jupyter-live-kernel

Use a live Jupyter kernel via the jupyter_live_kernel.py script's execute command, which keeps variables, imports, and objects alive across calls. Point it at a notebook path with an active kernel session and pass code with the --code flag.

Use a live kernel for iterative exploration, data science work, and building state incrementally across steps. Use one-shot execution for stateless scripts that need tool access like web search or file operations, and the terminal for shell commands and installs.

Run the variables subcommand with the notebook path to list all live variables, or add preview with a variable name to inspect a specific object's contents. Always include the --compact flag to reduce verbose JSON output.

The kernel needs time to initialize after the server starts, so the first execution may exceed the 30-second default timeout. Retry the command, or pass a larger value such as --timeout 120 for setup and heavy computation.

The kernel uses JupyterLab's Python environment, so packages must be installed into that environment before use. Install them into the JupyterLab tool environment first, then they become importable in kernel executions.