Alpha-Dojo/DojoAgents

DojoAgents: Full-Market AI Copilot for Personal Investment

What it solves

DojoAgents bridges the gap between individual investors and institutional-grade tools by providing an AI-powered copilot for personal investment. It replaces simple dashboards with an autonomous reasoning agent capable of full-market data cognition, cross-market strategy deduction, and portfolio-aware reasoning to help users manage risk and identify market opportunities.

How it works

The system uses a "Loop-Driven Cognitive Portfolio Agent" that orchestrates multi-turn tool execution to fetch and analyze financial data (K-lines, financials, news). It features a seven-layer architecture including an Agent Loop engine for reasoning, an execution sandbox for Python code and technical indicators, and a memory system that distills successful workflows into reusable "SKILLS". It also supports multimodal inputs, allowing users to upload portfolio screenshots for automated diagnosis.

Who it’s for

Individual investors who want institutional-level market research, autonomous quantitative analysis, and a comprehensive command center to track portfolios across US, HK, and A-share markets.

Highlights

  • Loop-Driven Reasoning: Moves beyond simple summaries to perform multi-step analysis, such as linking global news events to specific stock impacts.
  • Multimodal Portfolio Diagnosis: Ability to analyze holdings directly from screenshots to flag over-concentration and risk exposure.
  • Institutional-Grade Dashboard: A React-based SPA providing heatmaps, sector taxonomy, and net-worth tracking.
  • Omnichannel Integration: Planned support for daily briefings via Slack, Telegram, Discord, and other chat platforms.

Related

  • Project
    zhayujie/CowAgent

    CowAgent is an open‑source, self‑hosted AI assistant that plans tasks, runs tools, keeps a personal knowledge base, and can operate as a team of cooperating agents. It supports many LLM providers, multimodal input, dozens of chat channels (Telegram, Slack, WeChat, etc.), a plug‑in skill system, and a three‑tier memory with nightly “Deep Dream” distillation. Install via a one‑line script or Docker, manage everything through a web console, and extend the system through the public Skill Hub or custom tool integrations.

  • Project
    YoungCan-Wang/WyckoffTradingAgent

    WyckoffAgent is an open‑source, AI‑driven trading assistant that lets you converse with a “Wyckoff master” to analyse Chinese, Hong‑Kong and US stocks. It pulls real‑time data from TickFlow, identifies Wyckoff structures, generates LLM‑based research reports, and presents results via a React web UI, a terminal dashboard, or an Electron desktop app. All user data (portfolio, signals, back‑tests) lives in Supabase, and write actions go through an approval queue. The project is AGPL‑3.0, installable via Homebrew or pip, and includes detailed cost and architecture docs.

  • Project
    fluffypony/dothething

    Dothething (dtt) is a locally‑run AI agent that takes a plain‑English task, plans the work, and executes it using LLM‑driven tool calls (search via SearXNG, privacy‑focused browser automation, file/shell actions, email, clipboard, etc.). It supports three modes—Normal (cheap fast models), Advanced (strongest models), and Quick (single‑shot fast model). Installation is a one‑line script that sets up a Python venv, SearXNG, and the Notte/Camoufox browser. The tool tracks token usage and cost via OpenRouter and offers extensive CLI flags for model overrides, session resumption, browser session reuse, orchestration, and notifications.

  • Project
    AI4Finance-Foundation/FinRobot

    FinRobot is an open‑source, multi‑agent AI platform for high‑stakes financial analysis. It separates deterministic Python‑based valuation (DCF, LBO, etc.) from LLM‑generated narration, orchestrates specialized agents (data, analysis, modeling, synthesis, reporting, plus debate agents), and ships three versions: a production desktop app (V2), a self‑hosted web report generator (V1), and an educational AutoGen library (V0). The system integrates multiple market data sources, provides 56 analyst playbooks, and can be run locally via a CLI, a browser UI, or a native Tauri desktop client.

  • Project
    mudler/LocalAGI

    LocalAGI is a self‑hosted Go platform for building and running AI agents locally. It provides a web UI for no‑code agent creation, OpenAI‑compatible REST APIs, built‑in RAG/knowledge base, multimodal model support, and extensible Go‑based custom actions. Agents can be linked into teams, scheduled, and connected to Discord, Slack, Telegram, GitHub, and IRC. Docker‑Compose files let you run on CPU or various GPUs, keeping all data on‑premise for privacy.