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 Agent2026

Provides a lightweight Python harness that turns LLMs into working agents with tool-use, skills, persistent memory, permission controls and multi-agent coordination. Ships with a CLI/React TUI, 43+ built-in tools, a plugin/skill system and the ohmo personal-agent for chat gateways. Best for developers prototyping agent workflows and multi-agent experiments.

GitHub
AI Model2026

Runs the Bonsai family of quantized LLMs locally (including vision-capable 27B): provides scripts and demo UIs to run 1-bit and ternary Bonsai models on macOS (Metal), Linux/Windows (CUDA/Vulkan/ROCm), or CPU, with long context, tool-calling and an optional Open WebUI agent demo.

GitHub
AI Client2025

Turns Chromium into a local-first AI browser with an embedded assistant that can summarise pages, extract structured data, automate web tasks, and run scheduled agents. Built as an open-source Chromium fork with 53+ built-in browser tools, 40+ app integrations, and support for BYO AI keys or fully local models (Ollama / LM Studio).