives you access control, cost visibility, and audit logging for every call to your LLM providers, so platform teams can see who's calling which model and enforce spending and access policy centrally instead of per application.
Does agentgateway work as an MCP gateway?
Does agentgateway work as an MCP gateway?
Yes. agentgateway secures and observes MCP tool calls, so you know which agents are calling which tools and can enforce policy on that traffic the same way you would for any other API call.
How is agentgateway different from a cloud provider's AI gateway platform?
How is agentgateway different from a cloud provider's AI gateway platform?
agentgateway is open source and self-hosted, so it isn't tied to one cloud. Unlike a walled-garden ai gateway platform from a single vendor, you can run it anywhere Kubernetes runs without re-architecting when you change providers.
Do I need an enterprise contract to use an open source ai gateway like agentgateway?
Do I need an enterprise contract to use an open source ai gateway like agentgateway?
Most production deployments choose Solo's enterprise support for the SLAs, audit tooling, and production hardening a compliance-ready platform needs. The underlying project is open source and donated to a vendor-neutral foundation under the Linux Foundation, so it also remains free to run on your own if you'd rather self-support.
See the LLM Gateway Built for Secure AI Access
Request a demo to see how agentgateway secures and governs LLM access in your environment, or compare your options in the Buyer's Guide first.
