AIAny
AI Client2025
Icon for item

TaxHacker

Extracts and structures data from receipts, invoices and transaction documents using configurable LLM prompts for a self-hosted accounting workflow. Offers multi-currency (including crypto) historical conversion, custom fields/prompts, batch processing and Docker-based deployment for local data control.

Introduction

Most expense-tracking tools force you to choose between cloud convenience and data control. TaxHacker aims to keep your financial documents local while letting modern LLMs handle the messy work of recognition, parsing and categorization — useful when you need privacy, custom extraction rules, or industry-specific fields that off-the-shelf services miss.

What Sets It Apart
  • LLM-driven extraction with fully editable prompts: instead of a fixed OCR-to-field pipeline, you can write or tweak system and field prompts so the same document type can yield different structured outputs (e.g., invoice numbers, project codes, tax breakdowns). This makes it easier to adapt to country- or industry-specific formats without changing core code.
  • Historical, multi-currency conversion (including crypto): detected currencies are converted to your base currency using the exchange rate from the transaction date, which simplifies financial reporting across time and avoids manual corrections for FX differences.
  • Self-hosted, Docker-first design: the project provides images and compose files to run on your infrastructure, preserving document ownership and allowing integration with your existing Postgres instance and backup policies.
Who It's For — and Where to Be Cautious

Great fit if you are a freelancer, indie hacker, or small business operator who needs local control over receipts and invoices, wants to customize extraction behavior via prompts, and can tolerate some setup and operational maintenance. It’s particularly useful when you must extract non-standard or domain-specific fields (project codes, regulatory IDs) that commercial services miss.

Look elsewhere if you want a zero-maintenance, fully managed SaaS with guaranteed SLAs, or if you cannot accept the variable costs of invoking commercial LLMs for large document volumes. Also note the project was early-stage at the time of repository creation: expect occasional bugs, a need for manual verification of parsed results, and ongoing changes to prompts and provider integrations.

Where It Fits

TaxHacker sits between basic OCR tools and enterprise accounting suites: it is not an accountant-in-a-box but a customizable pipeline for turning heterogeneous documents into a structured dataset you can search, filter, export and feed to your reporting tools. Compared to cloud-only expense apps, its main trade-off is operational responsibility in exchange for data ownership and prompt-level customization.

Information

  • Websitegithub.com
  • Authorsvas3k
  • Published date2025/03/10

Categories

More Items

GitHub
AI Client2026

Aggregates multiple free public market endpoints into a self‑hosted, terminal‑style web trading workspace: live quotes, candlesticks, screener, options, crypto, portfolio tracking and an optional Claude AI assistant. No paid API keys and automatic provider fallbacks.

GitHub
AI Infra2026

Compresses tool outputs, logs, files and RAG chunks locally before they reach the LLM to reduce token usage while caching originals for on-demand retrieval. Provides proxy/library/wrap modes, JSON- and code-aware compressors, and reversible compression.

GitHub
AI Client2026

Operate DeepSeek Harness from an interactive terminal with streaming replies, tool cards, session controls and live context metrics. Also offers experimental Claude and Codex backends behind the same interface.