plano

Overview of plano

What it is

Plano is an AI-native proxy server and data plane for agentic applications. It centralizes common delivery concerns such as LLM routing, observability, agent orchestration, and guardrails, allowing developers to focus on core agent logic. The project is backed by LLM research and built on Envoy by its core contributors.

Key features

• Orchestration: Low-latency orchestration between agents; new agents can be added without modifying application code.
• Model Agility: Route by model name, alias (semantic names) or automatically via preferences.
• Agentic Signals™: Zero-code capture of signals plus OpenTelemetry traces and metrics across every agent.
• Moderation & Memory Hooks: Build jailbreak protection, add moderation policies, and implement memory consistently via Filter Chains.

Use cases

Plano is suitable for productionizing multi-agent workflows, managing LLM routing across multiple providers, adding guardrails and moderation to agent interactions, and capturing observability signals for continuous improvement. It is designed for teams building agentic applications who want to avoid building the “hidden middleware” needed to go from demo to production.

Getting started

See the repository README for prerequisites and detailed setup instructions. The following command starts Plano with a YAML configuration:```bashplanoai up config.yaml``````

License and pricing

The project is open source under the Apache-2.0 license. Plano and the Plano family of LLMs are hosted free of charge in the US-central region for development. For production scaling, users can run these LLMs locally or contact the project on Discord for API keys.

Based on the project's public README and repository metadata.