LedgerLocal

A lightweight, 100% offline invoice and receipt parser for freelancers. Runs on your own machine with Ollama. Zero cloud calls, zero monthly subscriptions.

Every tax season or quarter-end, freelancers and consultants go through the exact same headache: a folder full of random PDF invoices, Uber receipts, client coffee stubs, and software bills.

The existing tools usually fall into two traps:

1. Expensive SaaS subscriptions ($25-$40/mo): Bloated accounting platforms you only touch four times a year.
2. Privacy risks: Most "smart" parsers upload your documents to a cloud server. If your invoices contain client NDAs, project descriptions, or card slips, sending them to an unvetted third party is a dealbreaker.

LedgerLocal runs locally on your machine using open-weight models (powered by Google's gemma2:2b, with support for phi4-mini and llama3.2-vision) through Ollama.

• 100% Offline: Works without an internet connection.
• Zero API Bills: Process 10 or 1,000 receipts without paying per-token charges.
• Privacy by Default: Files never leave localhost.
• Editable Dashboard: Interactive web UI allows instant verification and edits before exporting to CSV for your accountant.

1. Python 3.10+
2. Ollama installed & running:

   ollama pull gemma2:2b

git clone https://github.com/alessiobianchini/ledgerlocal.git
cd ledgerlocal

pip install -r requirements.txt

python run.py

Open http://localhost:8000 in your browser. Drag & drop your receipts into the window.

If you prefer working from the terminal:

# Process all files in a folder
python cli.py import ./sample_data

# View your expense ledger
python cli.py list

# View summary stats by category and currency
python cli.py stats

# Export to CSV
python cli.py export -o expenses.csv

LedgerLocal includes a native Render Blueprint (render.yaml) to host the web interface:

1. Fork or push this repository to GitHub.
2. Go to dashboard.render.com and click New + → Blueprint.
3. Select your repository. Render will automatically detect render.yaml and deploy the service.

Transactions are automatically classified into standard expense categories:

• Software & Subscriptions
• Hosting & Cloud Infrastructure
• Hardware & Office Supplies
• Travel & Transportation
• Meals & Client Entertainment
• Professional & Legal Services
• Marketing & Advertising
• Utilities & Internet
• Other

MIT License. Built for the Hacktoberfest 2026 Open-Source AI Challenge.