Cayu documentation
Cayu is an open-source Python framework for building and running domain-specific long-horizon agents, with a durable runtime built in.
Assemble your harness from model providers, tools, context, knowledge, memory and verification. The integrated runtime executes the agent with durable sessions, explicit authority and recorded progress.
These docs cover the latest Cayu release, on Python 3.11 and newer. Start with the generated project, then add the capabilities your job needs. Cayu Cloud is optional.
The path from an idea to an operated app
Section titled “The path from an idea to an operated app”- Define the job. State the input, expected output and evidence that proves completion.
- Generate and verify. Use
cayu new; preserve the factory, tests and evals as you change behavior. - Build the harness. Add prompts, tools, context, policies and domain code only where the job requires them.
- Evaluate. Check both the result and the recorded path to it.
- Operate. Select stores, process roles, authentication and recovery policy for your deployment.
Find the right kind of documentation
Section titled “Find the right kind of documentation”| You want to… | Start here |
|---|---|
| Install and make a first run | Get started |
| Understand the framework’s pieces | Concepts |
| Add a particular capability | Build agents |
| Test an agent and compare changes | Evaluate |
| Deploy and inspect ongoing work | Operate |
| Follow a complete example | Recipes or the dining walkthrough |
| Find exact arguments and behavior | Reference |
Documentation for your installed version
Section titled “Documentation for your installed version”The API and package guides on this site are generated from the latest public release, named in the release manifest. Run cayu --version to compare it with your project. The installed cayu guide commands provide version-matched local guidance; use them when your project is on another release. Read the release and upgrade guide before changing a persisted application.
The documentation map lists the supported learning paths and their verification evidence. The machine-readable index helps coding agents discover the same canonical pages.