Plano: The AI-Native Proxy Server for Agentic Apps
Plano is an AI-native proxy server and data plane for agentic apps: smart LLM routing, agent orchestration, observability, and guardrails built on Envoy.
🚀 Want to deploy Plano yourself?
Docker configs, system requirements, and installation guides — all on one page.
View Plano Tool Page →What is Plano?
Plano is an AI-native proxy server and data plane built for agentic applications. While agent demos are easy to build, shipping them to production is hard: you end up writing "hidden middleware" for routing, guardrails, observability, and model-provider quirks. Plano pulls that rote plumbing into a single, out-of-process data plane built on Envoy, so you stay focused on your agents' core logic.
Key Capabilities
| Capability | What it does |
|---|---|
| 🚦 Agent Orchestration | Low-latency routing between agents — add new agents without modifying app code. |
| 🔗 Smart LLM Routing | Route by model name, semantic alias, or automatic provider preferences for model agility. |
| 🕵️ Agentic Signals™ | Zero-code capture of agent signals plus OTEL traces and metrics across every agent. |
| 🛡️ Guardrail Filter Chains | Jailbreak protection, moderation policies, and memory hooks applied consistently. |
Why Teams Choose Plano
Plano is framework-agnostic — use any language or AI framework, and it works as a drop-in OpenAI-compatible router or a full agentic gateway. It is built by core contributors of Envoy, who built critical infrastructure at scale, and is backed by industry-leading LLM research at Katanemo.
🚀 Want to deploy Plano yourself?
Docker configs, system requirements, and installation guides — all on one page.
View Plano Tool Page →