Edit Notebooks Locally in Cursor, Run on Colab GPUs via the Colab Plugin

Melvin Vivas · X post · 2026-08-18 · Open on X

Topics: AI Dev Tools & Productivity, Programming & ML Foundations · Level: beginner

Summary

Shows a workflow where you install the Google Colab plugin in Cursor. You edit notebook code locally in Cursor but run it on a Colab GPU instance, so you get both a local AI-assisted editor and free cloud GPUs.

Key points

• Install the Colab plugin inside the Cursor editor
• Write and edit notebook code locally in Cursor
• Run the code on a Google Colab GPU instance
• Useful for ML work when your own machine has no GPU

Resources mentioned

• Cursor · tool · x.com · free · recommended by both Bashiri Smith & Melvin Vivas
  AI-native code editor (VS Code with AI built in).
  Also in: GLM 5.3 and GLM 5.3 Flash now in Cursor (Melvin Vivas on X · notes), Grok Bot Can Now Hand Off Coding Tasks to Cursor (Melvin Vivas on X · notes), Why Plan Mode Still Matters in AI Coding Assistants (Codex, Claude, Cursor) (Melvin Vivas on X · notes), Why Plan Mode Still Matters in AI Coding Agents (Codex, Claude, Cursor) (Melvin Vivas on X · notes) and 121 more
• Google Colab · tool · colab.research.google.com · free · recommended by both Bashiri Smith & Melvin Vivas
  Free GPU notebooks.
  Also in: Run Notebooks on a Free GPU with Google Colab (T4, 15GB VRAM) (Melvin Vivas on X · notes), Run Local Models on a Free GPU with Google Colab (T4) (Melvin Vivas on X · notes), Free Colab Notebooks for Local Model Fine-Tuning and Inference (Melvin Vivas on X · notes), Intent classification for support using GLiNER2.5-Decide notebook (Melvin Vivas on X · notes) and 12 more
• Colab plugin for Cursor · tool · github.com · free
  Editor extension that connects local notebooks to Google Colab runtimes.

Try this

• Install the Colab plugin in Cursor
• Edit notebooks locally and run them on a Colab GPU runtime