kilolonion

kilolonion / excelmanus

Public

ExcelManus - AI-powered Excel Agent

24
0
100% credibility
Found Feb 26, 2026 at 19 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

An AI-powered agent for manipulating Excel spreadsheets using natural language, handling reading, writing formulas, data analysis, charting, and multi-sheet operations through CLI, web UI, or API.

How It Works

1
📖 Discover ExcelManus

You hear about a friendly helper that lets you talk to your Excel files like chatting with a smart friend.

2
🛠️ Get it ready

Download and set it up on your computer in just a few minutes, no tech skills needed.

3
🔗 Link your AI helper

Connect a smart AI service so it can understand and work with your spreadsheets.

4
💬 Start chatting

Open your Excel file and describe what you want in plain words, like 'sum the sales in column A' or 'make a chart by region'.

5
✨ Watch the magic

See it read data, add formulas, run analysis, or create charts right in your file, step by step.

6
Pick your view
💻
Desktop view

Chat alongside your Excel for real-time edits and previews.

📱
Mobile chat

Talk on your phone and get clear updates on what changed.

🎉 Excel tasks done effortlessly

Your spreadsheets are now supercharged – analysis, charts, and fixes happen by conversation, saving you hours.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 19 to 24 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is excelmanus?

ExcelManus is a Python-based, AI-powered agent that lets you manipulate Excel files through natural language commands—like summing columns, generating charts, or running data analysis on sales spreadsheets. Upload a file, chat via CLI (`excelmanus`), Web UI, or REST API endpoints like `/api/v1/chat/stream`, and it handles reads, writes, formulas, pivots, even image-to-table extraction. It solves the drudgery of manual Excel tinkering by turning vague queries into precise actions across multiple sheets.

Why is it gaining traction?

It stands out with built-in safety like operation approvals (`/accept`), version rollback (`/undo`), and Docker sandboxing, plus persistent memory that remembers your style across sessions. Multi-LLM support (OpenAI, Claude, Gemini) auto-detects providers, and extensible "skillpacks" let you add domain-specific prompts via Markdown files. Developers dig the bench framework for testing agent performance on custom suites.

Who should use this?

Data analysts grinding through Excel reports, finance teams automating VLOOKUPs and charts, or spreadsheet-heavy ops folks needing quick audits. Python scripters building AI wrappers for non-technical users, or teams prototyping agentic workflows without starting from scratch.

Verdict

Promising early-stage tool with solid docs, Docker Compose deploys, and MIT license, but only 17 stars and 1.0% credibility signal it's raw—test thoroughly via the bench suite before production. Worth a spin for Excel-heavy AI experiments.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.