TNT-Likely/BeeCount

Local-first bookkeeping for iOS/Android/Web · Self-hosted cloud + iCloud/WebDAV/S3 sync · AI capture · MCP | 本地优先的跨端记账 · 自建云 + iCloud/WebDAV/S3 同步 · AI 记账 · MCP

What it solves

BeeCount is an open-source personal finance and expense tracking application designed to give users full control over their data and privacy. It eliminates the need to rely on third-party servers where data cannot be audited, avoids data loss from service provider shutdowns, and provides a free alternative to apps with paywalls for advanced features like AI-powered entry.

How it works

The app is built with Flutter for cross-platform support (Android, iOS, and Web). It uses a local-first approach with five flexible synchronization options: BeeCount Cloud (self-hosted), iCloud, Supabase, WebDAV, and S3. For AI capabilities, it integrates GLM-4 for natural language processing, TFLite for local OCR, and cloud-based OCR for recognizing payment screenshots from platforms like Alipay and WeChat.

Who it’s for

Individuals seeking a privacy-focused, open-source financial management tool that allows them to own their data through self-hosting or trusted cloud storage, as well as users who want AI-assisted bookkeeping without subscription fees.

Highlights

  • AI-Powered Bookkeeping: Supports natural language chat, voice entries, and OCR for automatic recognition of payment screenshots.
  • Data Sovereignty: Five sync options including a self-hosted cloud (BeeCount Cloud) with AES-256 encrypted backups.
  • Comprehensive Finance Tools: Features multi-ledger, multi-account management, budget tracking, periodic entries, and detailed chart analysis.
  • MCP Support: Integration with Model Context Protocol (MCP) allows LLMs to manage account books directly when paired with BeeCount Cloud.
  • User Experience: Includes a highly customizable interface with dark mode, multiple themes, and 12 different desktop widget specifications.

Related

  • Dispatch
    ChatGPT Personal Finance Experience Release

    OpenAI has introduced a new personal finance experience in ChatGPT, allowing users to securely connect financial accounts for grounded, AI-driven budgeting and financial planning.

  • Project
    ownpilot/OwnPilot

    A privacy-first, self-hosted AI assistant platform featuring autonomous agents, 250+ tools, and integrations for IoT, browser automation, and messaging apps.

  • Project
    Lucassssss/eechat

    A secure local AI chat application that supports the Model Context Protocol (MCP) for easy integration of AI tools and services while keeping data stored locally.

  • Project
    agentpit-io/hunter-community

    Hunter Community Edition is an open‑source, Docker‑compose‑deployed financial AI agent platform. With a single LLM API key it provides real‑time market data (32+ sources), 23 pre‑built analysis SKILLs, a local “investment thesis” memory, and plug‑and‑play model compatibility (DeepSeek, Claude, Qwen, etc.). Everything runs on the user’s machine—data, chat history, and thesis stay on local disk—while remaining extensible via custom Markdown SKILLs or user‑provided MCP data services.

  • Project
    SilentCoderHere/aihub

    A privacy-first, open-source Android app that consolidates multiple AI assistants into a single, customizable interface with built-in ad and tracker blocking.