CAMBRIDGE, Mass., Sept. 10, 2026 (GLOBE NEWSWIRE) -- Solo.io, the leading provider of cloud native connectivity and AI-ready infrastructure, today announced a standalone mode for Solo Enterprise for agentgateway. Standalone mode ships the enterprise gateway as a single self-contained binary or container that runs in any environment, from a virtual machine or ECS task to bare metal or a developer workstation, extending the governance capabilities Solo.io has implemented for agentic infrastructure to every environment where agents run. Standalone also adds a complete self-service UI for configuration and management, allowing teams to configure model providers, register MCP servers, set policy, and inspect traffic across all supported environments.
Enterprise AI does not run only in corporate applications. It runs in the production services a platform team ships, in the agents an MLOps team stands up on a virtual machine, and in the agent harnesses employees install on their laptops to get their own work done. A marketer using a desktop agent to draft campaign copy calls the same model providers and the same MCP servers as a production service. Every one of these calls needs the same things: identity on the request path, policy in front of model providers, governance over which MCP tools an agent can reach, and observability across all of it.
Solo Enterprise for agentgateway allows organizations to govern this traffic wherever agents, tools, models, and harnesses run, while centralizing operations through a Kubernetes-native control plane and data plane. Standalone mode brings these same capabilities in a self-contained form factor outside of Kubernetes. Teams download the binary or pull the container image, point it at their model providers and MCP servers, and connect it to the identity providers and observability backends they already operate. The same artifact runs on a well-provisioned host fronting an entire business, on a controller at a remote site with no platform team nearby, or on a developer's laptop.
Solo Enterprise for agentgateway gives teams five capabilities from a single deployment:
- Identity: full STS-backed token exchange, OAuth authorization flows, eager authorization, and interactive login driven from the management UI. Every call carries a verifiable identity, whether it is headed for a model or a tool, rather than a shared static key.
- Management: a full read-write UI to configure model providers, register MCP servers, define policy, and inspect traffic. Teams that operate from a console rather than a repository get the same control without editing configuration files.
- Governance: administrators set which model providers a caller can reach, whether that model is hosted internally or served by a frontier provider, and apply guardrails to those calls. MCP servers are handled as first-class backends, with search mode and code mode for tool discovery and invocation, so agents stay effective against large tool catalogs while administrators keep control of what is reachable.
- Cost: token budgeting, spend attribution, and cost control applied at the gateway. Every request is attributed to the model that served it and the identity that made it, so spend is visible where it happens rather than reconstructed from provider invoices later.
- Observability: traces across model calls and tool calls, exported to the backends an organization already runs.
Solo Enterprise for agentgateway builds on the open source agentgateway, an Agentic AI Foundation project written in Rust and purpose-built for agentic protocols with over 50 million image downloads and 500 contributors from a diverse range of organizations including Microsoft, Coinbase, Amazon, Adobe, and Okta.
The Solo.io agentic stack provides everything teams need to develop, deploy, and operate AI agents across agentic runtime environments. Powered by core open source projects created and contributed to the community by Solo.io, including:
- agentgateway, an Agentic AI Foundation project, is the high-performance data plane for agentic traffic, built from the ground up in Rust to span the full range of agentic protocols and use cases as a unified inference gateway, LLM gateway, MCP gateway, and A2A gateway.
- kagent, a CNCF Sandbox project, is the Kubernetes-native runtime that makes agents first-class workloads, with the security, observability, and lifecycle controls enterprises need to run programmatic, declarative, and always-on assistant patterns side-by-side.
- agentregistry, contributed to CNCF, is the trusted source for discovering, packaging, and distributing agents and tools across an organization with centralized observability, security, and governance across agent runtimes.
- agentdesktop is the open source governance layer for AI agents on the desktop, bringing inventory, managed configuration, non-human identity, and observability to the workstations where most enterprise agent activity actually happens.
- agentevals captures evaluation and quality signals using OpenTelemetry rather than in-process instrumentation, providing continuous, framework-agnostic visibility into how agents actually behave in production across the entire agentic loop.
To get started, please visit the Solo Enterprise for agentgateway documentation.
Media Contact
Solo.io Press Team media@solo.io
