Skip to main content
Get a GPU-backed Jupyter Lab environment running in a few minutes. Your AI agent deploys the instance, installs JupyterLab, and tells you how to open it.

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

The agent handles the full setup:
  1. list_gpu_types: confirms RTX 4090 availability and its live hourly rate
  2. create_instance: deploys jupyter-dev with RTX 4090
  3. instance_status: polls until running
  4. ssh_execute: installs JupyterLab and common ML packages:
  5. ssh_execute: starts JupyterLab on the instance’s loopback address, with a token:
  6. ssh_execute: sleep 5; jupyter server list to read the address and its token
JupyterLab is running on jupyter-dev. It only listens inside the instance, so open it through an SSH tunnel. Run this on your computer and leave it open:
Then open:
Specs: RTX 4090 (24 GB VRAM), billed by the second on most GPUs while running Pre-installed packages: PyTorch, torchvision, NumPy, Pandas, Matplotlib, scikit-learn.
JupyterLab listens on 127.0.0.1 and asks for its token, so nobody on the internet can reach it. The tunnel uses the Runcrate CLI. If the instance has your own SSH key, add -N -L 8888:localhost:8888 to the SSH command on its page instead.

”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
  • GPU: RTX 4090 (the exact charge is in billing_usage)
Instance jupyter-dev terminated. Billing stopped.

Tools used in this workflow