# vas3k/TaxHacker

Self-hosted AI accounting app. LLM analyzer for receipts, invoices, transactions with custom prompts and categories

Repository: https://github.com/vas3k/TaxHacker
Canonical: https://ross.abutalabs.com/products/taxhacker
Homepage: https://taxhacker.app
Language: TypeScript
License: MIT
License Family: permissive
Topics: accounting, currency-exchange, llm, self-hosted, taxes, ai-analysis, expenses, invoices, gemini, ocr-recognition, ollama, openai
Last push: 2026-08-24T15:36:32+00:00

## Health v2 (maintenance only)
Score: 85/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 93, longevity 38
- inputs: {"age_days": 541, "days_push": 9, "days_rel": 44, "gap_med": 5.5, "n_releases_24m": 15}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6658, forks 1085 (observed 2026-08-28T04:09:47.453981+00:00)

## What it is
TaxHacker is a self-hosted AI-powered accounting app for freelancers, indie-hackers, and small businesses. It uses LLMs to OCR and analyze photos of receipts, invoices, and PDFs, extracting structured transaction data with automatic categorization, currency conversion, and custom AI prompts.

## Use cases
- scan receipts and extract data with AI
- parse invoices from pdfs into a database
- track expenses and income for tax filing
- convert foreign currency transactions using historical exchange rates
- generate invoices as pdf
- self-host an accounting app with local LLM
- auto-categorize transactions with custom prompts

## When to choose
- you're a freelancer or small business wanting automated expense tracking
- you want your financial data kept private via self-hosting
- you need OCR plus LLM extraction from receipts and invoices in any language
- you want customizable categories, projects, and AI extraction prompts

## When to avoid
- you need battle-tested, production-grade accounting software
- you require full double-entry bookkeeping or accountant-grade compliance features
- you don't want to manage your own hosting or LLM API keys
- you need guaranteed accuracy without manually verifying AI outputs

## Facets
- artifact type: application
- maturity: experimental
- function: ocr, nlp, llm-inference, data-science, analytics, pdf
- domain: fintech, developer-tools, self-hosted, artificial-intelligence
- platform: self-hosted
- tags: accounting, expense-tracking, receipt-scanning, invoice-generator, currency-conversion, freelancers, small-business, openai, gemini, ollama, natural-language-processing, web-server, docker, typescript

## Member repositories
- vas3k/TaxHacker (main) score 85

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:47.453981+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:43:02.878987+00:00, confidence not recorded.
  - readme: https://github.com/vas3k/TaxHacker (fetched 2026-08-28T04:09:47.453981+00:00, sha 71f04bc06b6a)
  - homepage: https://taxhacker.app (fetched 2026-08-29T08:39:37.456267+00:00, sha 81491b19b4e5)
  - site_page: https://taxhacker.app/docs/terms (fetched 2026-08-29T08:39:37.458819+00:00, sha c172f7a4079a)
  - site_page: https://taxhacker.app/docs/privacy_policy (fetched 2026-08-29T08:39:37.460606+00:00, sha dff3b48635e0)
  - site_page: https://taxhacker.app/docs/ai (fetched 2026-08-29T08:39:37.462233+00:00, sha 3add06fa5a6a)
  - site_page: https://taxhacker.app/docs/cookie (fetched 2026-08-29T08:39:37.463882+00:00, sha 25c2a156b65e)
- Data as of 2026-08-30T08:39:29.467469+00:00.