I Built a Local AI Finance Coach for My Friend's Bubble-Tea Shop - No Cloud, No API Keys

A developer built Finance Friend, a fully local AI finance coach that turns a small business's Excel/CSV bank statement into a plain-language report without any cloud service or API keys. The tool uses pandas to auto-detect date, description, income and expense columns and produce a compact JSON summary, then runs Qwen2.5-3B-Instruct via llama.cpp on the user's own machine to generate a 250-350 word business report in English or Chinese. The developer says the design keeps sensitive financial data such as income, rent, supplier payments and staff wages from ever leaving the laptop.

This is built for a friend - a small business owner who runs a bubble-tea shop. Every month she exports her bank statement to reconcile her books, and every month it's the same wall of numbers: hundreds of rows of transactions, no structure she can act on. She asks the same question in three different ways - "Is the shop actually making money? Where does it all go? What should I do differently?" Her bank statement is also exactly the kind of file she should never upload to some AI service. It's her income, her rent, her suppliers, her staff wages. A closed API would mean shipping all of that to someone else's server. So I built Finance Friend for exactly this person: upload an Excel/CSV export, and a small open-weight model running on her own machine writes a plain-language report - where the money comes from, where it goes, and what to watch. No cloud. No API keys. No data leaving the laptop. bank statement xlsx / xls / csv | v analyzer.py -- pandas, on this machine | auto-detects date / description / income / expense columns | monthly income & expenses, net flow | top income sources, top expense categories, biggest transactions | compact JSON summary v reporter.py -- llama.cpp, on this machine | Qwen2.5-3B-Instruct open weights, GGUF | 250-350 word plain-language business report v Gradio UI - overview table, monthly table, AI report The parser is forgiving on purpose - Chinese and English bank exports name their columns differently, so it matches common names loosely Chinese exports use columns like income/expense in Chinese, which the same matcher handles : IN KEYS = "income", "deposit", "credit" OUT KEYS = "expense", "withdrawal", "debit" def pick columns df, keys : cols = { norm c : c for c in df.columns} for k in keys: if norm k in cols: return cols norm k fall back to substring matching ... The report generator is just a chat completion against a local llama.cpp model: python from llama cpp import Llama llm = Llama model path="qwen2.5-3b-q4.gguf", n ctx=8192, n threads=8 report = llm.create chat completion messages= {"role": "system", "content": SYSTEM PROMPT}, {"role": "user", "content": prompt}, the compact JSON summary , temperature=0.3, "choices" 0 "message" "content" That's the whole AI surface. One model file, one local process, zero network calls. Feed it three months of a bubble-tea shop's transactions and it produces a report like this I asked it for English here; for her, the same model writes in Chinese - the language is part of the prompt : In the period from July 1 to September 28, 2026, this small bubble-tea shop is profitable overall, with a net surplus of 6,536.07 yuan. Revenue comes mainly from in-store WeChat payments and Alipay takeout orders, which together make up most of income, and both are trending upward month over month. Spending is dominated by dairy suppliers and staff wages. Rent and utilities also stand out as large monthly costs. Overall, income exceeds spending and revenue is growing, but rent and utilities deserve attention. Recommendation: negotiate with suppliers to lower purchase costs, and review whether the current rent and utility terms can be improved. Which is exactly the answer to her three questions: yes, it's profitable; the money goes to dairy and staff; negotiate with suppliers and review rent. This is the "Build for a Friend" challenge, and the friend is real - a small business owner, exactly the person I have in mind at every design decision. The demo data is synthetic on purpose : even a demo shouldn't run on anyone's real financial data, which is the product philosophy in a nutshell. Next step: hand the app to her, tune the report to how she actually reads it, and let her real statements run only on her own machine - never anywhere else. Repo: github.com/fengyuGbt/finance-friend https://github.com/fengyuGbt/finance-friend python3 -m venv .venv && source .venv/bin/activate pip install llama-cpp-python pandas openpyxl gradio curl -L -o qwen2.5-3b-q4.gguf \ https://hf-mirror.com/Qwen/Qwen2.5-3B-Instruct-GGUF/resolve/main/qwen2.5-3b-instruct-q4 k m.gguf python app.py - http://127.0.0.1:7860 Want a demo file without using your own data? python sample data.py generates a synthetic three-month statement. Built with open-source AI at its core: an Apache-2.0 open-weight model, running locally through llama.cpp - because for this friend, privacy isn't a feature, it's the whole product.