Skip to main content
Claude

​
Overview

This guide walks you through setting up the KumoSDK and Kumo Coding Agent with Anthropic Claude Code in desktop and CLI environments. Claude Code is an AI coding agent by Anthropic. It can read your project files, write code, run commands, and iterate on errors. You interact with it by typing natural language prompts.

​
Prerequisites

Make sure you have:
  1. Python 3.10 to 3.13 installed
  2. A Kumo account and API key (Create)
  3. An Anthropic account
  4. Claude Code installed and authenticated. See the official Claude Code docs for desktop app and CLI installation.

​
Step 1: Create a Project

Create or open a project directory: 
mkdir my-kumo-project
cd my-kumo-project
Desktop app: Open Claude Code and select your project folder. CLI: Navigate to your project in the terminal.

​
Step 2: Install KumoSDK

pip install kumoai
Verify: 
python -c "import kumoai; print(f'kumoai {kumoai.__version__} installed')"

​
Step 3: Authenticate with Kumo

Set your API key: 
export KUMO_API_KEY="YOUR_API_KEY_HERE"    # from https://kumorfm.ai/api-keys

​
Step 4: Install Kumo Coding Agent

The 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: 
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
The second line tells Claude Code to read the agent’s knowledge base on startup. Install the skills (optional): 
npx skills add kumo-ai/kumo-coding-agent --agent claude-code

​
Step 5: Use the Kumo Coding Agent

Desktop app:
  1. Open Claude Code
  2. Select your project folder (if not already open)
  3. Type a prompt in the chat panel:
Load the RelBench F1 dataset and predict whether each driver will finish in the top 3 in the next race
  1. Claude Code will read the Kumo Coding Agent context, inspect the data, build a graph, write PQL, and run the prediction.
  2. Review the changes Claude proposes. You can approve, edit, or reject each change before it is applied.
CLI: Start an interactive session: 
cd my-kumo-project
claude
This opens an interactive prompt. Type your request: 
Load the RelBench F1 dataset and predict whether each driver will finish in the top 3 in the next race
You can also run a single prompt directly: 
claude "Load the RelBench F1 dataset and predict whether each driver will finish in the top 3 in the next race"

​
Step 6 (Optional): Upgrade

Upgrade KumoSDK: 
pip install --upgrade kumoai
Upgrade the Kumo Coding Agent: 
cd kumo-coding-agent && git pull
To pin to a specific version: 
cd kumo-coding-agent && git checkout v1.0.0

​
Troubleshooting

​
kumoai cannot be imported

pip install kumoai

​
API key is missing

export KUMO_API_KEY="YOUR_API_KEY_HERE"

​
Agent does not respond with Kumo knowledge

  • Verify kumo-coding-agent/ exists in your project directory
  • Verify your project’s CLAUDE.md contains the line referencing kumo-coding-agent/CLAUDE.md
  • Restart Claude Code or start a new session with claude

​
Claude Code CLI not found

npm install -g @anthropic-ai/claude-code

​
Next Steps