Introduction

Cadenya is a headless agent runtime for building and managing AI agents that use tools to accomplish tasks. You define what an agent can do, how it should behave, and then let it execute work on your behalf.

Core concepts

Cadenya is built around three core concepts:

• Tool Sets — Collections of tools that give agents capabilities. Connect to MCP servers or HTTP endpoints, and Cadenya syncs the available tools automatically.
• Agents — Define how an AI executes work. Each agent has one or more variations — configurations with a system prompt, model, and assigned tools.
• Objectives — Execution instances where an agent works on a task. You provide an initial message, and the agent reasons through the problem, calling tools as needed.

These concepts compose naturally: you create tool sets to define capabilities, wire them into agents that define behavior, and run objectives to execute work.

Get started

Follow the Getting Started guide to create your first tool set, configure an agent, and run an objective.

Or dive into the individual concept guides:

• Tool Sets — How to organize and manage tools
• Agents — How to define agent behavior
• Objectives — How to execute and monitor agent work

API Reference

The API Reference provides complete SDK documentation for all endpoints, generated automatically from the Cadenya API specification. SDK examples are available in TypeScript and Go.