I made a free (open-source) extension, to use any LLM on Google sheet
Hello everyone, This past Saturday, I decided to make purchase on Cursor after hearing how good it is with Composer function that allow to generate code on fly, especially on Claude Sonnet (not an affiliate of the products, just curious!). To make the purchase worthwhile, I challenged myself to build a Google Sheets extension in just 24 hours that allows users to connect with any Language Model (LLM)—whether it’s ChatGPT, Claude, Groq, or Gemini. The Idea The idea was simple: a formula like =Claude(prompt, model) that lets users integrate AI anywhere in their sheets. The most impressive…
In plain words
AiSheeter is a free, open-source Google Sheets extension that lets users integrate any language model—including ChatGPT, Claude, Groq, and Gemini—directly into spreadsheets using simple formulas like =Claude(prompt, model). Built as a 24-hour challenge using Cursor and AI assistance, it enables spreadsheet users to leverage AI capabilities for data processing and analysis without leaving their sheets. The extension connects to multiple AI APIs and is available as an open-source tool.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hello everyone, This past Saturday, I decided to make purchase on Cursor after hearing how good it is with Composer function that allow to generate code on fly, especially on Claude Sonnet (not an affiliate of the products, just curious!). To make the purchase worthwhile, I challenged myself to build a Google Sheets extension in just 24 hours that allows users to connect with any Language Model (LLM)—whether it’s ChatGPT, Claude, Groq, or Gemini. The Idea The idea was simple: a formula like =Claude(prompt, model) that lets users integrate AI anywhere in their sheets. The most impressive part? 80% of the process was just tabbing and prompting AI, while only *20% was actual coding The Tech Stack Frontend: React with Next.js Backend: Node.js with Next.js API routes Database: Supabase AI Integration: OpenAI API, Anthropic API, Groq API, and Google AI API Development Assistance: Cursor and Claude Sonnet 3-5 The Journey Planning (2 hours): I started by using Claude Sonnet 3-5 to brainstorm and outline the project. It handled so much of the heavy lifting when it came to feature ideas and technical suggestions. Frontend Development (8 hours):With Cursor, I was literally tabbing through suggestions, and it felt more like _prompting_ AI to get the right code rather than writing it myself. Backend Development (6 hours): The same pattern applied here: I spent most of the time *tabbing through Cursor’s suggestions and tweaking AI prompts* for the backend, which helped me set up secure API endpoints and efficient database schemas. AI Integration (4 hours): This was the core part. I integrated multiple AI models to give users options. Claude helped refine the prompts and handle API responses with ease. Testing and Debugging (3 hours): Cursor and Claude once again made it feel like I was navigating through the process rather than writing tests from scratch. Their combined tools flagged issues quickly, cutting debugging time in half. Documentation and Deployment (1 hour): Drafted clear documentation with Claude’s help, and Cursor’s deployment features made production a breeze. Key Features AI in Google Sheets: Use AI directly with simple formulas. Multiple AI Models: Support for ChatGPT, Claude, Groq, Gemini, and more. - Cost Tracking: Automatic token calculation to track usage costs. - Security: Encrypted API key storage for peace of mind. Demo of the app : https://www.youtube.com/watch?v=HczW0F_tmvo Challenges & Solutions The biggest challenge was integrating multiple AI models seamlessly. But with *Claude Sonnet 3-5* guiding the architecture and *Cursor* suggesting solutions, the integration was mostly about *tabbing and prompting*. The architecture now easily accommodates different AI services. The extension is completely free at. : https://workspace.google.com/marketplace/app/aisheeter_smart... What’s Next I named the project AISheeter.com - Sheets Smarter not Harder I’m releasing it for free and open-sourcing the code [here](https://github.com/Ai-Quill/ai-sheet-frontend.git). This is just the start—let’s see where it goes from here! Website is at : https://www.aisheeter.com/ Takeaway What stood out the most throughout this project was how much *AI could take over the coding process*. It was 80% navigating through suggestions and refining prompts, and only 20% traditional coding. With the right tools and mindset, it feels like the boundaries of what’s possible in such a short time are expanding. Excited time ahead with AI !
Does a similar job
all alternatives →
ChatGPT for Google SheetsMay 2026 · workspace.google.com · ▲119Chat with your spreadsheet, edit cell with natural language
- AMAdding Mistral Codestral and GPT-4o to Jupyter Notebooks2024 · github.com · ▲269
Hey HN! We’ve forked Jupyter Lab and added AI code generation features that feel native and have all the context about your notebook. You can see a demo video (2 min) here: https://www.tella.tv/video/clxt7ei4v00rr09i5gt1laop6/view Try a hosted version here: https://pretzelai.app Jupyter is by far the most used Data Science tool. Despite its popularity, it still lacks good code-generation extensions. The flagship AI extension jupyter-ai lags far behind in features and UX compared to modern AI code generation and understanding tools (like…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 18d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 19d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 28d ago · cactuscompute.com
Launched alongside, October 2024
the whole month →
Softr for Notion▲925Turn Notion databases into portals & apps with no code
Dev tools · 2024 · softr.io
One inbox for all your work discussions
Work · 2024 · generalcollaboration.com