Skip to main content
1

Install the agent skills

These skills teach your agent how to write experiment logic, import data, operate the runner and viewer, manage their state, and much more. Just ask for what you want!
From a terminal:
To update the skills later, refresh the marketplace, update the plugin, and then restart Claude Code:
2

System prerequisites

Before continuing, make sure you have the following tools installed on your machine:
3

Start Postgres

fxtr keeps every job, result, and cache entry in Postgres. To run a local server in a container:
It listens on port 55433, with user, password, and database all named fxtr, so its URL is postgresql+asyncpg://fxtr:fxtr@localhost:55433/fxtr.

Run an example

To check your installation, you can create and run a complete greeting example:
1

Create the example project

This writes a uv project that depends on fxtr, with a complete greeting experiment in src/fxtr_example/experiment.py, a launch.py that runs it, and greeting renderers for the viewer. It also runs git init and prints the next steps.Install the example’s Python and renderer dependencies:
2

Connect it to the database

From the new project:
This writes fxtr.local.toml, which records where this machine reaches the database and is never committed, and creates the project’s tables.
3

Start the viewer

In a second terminal, from the project:
This serves the experiment viewer at http://127.0.0.1:8000/ and opens it in your browser.
4

Commit and launch the example

Every launch records the commit it runs, so commit first:
The included code greets three guests:
The viewer switches to the job, showing its graph: the guest list, the greet step mapped over it, and each greeting it produced.

What’s in the example project

[tool.fxtr] modules in pyproject.toml lists the modules that define your steps and workflows. When you add an experiment module, add it there too. Project configuration describes each setting and the files fxtr new writes. The renderers’ fxtr packages aren’t on npm: fxtr carries them, and views/vendor/fxtr/ is the project’s copy. Commit it. After upgrading fxtr, refresh it with uv run fxtr views vendor, then run pnpm install in views/ and rebuild.

Next steps

Your first experiment

Bring a question about language models, and run an experiment that answers it.

Core concepts

How projects, steps, workflows, jobs, and arrays fit together.