Agent Gateway
agentgateway/agentgateway
Proxy agentico unificado para roteamento seguro de LLMs, MCPs e agentes
Ver no GitHubProxy open source nativo de IA que oferece conectividade, segurança e governança para comunicação entre agentes, LLMs e ferramentas usando protocolos MCP e A2A. Fornece roteamento inteligente, guardrails, observabilidade e controle de custos em um único ponto de entrada.
Instalação
npx convez-ai agentgateway/agentgateway1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.
Métricas
Casos de uso
- Roteamento centralizado de requisições LLM com fallover e controle de orçamento
- Federação de ferramentas e integração de dados via MCP com múltiplos transportes
- Comunicação segura entre agentes autônomos com descoberta de capacidades
- Filtragem de conteúdo e auditoria de inferências com políticas CEL customizáveis
- Roteamento inteligente para modelos self-hosted baseado em utilização de GPU
Veredito

Solução robusta e bem-arquitetada para governança de infraestrutura agentica em produção. Implementação em Rust com suporte a múltiplos protocolos (MCP, A2A, OpenAI-compatible) torna-a adequada para equipes que precisam de controle fino e observabilidade em ambientes multi-agente complexos.
README
A tradução para o português deste README ainda está na fila.
Agentgateway is an open source proxy built on AI-native protocols (MCP & A2A) that provides drop-in security, observability, and governance for agent-to-LLM, agent-to-tool, and agent-to-agent communication across any framework and environment.
Intro to Agentgateway Video
Key Features
-
LLM Gateway Route traffic to major LLM providers (OpenAI, Anthropic, Gemini, Bedrock, and more) through a unified OpenAI-compatible API with budget and spend controls, prompt enrichment, load balancing, and failover.
-
MCP Gateway Connect LLMs to tools and external data sources via MCP with tool federation, stdio/HTTP/SSE/Streamable HTTP transports, OpenAPI integration, and OAuth authentication.
-
A2A Gateway Enable secure agent-to-agent communication using A2A, with capability discovery, modality negotiation, and task collaboration.
-
Inference Routing Intelligent routing to self-hosted models using Kubernetes Inference Gateway extensions, with decisions based on GPU utilization, KV cache, LoRA adapters, and queue depth.
-
Guardrails Multi-layered content filtering with regex, OpenAI moderation, AWS Bedrock Guardrails, Google Model Armor, and custom webhooks.
-
Security & Observability Auth (JWT, API keys, OAuth), fine-grained RBAC with CEL policy engine, rate limiting, TLS, and OpenTelemetry metrics/logs/tracing.
Getting Started
- Standalone Quickstart — Get started with agentgateway in minutes.
- Kubernetes Quickstart — Deploy on Kubernetes using the built-in controller and Gateway API.
Documentation
Depending on your deployment environment, check out the following docs:
- agentgateway.dev/docs: For standalone deployments such as local or on-prem. These docs are for this upstream
agentgateway/agentgatewayGitHub project. - agentgateway.dev/docs/kubernetes/latest: For Kubernetes-based deployments using the built-in Kubernetes controller and Gateway API support.
Agentgateway has a built-in UI for you to explore agentgateway connecting agent-to-agent or agent-to-tool:
Sponsors
Thank you to our sponsors for helping to fund the development of agentgateway!
Contributing
For instructions on how to contribute to the agentgateway project, see the CONTRIBUTION.md file.
Community Meetings
To join a community meeting, add the agentgateway calendar to your Google account. Then, you can find event details on the calendar.
Recordings of the community meetings will be published on our google drive.
Roadmap
agentgateway is currently in active development. If you'd like a feature that's missing, open an issue in our GitHub repo.
Contributors
Thanks to all contributors who are helping to make agentgateway better.
