Decorative header graphic for the VS Code and Jupyter setup guide

Jupyter in VS Code + Kumo Coding Agent

Overview

This guide walks you through setting up the KumoSDK and Kumo Coding Agent for use with the KumoRFM Pre-Trained model in Jupyter notebooks inside VS Code. This guide assumes minimal prior experience with Jupyter, VS Code, and coding agents. Experienced users may skip directly to relevant sections.

Prerequisites

Make sure you have:

VS Code installed (Download)
Python installed at the system level
A Kumo account and API key (Create)
VS Code Extensions
- Python (by Microsoft)
- Jupyter Extension Pack (by Microsoft)

You may also need:

OpenAI or Anthropic subscription (recommended - required for use with Kumo Coding Agent)
- OpenAI Codex (Subscribe)
- Anthropic Claude Code (Subscribe)
Homebrew (macOS package manager) (Install)
GitHub CLI installed and authenticated (required for installing coding agent skills):

🖥 Terminal

brew install gh     # install via Homebrew
gh auth status      # check if authenticated
gh auth login       # authenticate

Part 1: Setup for Jupyter in VS Code + KumoSDK

Step 1: Create or Open a Jupyter Notebook

To create a new notebook:

Open the Command Palette (Cmd + Shift + P)
Search for Create: New Jupyter Notebook
Save the notebook (e.g., kumo_notebook.ipynb)

Click Select Kernel in the top-right of the notebook, then select or create a new Python virtual environment.

Environment type: Venv (recommended) or Conda (if the Anaconda distribution is installed)
Select a Python version between 3.10 and 3.13

Once complete, ensure the selected kernel appears in the top-right of the notebook.

A project-specific interpreter keeps KumoSDK and notebook dependencies separate from your system Python and from unrelated projects.

Step 2: Install KumoSDK

Install the KumoSDK inside the notebook kernel: 📓 Notebook cell

%pip install kumoai

Using %pip instead of !pip ensures the package installs into the active notebook kernel.

Verify installation: 📓 Notebook cell

import kumoai.experimental.rfm as rfm

print("Kumo SDK loaded successfully")

Step 3: Authenticate KumoSDK

You will need an API key to make calls to KumoRFM. There are two common approaches:

Use the interactive code block below to set KUMO_API_KEY from the notebook
Use the KumoRFM website and set KUMO_API_KEY manually

** Interactive authentication: ** 📓 Notebook cell

import os
import kumoai.experimental.rfm as rfm

if not os.environ.get("KUMO_API_KEY"):
    rfm.authenticate()

rfm.init(api_key=os.environ.get("KUMO_API_KEY"))

** Manual authentication: ** 📓 Notebook cell

import os
import kumoai.experimental.rfm as rfm

os.environ["KUMO_API_KEY"] = "YOUR_API_KEY_HERE"  # from  https://kumorfm.ai/api-keys
rfm.init(api_key=os.environ.get("KUMO_API_KEY"))

Step 4: Optional Dependencies

Install Graphviz:

The KumoSDK allows you to define and visualize a Kumo Graph, which represents data tables and the relationships between them. To enable Kumo Graph visualization with KumoSDK, the Graphviz library must be installed correctly. Installation requires:

dot — an executable that is part of the Graphviz library, installed at the system level
The graphviz Python package installed in the notebook kernel

Check if dot is installed: 📓 Notebook cell

import shutil
print(shutil.which("dot"))

If this returns None, install Graphviz: 🖥 Terminal

brew install graphviz

Install the Python package: 📓 Notebook cell

%pip install graphviz

Test that a simple graph renders: 📓 Notebook cell

from graphviz import Digraph

g = Digraph()
g.edge("Hello", "Kumo")
g

Install Jinja2:

The KumoSDK requires Jinja2, a Python library used to style displayed outputs. 📓 Notebook cell

%pip show Jinja2   # check if Jinja2 is installed
%pip install jinja2  # install

Part 2: Add a Coding Agent (Optional)

Choose one of the following to add an AI coding agent to your workflow:

Flow A — OpenAI Codex
Flow B — Anthropic Claude Code

Step 1: Install Extension

Open VS Code Extensions (Cmd + Shift + X)
Search for “Codex – OpenAI’s coding agent”
Install the extension

Authenticate:

Sign in with ChatGPT (recommended)
Or configure ~/.codex/config.toml

Open Codex Chat using:

The ChatGPT icon in the top-right corner added by the plugin

Reload VS Code if the extension does not appear.

Step 2: Install the Jupyter-Notebook skillA Codex skill is a reusable set of instructions and resources that teaches Codex how to carry out a coding workflow consistently. In this case, you will add the Jupyter Notebook skill so Codex can create and modify Jupyter cells.To check which skills are already available, run the following in Codex:🤖 Codex

/skills

If the Jupyter Notebook skill is installed, you should see listed:

jupyter-notebook: create/scaffold/edit Jupyter notebooks

To install the skill, run:🤖 Codex

wrap-code

$skill-installer install https://github.com/openai/skills/tree/main/skills/.curated/jupyter-notebook

Ensure GitHub CLI is installed and authenticated before running the skill installer. See prerequisites.

Step 3: Verify Codex is Working in JupyterOpen the Codex panel and run:🤖 Codex

Create a new cell in rfmsetup.ipynb and plot a sine wave

Expected behavior:

The Codex agent can now modify files and notebooks, but you must still execute notebook cells manually.

Step 4: Install Kumo Coding AgentThe Kumo Coding Agent has two parts:

Context (knowledge base): Documentation, PQL rules, workflow guides, and data connector references that teach the agent how to use the Kumo platform. Installed by cloning the repository.
Skills (slash commands): Actions like /kumo-issue and /kumo-pr for reporting bugs and contributing fixes. Installed via the skill installer.

Install the context:🖥 Terminal

cd your-project
git clone https://github.com/kumo-ai/kumo-coding-agent.git kumo-coding-agent

This action adds a directory named kumo-coding-agent to your project. It contains the Kumo Coding Agent’s knowledge base. Confirm that this directory appears in your project.Codex reads AGENTS.md automatically. No extra configuration needed.Install the skills (optional). Inside a Codex session:🤖 Codex

$skill-installer install https://github.com/kumo-ai/kumo-coding-agent

Step 5: Use the Kumo Coding AgentTry a real prediction:🤖 Codex

wrap-code

Use the active VS Code notebook with the kumo-coding-agent skill to load the RelBench F1 dataset and use KumoRFM to predict whether each driver will finish in the top 3 in their next race.

The agent will inspect the data, build a graph, and write PQL. You can then run the notebook end-to-end. If needed, authenticate the KumoSDK within the notebook before running the prediction.

Placeholder image for the Codex end-to-end prediction workflow

Before asking Codex to modify the notebook, save your changes first. If the notebook is not saved, VS Code may keep your unsaved version as the active notebook view and treat Codex’s edits as the previous file version. If you do not see Codex’s changes, try one of the following:

Use the “Revert File” option in VS Code to refresh the notebook (Cmd + Shift + P -> Revert File)
Close the notebook tab and reopen it

You are now fully set up with KumoSDK and the Kumo Coding Agent. You can proceed to:

the Kumo Coding Agent Quick Start for coding agent examples
the Kumo SDK Quick Start to get familiar with core SDK functionality

Step 6 (Optional): UpgradeUpgrade the KumoSDK:📓 Notebook cell

%pip install --upgrade kumoai

Upgrade the Kumo Coding Agent:🖥 Terminal

cd kumo-coding-agent && git pull

To pin to a specific version:

cd kumo-coding-agent && git checkout v1.0.0

Step 1: Install Extension

Open VS Code Extensions (Cmd + Shift + X)
Search for “Claude Code” (by Anthropic)
Install the extension

Authenticate:

Open Claude Code using either:

The Anthropic spark icon in the sidebar
The Anthropic spark icon in the top-right corner
Cmd + Shift + P -> Claude Code: Open

Reload VS Code if the extension does not appear.

Step 2: Install Kumo Coding AgentThe Kumo Coding Agent has two parts:

Context (knowledge base): Documentation, PQL rules, workflow guides, and data connector references that teach the agent how to use the Kumo platform. Installed by cloning the repository.
Skills (slash commands): Actions like /kumo-issue and /kumo-pr for reporting bugs and contributing fixes. Installed via npx skills add.

Install the context:🖥 Terminal

cd your-project
git clone https://github.com/kumo-ai/kumo-coding-agent.git kumo-coding-agent
echo 'Also read kumo-coding-agent/CLAUDE.md for Kumo agent capabilities.' >> CLAUDE.md

This action adds a directory named kumo-coding-agent to your project. It contains the Kumo Coding Agent’s knowledge base. Confirm that this directory appears in your project.The second line tells Claude Code to read the agent’s knowledge base on startup.Install the skills (optional):To run the following command you will need node.js installed on your system🖥 Terminal

npx skills add kumo-ai/kumo-coding-agent --agent claude-code

Step 3: Use the Kumo Coding AgentTry a real prediction:✨ Claude

wrap-code

Use the active VS Code notebook with the kumo-coding-agent skill to load the RelBench F1 dataset and use KumoRFM to predict whether each driver will finish in the top 3 in their next race.

The agent will inspect the data, build a graph, and write PQL. You can then run the notebook end-to-end. If needed, authenticate the KumoSDK within the notebook before running the prediction.

Placeholder image for the Claude Code end-to-end prediction workflow

Before asking Claude to modify the notebook, save your changes first. If the notebook is not saved, VS Code may keep your unsaved version as the active notebook view and treat Claude’s edits as the previous file version. If you do not see Claude’s changes, try one of the following:

Use the “Revert File” option in VS Code to refresh the notebook (Cmd + Shift + P -> Revert File)
Close the notebook tab and reopen it

You are now fully set up with KumoSDK and the Kumo Coding Agent. You can proceed to:

the Kumo Coding Agent Quick Start for coding agent examples
the Kumo SDK Quick Start to get familiar with core SDK functionality

Step 4 (Optional): UpgradeUpgrade KumoSDK:📓 Notebook cell

%pip install --upgrade kumoai

Upgrade the Kumo Coding Agent:🖥 Terminal

cd kumo-coding-agent && git pull

To pin to a specific version:

cd kumo-coding-agent && git checkout v1.0.0

Troubleshooting

Notebook does not run

Ensure the Jupyter extension is installed
Ensure a kernel is selected
Ensure Python version is 3.10–3.13

Kernel does not appear

Restart VS Code
Reopen the notebook
Install ipykernel

Wrong Python environment

Re-select the kernel from Python Environments

`kumoai` cannot be imported

📓 Notebook cell

%pip install kumoai

Restart the kernel after installation.

API key is missing

📓 Notebook cell

import os
os.environ["KUMO_API_KEY"] = "YOUR_API_KEY_HERE"

Next Steps

Setup for SDK fundamentals
Make Predictions for PQL query reference
Kumo Coding Agent for agent source and skills

Get Started

KumoRFM SDK

KumoRFM Fine-Tuning SDK

KumoRFM Fine-Tuning Platform

Jupyter in VS Code

Jupyter in VS Code + Kumo Coding Agent

Overview

Prerequisites

Part 1: Setup for Jupyter in VS Code + KumoSDK

Step 1: Create or Open a Jupyter Notebook

Step 2: Install KumoSDK

Step 3: Authenticate KumoSDK

Step 4: Optional Dependencies

Install Graphviz:

Install Jinja2:

Part 2: Add a Coding Agent (Optional)

Troubleshooting

Notebook does not run

Kernel does not appear

Wrong Python environment

`kumoai` cannot be imported

API key is missing

Next Steps

Get Started

KumoRFM SDK

KumoRFM Fine-Tuning SDK

KumoRFM Fine-Tuning Platform

​Jupyter in VS Code + Kumo Coding Agent

​Overview

​Prerequisites

​Part 1: Setup for Jupyter in VS Code + KumoSDK

​Step 1: Create or Open a Jupyter Notebook

​Step 2: Install KumoSDK

​Step 3: Authenticate KumoSDK

​Step 4: Optional Dependencies

​Install Graphviz:

​Install Jinja2:

​Part 2: Add a Coding Agent (Optional)

​Troubleshooting

​Notebook does not run

​Kernel does not appear

​Wrong Python environment

​kumoai cannot be imported

​API key is missing

​Next Steps

Jupyter in VS Code + Kumo Coding Agent

Overview

Prerequisites

Part 1: Setup for Jupyter in VS Code + KumoSDK

Step 1: Create or Open a Jupyter Notebook

Step 2: Install KumoSDK

Step 3: Authenticate KumoSDK

Step 4: Optional Dependencies

Install Graphviz:

Install Jinja2:

Part 2: Add a Coding Agent (Optional)

Troubleshooting

Notebook does not run

Kernel does not appear

Wrong Python environment

`kumoai` cannot be imported

API key is missing

Next Steps