getcellm/cellm

Use LLMs in Excel formulas

Cellm – AI‑powered Excel formulas

What it is – Cellm is an Excel add‑in that lets you call large language models (LLMs) directly from worksheet cells with a =PROMPT() function. The function works like any native Excel formula: you pass a prompt (or a prompt plus a range of cells) and the model returns its answer into the cell. It can call hosted APIs (OpenAI, Anthropic, Azure, etc.) or local models via Ollama, Llamafile, vLLM, etc.

Why it matters – It turns the spreadsheet—a tool that virtually every business user already knows—into an AI‑augmented workbench. Repetitive data‑cleaning, classification, extraction, translation, summarisation, or competitive‑monitoring tasks that would otherwise require copy‑pasting into a chat window can be run on thousands of rows in seconds.

How to get started

  1. Install the MSI from the Releases page (requires Windows 10+, .NET 9.0 Runtime, and desktop Excel 2010+).
  2. Open Excel, pick a provider from the new Cellm tab, and enter your API key (or select Ollama for a local model).
  3. Use the formula, e.g. =PROMPT("Extract all person names mentioned in the text", A1) and drag‑fill to apply it to a whole column.

Key features

  • =PROMPT() works with single cells, ranges (A1:F10) or multiple ranges.
  • Supports function‑calling and advanced configuration (see the online docs).
  • Telemetry is optional and can be disabled via a JSON config file.
  • Free tier for local models or personal API keys; paid tiers for managed infrastructure and EU‑compliant data processing.

Typical use cases

Domain Example
Competitive monitoring Pull headlines from a list of competitor URLs, translate them, and auto‑categorise.
Multi‑language analysis Extract sentiment or entities from customer feedback in dozens of languages.
Text classification Tag survey responses, support tickets, or research abstracts.
Model comparison Run the same prompt against several LLMs side‑by‑side in the sheet.
Data cleaning Standardise names, dates, or formatting across large CSV imports.
Summarisation Condense articles, papers, or reports directly in the workbook.

Documentation & support – Full user guide, prompting tips, and developer instructions are hosted at https://docs.getcellm.com. The repo also contains the source code (C#/.NET) and a CI badge showing automated tests.

License – Fair Core License 1.0 (a permissive license with Apache 2.0‑style terms).

Cellm lets anyone who knows Excel start using LLMs without writing code, turning spreadsheets into fast, AI‑driven data pipelines.

Related

  • Project
    tmustier/pi-for-excel

    Pi for Excel is an open‑source Office add‑in that embeds a conversational AI agent inside Microsoft Excel. The agent can read, write, format, and analyse spreadsheets using any LLM you configure, offering 16 built‑in spreadsheet tools, session management, automatic checkpoints for one‑click rollback, and extensible sandboxed extensions.

  • Project
    cyberchitta/llm-context.py

    A context curation tool that enables AI coding agents to automatically identify, pack, and manage the specific files and code excerpts needed for a task to avoid token limits and missing information.

  • Project
    alexzhang13/rlm

    An inference engine and training environment for Recursive Language Models (RLMs) that enable LLMs to handle near-infinite context by programmatically decomposing tasks via recursive sub-calls in a REPL environment.

  • Project
    chr15m/runprompt

    A command-line tool to execute .prompt files, allowing users to treat LLM prompts as versionable artifacts and automate AI workflows via the shell.

  • Project
    theJayTea/WritingTools

    Writing Tools is a free, open‑source desktop app for Windows, Linux and macOS that lets you invoke an LLM anywhere on your computer with a hot‑key. It can proofread, rewrite, change tone, translate, summarise web pages or YouTube transcripts, and even chat with the model. You can use cloud APIs (Gemini, OpenAI, Anthropic, etc.) or run local models via Ollama, llama.cpp or Apple‑silicon MLX. The app is privacy‑focused (no telemetry, local storage of API keys) and licensed under GPL‑v3.