Skip to main content
Cursor

​
Overview

This guide walks you through setting up the KumoSDK and Kumo Coding Agent in Cursor. It covers installation, authentication, agent setup, and a first prediction example.

​
Prerequisites

Make sure you have:
  1. Cursor installed and set up. See the official Cursor docs for installation.
  2. Python 3.10 to 3.13 installed
  3. Access to a KumoRFM environment, including an API key and any required API URL

​
Step 1: Create a Project

Create or open a project directory:
Open the folder in Cursor: File > Open Folder.

​
Step 2: Install KumoSDK

🖥 Terminal
Verify installation:

​
Step 3: Authenticate

Set your API key: 🖥 Terminal

​
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: 🖥 Terminal
Cursor reads .cursor/rules/ automatically. No extra configuration needed. Install the skills (optional): 🖥 Terminal

​
Step 5: Use the Kumo Coding Agent

Open the Cursor chat and try a real prediction:
The agent will inspect the data, build a graph, write PQL, and run the prediction end-to-end.

​
Step 6 (Optional): Upgrade

Upgrade KumoSDK: 🖥 Terminal
Upgrade the Kumo Coding Agent: 🖥 Terminal
To pin to a specific version:

​
Troubleshooting

​
kumoai cannot be imported

​
API key is missing

​
Agent does not respond with Kumo knowledge

  • Verify kumo-coding-agent/ exists in your project directory
  • Verify kumo-coding-agent/.cursor/rules/ contains kumo-coding-agent.mdc
  • Restart Cursor

​
Next Steps