返回资讯中心
外部精选
软件工程
#开发者实时流

Agentgateway – One high-performance gateway for service, LLM, and MCP traffic

One high-performance gateway for service, LLM, and MCP traffic.

Hacker News 最新cgeier2026/10/18 · 2026/10/1830 分钟阅读

以下正文同步自 Hacker News 最新,版权归原站所有,已转换为易读排版。

Standalone Kubernetes

Models Blog Enterprise Community

Light

Dark

System

Get Started

GitHub

Light

Dark

System

Docs Standalone Kubernetes Models Blog Enterprise Community

@agentgatewayGet Started GitHub

One high-performance gateway for service, LLM, and MCP traffic.

An open source HTTP and gRPC gateway that handles traditional application traffic and AI-native protocols in one data plane. Route, secure, observe, and govern services, LLM provider traffic, MCP tools, and agent-to-agent communication without stitching together separate gateways.

See it in action

View on GitHub

Discord

Install the agentgateway binary

$ curl -sL https://agentgateway.dev/install | bash

Copy

LLM Gateway

Route to OpenAI, Claude, Gemini, or any self-hosted model with credentialing and failover.

Native protocol support for Model Context Protocol and agent-to-agent traffic.

APIs & Services

HTTP, gRPC, and TCP traffic — observable by default with mTLS and OIDC built in.

CLI / IDEAI agentsApps & clientsLLM GatewayMCP / A2AAPIs & ServicesTraffic ManagementLLM GatewayInference RoutingMCP / A2A gatewayagentgatewayREQUEST · INBOUNDROUTE·SECURE·OBSERVE·GOVERN·COSTRESPONSE · OUTBOUND

Swipe to explore →

One control plane for service traffic, LLM routing, MCP, A2A, and inference — with the policy, observability, and cost controls that a platform team actually trusts.

One data plane for HTTP, gRPC, and TCP services, every major LLM provider, self-hosted inference, and the MCP and A2A protocols your agents speak.

Run any north–south or east–west traffic through a single binary. Zero-config TLS, OIDC, mTLS-rotation, native Envoy compatibility for those who want it.

Drop-in OpenAI-compatible API in front of OpenAI, Anthropic, Bedrock, Gemini, Vertex, and OSS Llama runs — with token budgets, semantic caching, and prompt redaction.

Latency-aware, cost-aware, model-aware routing for self-hosted inference. Plug-in vLLM, TGI, Triton; agentgateway picks the warmest replica.

Treat MCP servers like microservices: discover them, sign and scope every tool call, and keep an audit trail of what agents invoked.

Route agent-to-agent invocations between LangChain, CrewAI, ADK, and your own runtime, with identity and tracing on every hop.

Try a route before you ship it: pick a model, send a prompt from the admin UI, and see which backend actually served the request.

Authenticate, authorize, and redact on every hop — not just at the edge.

The policy layer itself: what attaches where, how rules merge, and how a decision is reached on every hop — with tamper-evident audit logs.

Validate JWTs at the edge and pull claims into routing and authorization decisions, or hand off a full OIDC login flow for browser traffic.

Issue and rotate API keys per consumer, or fall back to basic auth for internal tooling that cannot speak OIDC.

Delegate the allow/deny call to your own service over gRPC or HTTP, so existing entitlement logic stays where it already lives.

Express allow/deny rules over method, path, headers, and JWT claims — evaluated per hop, on both HTTP and network listeners.

Authenticate callers into MCP servers and scope which tools each identity may invoke, so an agent cannot reach past its mandate.

Terminate TLS at the listener and originate verified TLS or mTLS to every backend, with certificate rotation handled for you.

Browser-facing protections for gateways that serve web apps directly: origin allow-lists and CSRF token enforcement.

Local and global rate limits keyed on any request attribute, to blunt abuse and protect backends from a runaway agent loop.

Know exactly what happened on every request, and debug it without a restart.

OpenTelemetry by default. Token-usage histograms on Prometheus, traces in Jaeger, and request logs with status, latency, and token counts — each carrying the realized USD cost.

See what a proxy actually loaded, without a restart. proxy trace taps live requests into an interactive terminal view, proxy config dumps runtime state, and log levels change on the fly.

Fire test prompts at a provider straight from the admin UI and watch routing, policy, and token accounting play out on a real request.

Decide what each caller may invoke, inspect what flows through, and know how overlapping rules resolve.

Decide which tools on which MCP targets a caller may reach, and rewrite or restrict what the server exposes downstream.

Inspect tool calls and responses in flight, blocking prompt injection and unsafe payloads before they reach an agent or a server.

Pattern and model-based checks on LLM prompts and completions, with redaction for anything that should never leave your estate.

Where a policy binds — gateway, listener, route, or backend — and how overlapping rules merge into one decision per request.

Attribute, price, and cap what your agents spend.

Spend control in three stages: attribute it, price it, then enforce it — before the invoice is the first place you find out.

Hard caps per key or team: cut off token consumption and dollar spend once a limit is hit, rather than alerting after the fact.

Issue scoped keys per team, app, or user so every request carries an owner — the unit that budgets and reports attach to.

Spend, token usage, and traffic in the admin UI, grouped by model, provider, and user, so you can see where the money went.

Per-model input and output pricing, so each request carries a realized USD cost that logs, metrics, traces, and policies can all read.

The realized cost of every call, attached to logs, metrics, and traces — with catalog coverage reported so gaps do not hide.

Standalone

Kubernetes

Deploy to Render

Quick start

Get started with agentgateway in less than 5 minutes — local-first.

Connect agentgateway to MCP servers with built-in discovery and auth.

Deployment options

Binary, Docker, or Kubernetes — pick what fits your stack.

Hands-on lab: LLM cost management

Free, on-demand lab — monitor LLM usage, apply consumption controls, and optimize costs with agentgateway.

Calling all agent-curious tool-builders, platform engineers, and AI enthusiasts — come help shape the future of agentic connectivity.

Discord

GitHub

"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."

"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."

"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."

"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."

"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."

"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."

"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."

"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."

An open source HTTP and gRPC gateway that handles traditional application traffic and AI-native protocols in one data plane. Route, secure, observe, and govern services, LLM provider traffic, MCP tools, and agent-to-agent communication without stitching together separate gateways.

Ask AI Agentgateway assistant

0" class="flex items-center justify-center w-8 h-8 bg-transparent border-none rounded-lg text-gray-500 cursor-pointer transition-all duration-150 hover:bg-gray-200 hover:text-gray-900 dark:hover:bg-gray-700 dark:hover:text-gray-50" aria-label="Export conversation" title="Export as Markdown">

Ask me anything about agentgateway configuration, features, or usage.

Note: AI-generated content might contain errors; please verify and test all returned information.

Tip: one topic per conversation gives the best results. Use the + button in the chat header to start a new conversation.

• • •

Rate limit reached

The assistant keeps a rolling history of 3 exchanges. Any older messages are no longer included in the context.

Switching topics? Starting a new conversation improves accuracy. Start new conversation

0" x-transition.duration.150ms class="px-3 pt-2.5 pb-0 flex flex-wrap gap-1.5">= 3 ? 'Exceeds the 3-page limit — this page will not be sent as context.' : ''" class="inline-flex items-center gap-1.5 max-w-full px-2 py-1 border rounded-lg text-xs font-medium">

0" x-transition:enter="transition ease-out duration-100" x-transition:enter-start="opacity-0 -translate-y-1" x-transition:enter-end="opacity-100 translate-y-0" x-transition:leave="transition ease-in duration-75" x-transition:leave-start="opacity-100 translate-y-0" x-transition:leave-end="opacity-0 -translate-y-1" class="chatbot-mention-menu absolute bottom-full left-0 right-0 mb-1 mx-2 bg-white dark:bg-gray-800 border border-gray-200 dark:border-gray-700 rounded-xl shadow-lg z-20 overflow-hidden"> Current page

↑↓ navigate ↵ select esc dismiss

0 ? 'text-violet-600 dark:text-violet-400 bg-violet-50 dark:bg-violet-500/10' : 'text-gray-400 dark:text-gray-500 hover:text-gray-600 dark:hover:text-gray-300 hover:bg-gray-100 dark:hover:bg-gray-700'" class="flex items-center justify-center w-8 h-8 bg-transparent border-none rounded-lg cursor-pointer transition-all duration-150" a

正文由 探How 从来源站点 RSS 同步,内容未经改写;遇到排版缺失或需要图片、视频时请以原文为准。

打开原文
去社区讨论 →