LedgerLocal - your receipts never leave your laptop

A developer built LedgerLocal, an open-source CLI that uses a local vision model to extract vendor, date, tax and total from a freelancer's invoices and receipts, categorise them against user-defined rules, file them into a year/quarter/category tree, and export an accountant-ready CSV without any network access. The tool installs a process-wide socket allowlist so that connections to external APIs raise an OfflineViolation while localhost model servers remain reachable, and it audits each extraction with arithmetic checks — catching a misread $65.09 as $65.00 in the demo. The project is Apache-2.0 licensed, spans roughly 3,600 lines with 89 tests, and requires no GPU.

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle https://dev.to/challenges/hacktoberfest-week2-2026-10-12 LedgerLocal — a CLI that turns a freelancer's folder of invoices and receipts into a sorted, accountant-ready archive, entirely on their own laptop. Point it at a folder: it reads each document with a local vision model, extracts vendor / date / tax / currency / total, categorises it against rules you control, files it into a year/quarter/category tree, and exports the CSV your accountant asks for. Who pays: freelancers and one-person studios with 300 unsorted receipts and a lost weekend every tax season. Plenty of SaaS does this — all of it wants the documents uploaded. Receipts name your clients, expose your rates, and carry card digits and tax IDs. For consultants under NDA or anyone under data-residency rules, uploading isn't a price question, it's a non-starter. Their real choice is local tool vs. the weekend . The best part isn't extraction, it's distrust: every document is audited after the model answers. In the demo the model misreads $65.09 as $65.00 and the tool catches it from the arithmetic — nobody told it to look. Sort a year of invoices and receipts into a clean, accountant-ready archive — on your own laptop, with an open-weight model, with no network access at all. Point it at the folder where your receipts pile up. It reads each one with a local vision model, pulls out vendor, date, tax and total, categorises it against rules you control, files it into a sane folder tree, and exports the CSV your accountant actually wants. bash $ ledgerlocal ingest ~/Downloads/receipts read hetzner-feb.pdf read coffee-with-northwind.jpg read adobe-jan.pdf read legal-invoice.pdf 2026-02-14 Hetzner Online GmbH 32.73 EUR hosting 2026-04-03 Blue Fox Coffee 11.77 EUR meals 2026-01-07 Adobe Inc. 65.00 USD software review 2026-03-02 Bright Path Legal LLP 990.00 USD professional fees 4 ingested, 0 already known, 0 failed, 1 need review $ ledgerlocal review 1 document s the pipeline is not confident about: 2026-01-07 Adobe Inc. 65.00 USD · subtotal + tax differs from total … "1.234,56 €" is Decimal "1234.56" . Small models are good at finding, unreliable at formatting. urllib against localhost. When the pitch is "audit this yourself," a 40-package tree undermines it. SQLite keyed on content hash re-running a folder is a no-op . ~3,600 lines, 89 tests, no GPU or network needed. Apache-2.0: github.com/Pager-dot/ledgerlocal The headline feature is one a closed API cannot ship. Rather than ask users to trust a privacy policy, I removed the capability. Every command installs a process-wide socket allowlist first: socket.create connection "api.openai.com", 443 OfflineViolation socket.create connection "127.0.0.1", 11434 fine — that's your model A hosted version can't implement this , because the egress it blocks is the call the product depends on. Not a cheaper substitute — a product that otherwise can't exist. Unmetered inference changed the engineering, not just the bill. The repair pass runs on every uncertain document; on a metered API you'd ration that. recategorise replays three years of documents against new rules in under a second with zero model calls — there's a test asserting the provider is never touched. With per-document pricing you simply don't change your mind, and the rule system dies unused. Swappability is leverage you keep. A 3B on battery, a 32B at year-end, a LoRA fine-tuned on one client's bizarre invoice layout. With a closed API that last one is a feature request to a vendor who'll never prioritise it. Where closed wins, honestly: a frontier model reads a crumpled thermal receipt better than a 7B. I closed most of that gap with structure instead of scale — constrained decoding, deterministic parsing, arithmetic audits — and surfaced the rest in a review queue. The discipline a small model forced made a better product, because a frontier model would have tempted me to skip the checks.