AI News HubLIVE
In-site rewrite5 min read

Show HN: PDF Insight – local-first AI that sorts your PDFs on-device

PDF Insight is a local-first AI tool that sorts and merges your PDFs entirely on your computer, ensuring privacy. Designed for accountants and self-employed users, it handles tax slips like T4 and RL-1, uses Ollama for AI and Tesseract for OCR locally. Offers a free trial and various pricing plans.

SourceHacker News AIAuthor: jacoblav

PDF Insight — Private Local AI Tax PDF Organizer (Mac/Win)

🔒 100% local — the data never leaves your computer

Got a messy folder of PDFs? Get back one clean, ordered file — nothing leaves your computer.

Drop a folder of receipts, statements and slips into PDF Insight. It reads each page, sorts and orders everything the way you ask, then hands back a single merged PDF. It all runs on your own computer.

✓ It sorts & merges client tax documents ✗ It is not tax-filing software — it doesn't do your taxes

Download the free trial See how it works

✓ 14-day free trial, no card ✓ No upload. No server. Nothing leaves your machine. ✓ French & English · macOS & Windows

Who it's for

Two kinds of people use PDF Insight. Pick the door that sounds like you.

For accountants & bookkeepers

Tax preparers, bookkeepers and firms handling client files

Sorts and merges a client's T4, T4A, T5, RL-1, RL-3 and RL-31 slips into one correctly-ordered file

Speaks Québec slip vocabulary in French and English, the way your clients' documents arrive

Client files stay on your machine, so there's no third-party cloud copy to breach

See the accountant workflow →

For everyone else

Self-employed, and anyone with a pile of PDFs to organize

Self-employed: turn a year of receipts and statements into one clean PDF to send your accountant

Legal bundles, patient records, closing packages, research files

No setup and no jargon: drop in a folder, say how you want it ordered, get one file back

See everyday uses →

From a messy folder to a signed-off PDF

Point it at a folder. Write your sorting rules once. PDF Insight reads and classifies every document, even scanned pages, orders them your way, lets you review, and exports one clean merged file. Nothing leaves your computer. Curious how it works? It's all under the hood, just below.

1

Drop in a client folder

2

It sorts & merges

3

One clean, ordered PDF

T4 — Employeur ABC.pdfEmploi

RL-1 — Revenus.pdfQuébec

RL-31 — Logement.pdfLogement

REER — Cotisation.pdfDéductions

→ client-merged.pdf (ready)✓

🧭 On the roadmap: a guided assistant that asks the right questions as you go, so nothing's missed in a client's return. Not in the app yet — the tool sorts and merges today.

How it works, under the hood

The plain version is above. Here's the technical detail, for anyone who wants it.

The local AI model runs via Ollama (free)

PDF Insight runs an open local language model on your own machine through Ollama, which is free to install. The model reads and classifies each document locally; no account, API key or internet connection is needed for the local tier.

On-device OCR for scans, via Tesseract (English & French)

Scanned and image-based pages are read with on-device OCR using Tesseract, in both English and French, so scanned slips are sorted and ordered just like native digital PDFs. The OCR runs entirely on your computer.

Nothing is uploaded, and it works offline

In the local tier, nothing is uploaded. No server, no cloud copy of your files. It works with no internet connection, so it keeps running on an air-gapped machine during tax season.

Optional, clearly-labelled paid cloud speed lane (Cerebras)

If you want near-instant processing, there is an optional, clearly-labelled paid cloud speed lane powered by Cerebras. It is off by default and billed separately; only when you turn it on do documents leave your machine.

Why local-first matters

Your clients' files never leave your computer. Not stored elsewhere — not stored at all.

TaxDome, SmartVault, Canopy and Dext lead with compliance badges precisely because client files sit in their cloud. Pasting documents into ChatGPT ships client SINs to a third party. PDF Insight reads, sorts and merges entirely on your machine — so there's no upload, no server, and no third-party copy to breach. It removes the risk instead of insuring it.

✗ Cloud document tools

Client files uploaded to someone else's servers. You're trusting their breach response.

✓ PDF Insight

The AI runs on your machine. Files are read locally and never transmitted. Nothing to breach.

Simple, honest pricing — pick what fits you.

Prices in CAD. 14-day free trial, no card required. Plans named for who you are, not for upsells.

🚀 Launch offer — first 100 customers: get the Founder Lifetime for $399 once, instead of subscribing. Same app, paid one time.

Solo

For one person organizing their own PDFs

$49 CAD, once

Pay once — perpetual for the current major version

Every local feature, on your own computer

No subscription, no account

Buy Solo — $49

Individual

For you — a solo preparer or personal use

$290 /year

One preparer, every feature

2 months free vs. paying monthly

About ⅓ of TaxDome — and data stays local

Subscribe yearly or $29/month →

BEST VALUE · FIRST 100

Founder Lifetime

Pay once, keep it forever — for early adopters

$399 once

Lifetime access, all future updates

Every feature, no seat limit for solo use

Priority support, founder badge

Buy lifetime — $399

No subscription. Best if you plan to keep using it.

Firm

For your team — multiple preparers

$25 /seat/mo

3+ seats, billed annually

Team admin & shared sorting rules

Onboarding help included

Talk to us — Firm

💡 At ~2 hours saved per client and 200 clients a season, $290/yr pays for itself on your very first client.

Handling client tax documents? See how the local-first architecture keeps files on your machine — nothing uploaded by default. Privacy & security →

Start free — 14-day trial

No credit card. Runs entirely on your computer — nothing to upload. macOS, Windows, and Linux.

Download for macOS Download for Windows Download for Linux

macOS — signed & notarized by Apple: just open it, no warnings. Windows — unsigned for now, so on first launch click “More info” → “Run anyway” (one time). Needs Ollama (free) for the local AI — setup link in the app.

Frequently asked questions

Tap a question to expand. Straight answers for accountants and bookkeepers evaluating a private, local document tool.

I'm self-employed and not techy — is this for me?

Yes. You don't set up anything. Drop your receipts and statements in a folder, type how you want them ordered, and get one clean PDF to send your accountant. Nothing is uploaded.

Is PDF Insight private — does it upload my clients' files anywhere?

No. In the default local tier, PDF Insight runs entirely on your own computer. Your clients' tax PDFs are read, classified and merged on-device and are never uploaded to any server. An optional, clearly-labelled paid cloud speed lane (powered by Cerebras) can be turned on for near-instant processing; only then do documents leave the machine. The local tier is the default — nothing leaves your machine when you use it.

Does PDF Insight work offline?

Yes. The local tier works fully offline. The AI model runs on-device through Ollama and the OCR runs on-device through Tesseract, so PDF Insight can organize and merge a client's documents with no internet connection. The licence check is offline-tolerant with a grace window, so it won't break on an air-gapped tax-season machine.

Which tax slips does PDF Insight support?

PDF Insight is built for Quebec and Canadian tax slips, including T4, T4A, T5, RL-1, RL-3, RL-31, RRSP/REER contribution receipts and FHSA documents. Because it uses a local LLM to read and classify documents, you can also write your own rules to handle any other document in a client's pile.

How do I merge a client's tax slips into one PDF?

Point PDF Insight at the client's folder, write your sorting rules once, and the local AI classifies and orders every slip the way you specified. You review the result and export a single merged, correctly-ordered PDF for that client. A real 11-document bundle is organized in about 100 seconds on a 16GB Mac.

Does PDF Insight do OCR on scanned documents?

Yes. PDF Insight reads scanned and image-based pages with on-device OCR using Tesseract, so scanned slips are classified and ordered just like native digital PDFs. The OCR runs locally and scanned pages are never sent to the cloud in the local tier.

Does PDF Insight run on both Mac and Windows?

Yes. PDF Insight is a desktop application that runs on both macOS and Windows. On a 16GB Mac it organizes a full client bundle in about 100 seconds entirely on-device.

How is PDF Insight different from TaxDome, SmartVault or Canopy?

TaxDome, SmartVault and Canopy are cloud document vaults that store your clients' files on their servers and charge per seat. PDF Insight is a local organizer that runs on your own machine and pre-sorts and merges the pile before it ever reaches a vault. Because nothing is uploaded in the local tier, there is no third-party copy of client data to breach. It also speaks Quebec slip vocabulary (T4, RL-1, RL-31) in French and English, which the US cloud tools do not.

How long does PDF Insight take to organize a client's documents?

A real 11-document client bundle is organized in about 100 seconds fully locally on a 16GB Mac. If you enable the optional paid cloud speed lane (Cerebras), the same work completes in roughly one second of compute.