Skip to main content

Documentation Index

Fetch the complete documentation index at: https://runcrate.ai/docs/llms.txt

Use this file to discover all available pages before exploring further.

Get a GPU-backed Jupyter Lab environment running in under five minutes. Your AI agent deploys the instance, installs JupyterLab, and returns the access URL.

​
”Spin up a Jupyter Lab environment on an RTX 4090.”

The agent handles the full setup:
  1. list_gpu_types — confirms RTX 4090 availability ($0.35/hr)
  2. create_instance — deploys jupyter-dev with RTX 4090
  3. instance_status — polls until running
  4. ssh_execute — installs JupyterLab and common ML packages: 
    pip install jupyterlab torch torchvision numpy pandas matplotlib scikit-learn
  5. ssh_execute — starts JupyterLab with no-auth for quick access: 
    nohup jupyter lab --ip=0.0.0.0 --port=8888 --no-browser \
  --allow-root --NotebookApp.token='' \
  > /root/jupyter.log 2>&1 &
  6. get_instance — retrieves the public IP
JupyterLab is running at: 
http://203.0.113.87:8888
Specs: RTX 4090 (24 GB VRAM) | Cost: $0.35/hr Pre-installed packages: PyTorch, torchvision, NumPy, Pandas, Matplotlib, scikit-learn. Open the URL in your browser and start coding.
This setup uses no authentication token for convenience. For longer-running notebooks, set a token: --NotebookApp.token='your-secret'.

​
”Install some extra packages on my Jupyter instance — I need HuggingFace and Weights & Biases.”

The agent installs without interrupting the running server:
  1. ssh_execute — pip install transformers datasets accelerate wandb
  2. ssh_execute — python -c "import transformers; print(transformers.__version__)" to verify
Installed on jupyter-dev:
  • transformers 4.44.0
  • datasets 3.0.1
  • accelerate 0.34.0
  • wandb 0.18.0
All available in your running JupyterLab session. Restart the kernel if you had a notebook open.

​
”I’m done with the Jupyter instance. Download my notebook and shut it down.”

The agent saves your work and cleans up:
  1. ssh_execute — ls /root/*.ipynb /workspace/*.ipynb 2>/dev/null to find notebooks
  2. file_download — downloads /workspace/experiment.ipynb
  3. billing_usage — checks how much the session cost
  4. delete_instance — terminates jupyter-dev
Downloaded experiment.ipynb (142 KB). Session summary:
  • Duration: 3.5 hours
  • Cost: $1.23
  • GPU: RTX 4090
Instance jupyter-dev terminated. Billing stopped.

​
Tools used in this workflow

ToolPurpose
list_gpu_typesCheck GPU options and pricing
create_instance / instance_statusDeploy and wait for readiness
ssh_executeInstall JupyterLab, packages, start the server
get_instanceGet the public IP for the Jupyter URL
file_downloadSave notebooks before teardown
delete_instanceClean up when done