
TaxHacker
Automatic AI analyzer for receipts, invoices, transactions, etc
Stars: 230

README:

I'm a small self-hosted accountant app that can help you deal with invoices, receipts and taxes with power of GenAI.
Share TaxHacker
TaxHacker is a self-hosted accounting app for freelancers and small businesses who want to save time and automate expences and income tracking with power of GenAI. It can recognise uploaded photos, receipts or PDFs and extract important data (e.g. name, total amount, date, merchant, VAT) and save it as structured transactions to a table. You can also create your own custom fields to extract with your LLM prompts.
It supports automatic currency conversion on a day of transaction. Even for crypto!
Built-in system of filters, support for multiple projects, import-export of transactions for a certain time (along with attached files) and custom categories, allows you to simplify reporting and tax filing.
[!IMPORTANT]
This project is still at a very early stage. Use it at your own risk! Star Us to receive notifications about new bugfixes and features from GitHub ⭐️
https://github.com/user-attachments/assets/3326d0e3-0bf6-4c39-9e00-4bf0983d9b7a
Take a photo on upload or a PDF and TaxHacker will automatically recognise, categorise and store transaction information.
- Upload multiple documents and store in "unsorted" until you get the time to sort them out by hand or with an AI
- Use LLM to extract key information like date, amount, and vendor
- Automatically categorize transactions based on its content
- Store everything in a structured format for easy filtering and retrieval
- Organize your documents by a tax season
TaxHacker recognizes a wide variety of documents including store receipts, restaurant bills, invoices, bank checks, letters, even handwritten receipts.
TaxHacker automatically converts foreign currencies and even knows the historical exchange rates on the invoice date.
- Automatically detect currency in your documents
- Convert it to your base currency
- Historical exchange rate lookup for past transactions
- Support for over 170 world currencies and 14 popular cryptocurrencies (BTC, ETC, LTC, DOT, etc)!
You can customize LLM Prompts for built-in fields, categories, and projects, as well as modify global templates in the application settings. This allows to customize the quality of recognizing specific things to your specific use-cases.
- General prompt template is configurable is settings
- Create custom extraction rules for your specific needs
- Adjust field extraction priorities and naming conventions
- Fine-tune the AI for your industry-specific documents
The whole extraction process is under your contoll all the time!
Adapt TaxHacker to your specific tracking needs. You can create new fields, projects or categories to extract additional information from documents. For example, if you need to save emails, addresses, and any custom information into separate fields, you can do it. Custom fields will be available when exporting too.
- Create unlimited custom fields for transaction tracking
- Automatically extract custom field data using AI
- Include custom fields in exports and reports
- Create new categories or projects to organise your transactions and filter by them
Once all documents have been uploaded and analyzed, you can view, filter and export your transaction history.
- Filter transactions by time, category, and other features
- Use full-text search by recognized document content
- Export filtered transactions to CSV with attached documents
- Upload your entire income and expense history at the end of the year for your tax advisor to analyze
TaxHacker can be self-hosted on your own infrastructure for complete control over your data and application environment. We provide a Docker image and Docker Compose files that makes setting up TaxHacker simple:
curl -O https://raw.githubusercontent.com/vas3k/TaxHacker/main/docker-compose.yml
docker compose up
The Docker Compose setup includes:
- TaxHacker application container
- PostgreSQL 17 database container
- Automatic database migrations
- Volume mounts for persistent data storage
New docker image is automatically built and published on every new release. You can use specific version tags (e.g. v1.0.0
) or latest
for the most recent version.
For more advanced setups, you can adapt Docker Compose configuration to your own needs. The default configuration uses the pre-built image from GHCR, but you can still build locally using the provided Dockerfile if needed.
For example:
services:
app:
image: ghcr.io/vas3k/taxhacker:latest
ports:
- "7331:7331"
environment:
- SELF_HOSTED_MODE=true
- UPLOAD_PATH=/app/data/uploads
- DATABASE_URL=postgresql://postgres:postgres@localhost:5432/taxhacker
volumes:
- ./data:/app/data
restart: unless-stopped
Configure TaxHacker to suit your needs with these environment variables:
Variable | Required | Description | Example |
---|---|---|---|
PORT |
No | Port to run the app on |
7331 (default) |
UPLOAD_PATH |
Yes | Local directory for uploading files | ./data/uploads |
DATABASE_URL |
Yes | PostgreSQL connection string | postgresql://user@localhost:5432/taxhacker |
SELF_HOSTED_MODE |
No | Set it to "true" if you're self-hosting the app: it enables auto-login, custom API keys, and more | false |
DISABLE_SIGNUP |
No | Disable new user registration on your instance | false |
OPENAI_API_KEY |
No | OpenAI API key for AI features. In self-hosted mode you can set it up in settings too. | sk-... |
RESEND_API_KEY |
No | Resend API key for email notifications | re_... |
RESEND_FROM_EMAIL |
No | Email address to send from | TaxHacker <[email protected]> |
We use:
- Next.js version 15+ or later
- Prisma for database models and migrations
- PostgreSQL as a database (PostgreSQL 17+ recommended)
- Ghostscript and graphicsmagick libs for PDF files (can be installed on macOS via
brew install gs graphicsmagick
)
Set up a local development environment with these steps:
# Clone the repository
git clone https://github.com/vas3k/TaxHacker.git
cd TaxHacker
# Install dependencies
npm install
# Set up environment variables
cp .env.example .env
# Edit .env with your configuration
# Make sure to set DATABASE_URL to your PostgreSQL connection string
# Example: postgresql://user@localhost:5432/taxhacker
# Initialize the database
npx prisma generate && npx prisma migrate dev
# Start the development server
npm run dev
Visit http://localhost:7331
to see your local instance of TaxHacker.
For a production build, instead of npm run dev
use the following commands:
# Build the application
npm run build
# Start the production server
npm run start
Contributions to TaxHacker are welcome and appreciated! Here's how you can help:
- Bug Reports: File detailed issues when you encounter problems
- Feature Requests: Share your ideas for new features
- Code Contributions: Submit pull requests to improve the application
- Documentation: Help improve documentation
All work is done on GitHub through issues and pull requests.
If TaxHacker has helped you - help us in return! You donations will support maintainance and development. If you find this project valuable for your personal or business use, consider making a donation.
TaxHacker is licensed under the MIT License - see the LICENSE file for details.
For Tasks:
Click tags to check more tools for each tasksFor Jobs:
Alternative AI tools for TaxHacker
Similar Open Source Tools

NekoImageGallery
NekoImageGallery is an online AI image search engine that utilizes the Clip model and Qdrant vector database. It supports keyword search and similar image search. The tool generates 768-dimensional vectors for each image using the Clip model, supports OCR text search using PaddleOCR, and efficiently searches vectors using the Qdrant vector database. Users can deploy the tool locally or via Docker, with options for metadata storage using Qdrant database or local file storage. The tool provides API documentation through FastAPI's built-in Swagger UI and can be used for tasks like image search, text extraction, and vector search.

AirConnect-Synology
AirConnect-Synology is a minimal Synology package that allows users to use AirPlay to stream to UPnP/Sonos & Chromecast devices that do not natively support AirPlay. It is compatible with DSM 7.0 and DSM 7.1, and provides detailed information on installation, configuration, supported devices, troubleshooting, and more. The package automates the installation and usage of AirConnect on Synology devices, ensuring compatibility with various architectures and firmware versions. Users can customize the configuration using the airconnect.conf file and adjust settings for specific speakers like Sonos, Bose SoundTouch, and Pioneer/Phorus/Play-Fi.

RainbowGPT
RainbowGPT is a versatile tool that offers a range of functionalities, including Stock Analysis for financial decision-making, MySQL Management for database navigation, and integration of AI technologies like GPT-4 and ChatGlm3. It provides a user-friendly interface suitable for all skill levels, ensuring seamless information flow and continuous expansion of emerging technologies. The tool enhances adaptability, creativity, and insight, making it a valuable asset for various projects and tasks.

openmeter
OpenMeter is a real-time and scalable usage metering tool for AI, usage-based billing, infrastructure, and IoT use cases. It provides a REST API for integrations and offers client SDKs in Node.js, Python, Go, and Web. OpenMeter is licensed under the Apache 2.0 License.

rag-chatbot
The RAG ChatBot project combines Lama.cpp, Chroma, and Streamlit to build a Conversation-aware Chatbot and a Retrieval-augmented generation (RAG) ChatBot. The RAG Chatbot works by taking a collection of Markdown files as input and provides answers based on the context provided by those files. It utilizes a Memory Builder component to load Markdown pages, divide them into sections, calculate embeddings, and save them in an embedding database. The chatbot retrieves relevant sections from the database, rewrites questions for optimal retrieval, and generates answers using a local language model. It also remembers previous interactions for more accurate responses. Various strategies are implemented to deal with context overflows, including creating and refining context, hierarchical summarization, and async hierarchical summarization.

ragflow
RAGFlow is an open-source Retrieval-Augmented Generation (RAG) engine that combines deep document understanding with Large Language Models (LLMs) to provide accurate question-answering capabilities. It offers a streamlined RAG workflow for businesses of all sizes, enabling them to extract knowledge from unstructured data in various formats, including Word documents, slides, Excel files, images, and more. RAGFlow's key features include deep document understanding, template-based chunking, grounded citations with reduced hallucinations, compatibility with heterogeneous data sources, and an automated and effortless RAG workflow. It supports multiple recall paired with fused re-ranking, configurable LLMs and embedding models, and intuitive APIs for seamless integration with business applications.

evidently
Evidently is an open-source Python library designed for evaluating, testing, and monitoring machine learning (ML) and large language model (LLM) powered systems. It offers a wide range of functionalities, including working with tabular, text data, and embeddings, supporting predictive and generative systems, providing over 100 built-in metrics for data drift detection and LLM evaluation, allowing for custom metrics and tests, enabling both offline evaluations and live monitoring, and offering an open architecture for easy data export and integration with existing tools. Users can utilize Evidently for one-off evaluations using Reports or Test Suites in Python, or opt for real-time monitoring through the Dashboard service.

stable-diffusion-prompt-reader
A simple standalone viewer for reading prompt from Stable Diffusion generated image outside the webui. The tool supports macOS, Windows, and Linux, providing both GUI and CLI functionalities. Users can interact with the tool through drag and drop, copy prompt to clipboard, remove prompt from image, export prompt to text file, edit or import prompt to images, and more. It supports multiple formats including PNG, JPEG, WEBP, TXT, and various tools like A1111's webUI, Easy Diffusion, StableSwarmUI, Fooocus-MRE, NovelAI, InvokeAI, ComfyUI, Draw Things, and Naifu(4chan). Users can download the tool for different platforms and install it via Homebrew Cask or pip. The tool can be used to read, export, remove, and edit prompts from images, providing various modes and options for different tasks.

inspector-laravel
Inspector is a code execution monitoring tool specifically designed for Laravel applications. It provides simple and efficient monitoring capabilities to track and analyze the performance of your Laravel code. With Inspector, you can easily monitor web requests, test the functionality of your application, and explore data through a user-friendly dashboard. The tool requires PHP version 7.2.0 or higher and Laravel version 5.5 or above. By configuring the ingestion key and attaching the middleware, users can seamlessly integrate Inspector into their Laravel projects. The official documentation provides detailed instructions on installation, configuration, and usage of Inspector. Contributions to the tool are welcome, and users are encouraged to follow the Contribution Guidelines to participate in the development of Inspector.

MetaGPT
MetaGPT is a multi-agent framework that enables GPT to work in a software company, collaborating to tackle more complex tasks. It assigns different roles to GPTs to form a collaborative entity for complex tasks. MetaGPT takes a one-line requirement as input and outputs user stories, competitive analysis, requirements, data structures, APIs, documents, etc. Internally, MetaGPT includes product managers, architects, project managers, and engineers. It provides the entire process of a software company along with carefully orchestrated SOPs. MetaGPT's core philosophy is "Code = SOP(Team)", materializing SOP and applying it to teams composed of LLMs.

OpenLLM
OpenLLM is a platform that helps developers run any open-source Large Language Models (LLMs) as OpenAI-compatible API endpoints, locally and in the cloud. It supports a wide range of LLMs, provides state-of-the-art serving and inference performance, and simplifies cloud deployment via BentoML. Users can fine-tune, serve, deploy, and monitor any LLMs with ease using OpenLLM. The platform also supports various quantization techniques, serving fine-tuning layers, and multiple runtime implementations. OpenLLM seamlessly integrates with other tools like OpenAI Compatible Endpoints, LlamaIndex, LangChain, and Transformers Agents. It offers deployment options through Docker containers, BentoCloud, and provides a community for collaboration and contributions.

notte
Notte is a web browser designed specifically for LLM agents, providing a language-first web navigation experience without the need for DOM/HTML parsing. It transforms websites into structured, navigable maps described in natural language, enabling users to interact with the web using natural language commands. By simplifying browser complexity, Notte allows LLM policies to focus on conversational reasoning and planning, reducing token usage, costs, and latency. The tool supports various language model providers and offers a reinforcement learning style action space and controls for full navigation control.

phospho
Phospho is a text analytics platform for LLM apps. It helps you detect issues and extract insights from text messages of your users or your app. You can gather user feedback, measure success, and iterate on your app to create the best conversational experience for your users.

xFasterTransformer
xFasterTransformer is an optimized solution for Large Language Models (LLMs) on the X86 platform, providing high performance and scalability for inference on mainstream LLM models. It offers C++ and Python APIs for easy integration, along with example codes and benchmark scripts. Users can prepare models in a different format, convert them, and use the APIs for tasks like encoding input prompts, generating token ids, and serving inference requests. The tool supports various data types and models, and can run in single or multi-rank modes using MPI. A web demo based on Gradio is available for popular LLM models like ChatGLM and Llama2. Benchmark scripts help evaluate model inference performance quickly, and MLServer enables serving with REST and gRPC interfaces.

ProX
ProX is a lm-based data refinement framework that automates the process of cleaning and improving data used in pre-training large language models. It offers better performance, domain flexibility, efficiency, and cost-effectiveness compared to traditional methods. The framework has been shown to improve model performance by over 2% and boost accuracy by up to 20% in tasks like math. ProX is designed to refine data at scale without the need for manual adjustments, making it a valuable tool for data preprocessing in natural language processing tasks.