ALPHA SOFTWARE: Unpage is experimental, under heavy development, and may be unstable. Use at your own risk!

Intro

Unpage is an agent builder and infrastructure knowledge graph builder that makes infrastructure context available via MCP server, enabling you to build LLM-powered applications that query and execute on your infrastructure safely and intelligently. At the end of this guide, you will have Unpage set up to run locally with built-in integrations and tools, a knowledge graph, and your first infrastructure-aware agent.

Installation

Prerequisites

  • Python 3.12 or higher
  • uv package manager
  • API keys for your LLM and alerting, infrastructure, and observability tools. Learn more in Plugins.

Install Unpage

Unpage is designed to be run using uv:
uvx unpage -h

Quickstart

To get started, run:
uvx unpage agent quickstart
This will get you up and running with your first agent, which will automatically investigate and add context to alerts from PagerDuty (or your preferred alerting provider). You will also have a chance to set up your infrastructure knowledge graph to provide your agent with more context. The quickstart flow will walk you through:
  • Configuring your LLM, PagerDuty plugin, and logs and metrics plugins
  • Creating your first agent and prompt
  • Testing your agent with an existing incident ticket
  • Building your knowledge graph

Running the Agent

Once you’re happy with the results of your agent, you can automate the agent’s actions for new incidents with:
uvx unpage agent serve
<placeholder for Frank>

Maintenance

Update Configuration

If you need to add or update plugins or API keys, you can update your configuration with:
uvx unpage configure

Update the Knowledge Graph

To refresh your knowledge graph to give your agent up-to-date information, run:
uvx unpage graph build -h

Add More Context

Your agent’s responses will improve with more context about your infrastructure, which can be provided via the knowledge graph or custom scripts. To provide your agents with more context in addition to the knowledge graph, see Shell Commands.

Create Agents

See Agents to learn more about how to create and edit your agents and prompts.