galculator-cu-python

Galculator Computer Use - Python

A Computer Use environment where Claude uses the Galculator GUI to solve math problems.

Running this example

Prerequisites:

• Docker
• taiga-local-tunnel installed and logged in (from the repo root: uv pip install -e local-tunnel/ && taiga-local-tunnel login)

Build the environment:

cd examples/galculator-cu-python
docker build --build-context taiga=../../ --platform linux/amd64 --build-arg APP_ENV=development -t galculator-cu-python -f Dockerfile .

Production build

The above command is ideal for development, as it doesn't bake the src files into the image. This allows the container to pick up new code more easily.

However for production you do want to include the src files in the image. To do this, run:

cd examples/galculator-cu-python
docker build --build-context taiga=../../ --platform linux/amd64 --build-arg APP_ENV=production -t galculator-cu-python -f Dockerfile .

Then start an interactive session against the hosted Taiga platform:

taiga-local-tunnel start \
  --image galculator-cu-python \
  --metadata-file problems-metadata.json \
  --problem-id factorial

This will open a browser where you can watch Claude solve the factorial problem using Galculator. The container is cleaned up automatically when you press Ctrl+C.

Available problems

• factorial - Compute 20! using the Galculator GUI

Viewing the desktop

To watch Claude interact with the GUI in real-time, you can use VNC (Virtual Network Computing) to view the container's desktop.

When the container is running, you can connect at localhost:6080