Logo
Deploy Now

Categories

Self-Hosted DevOps API Gateway Reverse Proxy AI Gateway Agent Infrastructure MCP Proxy LLM Router

Stars

4,476

Forks

752

Watchers

33

Developer links

Last Updated: 08-22-2026 12:36 PM (UTC)

Agent Gateway

Backed by the Linux Foundation with contributions from AWS, Cisco, IBM, Microsoft, Red Hat, and Shell, Agentgateway is the first data plane built from the ground up for AI agent workloads — providing a unified Rust-based proxy that handles conventional HTTP and gRPC traffic alongside MCP tool servers, A2A agent communication, and LLM inference endpoints through a single deployment. The LLM gateway routes requests to OpenAI, Anthropic, Gemini, AWS Bedrock, and other providers through an OpenAI-compatible unified API with per-tenant budget controls, spend tracking, prompt enrichment, load balancing across multiple model endpoints, and automatic failover when providers experience outages. The MCP gateway federates multiple tool servers behind one endpoint, supporting stdio, HTTP/SSE, and Streamable HTTP transports with built-in OAuth authentication compliant with the MCP auth specification, integrating Auth0 and Keycloak out of the box. OpenAPI integration exposes existing REST APIs as MCP-native tools without code changes, enabling legacy services to participate in agent workflows. Policy-based RBAC controls which agents access which tools, while OpenTelemetry integration provides distributed tracing across agent communication chains. Deploy as a standalone binary with flat YAML configuration or on Kubernetes using the built-in controller with Gateway API support for declarative infrastructure-as-code management. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache 2.0 licensed.

Agent Gateway
Agent Gateway

Benefits

  • Unified AI and API Gateway
  • Single Rust binary handles traditional HTTP/gRPC routing alongside MCP tool servers, A2A agents, and LLM inference endpoints without operating separate infrastructure stacks.
  • Enterprise LLM Cost Governance
  • Per-tenant budget controls, spend tracking, prompt enrichment, and automatic failover across multiple LLM providers prevent cost overruns and service disruptions.
  • Linux Foundation Backed Security
  • Policy-based RBAC, OAuth authentication for MCP servers, TLS termination, and rate limiting with contributions validated by AWS, IBM, Microsoft, and Red Hat engineers.
  • Native Agent Protocol Support
  • First-class implementation of MCP tool federation with OAuth authentication and Google A2A agent-to-agent protocol with OpenTelemetry distributed tracing across communication chains.

Features

  • LLM Routing Gateway
  • Routes to OpenAI, Anthropic, Gemini, and Bedrock through unified OpenAI-compatible API with load balancing, failover, and budget controls.
  • MCP Tool Federation
  • Federates multiple MCP servers behind one endpoint with stdio, HTTP/SSE, and Streamable HTTP transports plus OAuth authentication.
  • OpenAPI-to-MCP Bridge
  • Automatically exposes existing REST APIs as MCP-native tools without code modification, bridging legacy services into agent workflows.
  • Policy-Based Access Control
  • RBAC policies define which agents access which tools, LLM endpoints, and peer agents with per-route authorization rules.
  • Kubernetes Gateway API
  • Built-in Kubernetes controller implements Gateway API for declarative infrastructure-as-code deployment and policy management at scale.