AojdevStudio/Finance-Guru

Self-hosted family office engine: typed Python calculators, a private SQLite ledger, and specialist agents for Claude Code and Codex. Agents propose. Typed code computes.

What it solves

Finance Guru provides a self-hosted "family office" engine for technical users to manage and analyze their financial portfolios. It eliminates the need for third-party hosted services by allowing users to run analysis tools and AI agents locally, ensuring private data stays in a local SQLite database.

How it works

The system consists of a typed Python analysis engine that performs calculations for risk, volatility, and portfolio optimization. This engine is wrapped in CLI tools and integrated with AI agents (specifically for Claude Code or Codex) via a set of "skills" and specialist agents. Users can import data via broker CSV exports or set up optional live syncs through SnapTrade and SimpleFIN using their own credentials.

Who it’s for

Technical operators and developers who are comfortable using a terminal, run AI coding assistants like Claude Code, and want a private, self-hosted environment for financial portfolio management.

Highlights

  • Local-First Privacy: Stores all private data in a local instance directory and SQLite database.
  • AI Agent Integration: Includes specialist financial agents and workflows for tasks like dividend tracking and Monte Carlo simulations.
  • Comprehensive Analysis: Built-in calculators for momentum, correlation, hedging, and margin metrics.
  • Flexible Data Entry: Supports both manual CSV imports and automated live syncs via third-party APIs.

Related

  • Project
    staskh/trading_skills

    An AI-powered market analysis tool that consolidates technicals, fundamentals, and portfolio management into a conversational interface for traders.

  • 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
    FutureUniant/WorkShadow

    A local-first desktop work log application that uses AI for semantic search, automated report generation, and Q&A over personal work history while keeping data on the user's machine.

  • Project
    YUHAI0/fin-agent

    An AI-powered financial analysis assistant that uses LLMs and Tushare data to enable natural language stock screening, strategy backtesting, and portfolio monitoring.

  • Dispatch
    OpenAI and PwC Collaboration for AI Agents in Finance

    OpenAI and PwC are collaborating to deploy AI agents that automate finance workflows, using OpenAI's own finance organization as a testing ground to modernize the office of the CFO.