Stars
Forks
Watchers
Developer links
TradingAgents GUI
Built atop the TauricResearch TradingAgents framework with nearly 100,000 GitHub stars, TradingAgents GUI transforms a CLI-only multi-agent LLM stock analysis pipeline into a polished web application accessible at localhost:5000. The system deploys twelve specialized AI agents — fundamental analysts, sentiment experts, technical analysts, bull and bear researchers, a trader, risk management team, and portfolio manager — who collaboratively debate market conditions through structured LangGraph workflows before producing a final BUY, SELL, or HOLD recommendation. The interface supports ten LLM providers including OpenAI, Anthropic, Google, OpenRouter, DeepSeek, Ollama, xAI, Qwen, GLM, and MiniMax, with a first-run wizard that auto-detects configured API keys and tests connections. A live pipeline visualization shows each agent's status with real-time progress bars, while the tabbed output area separates Live Feed, Reports preview, and Tool calls into dedicated panes. The three-pane Reports tab provides searchable indexing, table-of-contents navigation, and export to Markdown, HTML, or PDF formats. Report length control across Concise, Standard, and Comprehensive modes saves up to 50% on token costs. Multi-session chat allows pinning past reports as grounding context with live token counting and context-window warnings. Three built-in themes — Terminal, Modern, and Bloomberg — persist per browser. Docker Compose deployment maps port 5000 with persistent report storage. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache 2.0 licensed.
Benefits
- Multi-Agent Collaborative Analysis
- Twelve specialized LLM agents including analysts, researchers, traders, and risk managers debate market conditions through structured LangGraph workflows before issuing recommendations.
- Ten LLM Provider Support
- Connects to OpenAI, Anthropic, Google, OpenRouter, DeepSeek, Ollama, xAI, Qwen, GLM, and MiniMax with automatic key detection and connection testing via the setup wizard.
- Token-Saving Report Controls
- Three report length modes — Concise, Standard, and Comprehensive — inject directives into all twelve agent prompts, saving approximately 50% on token costs in Concise mode.
- One Command Docker Deployment
- Single docker-compose command deploys the full stack on port 5000 with persistent report storage, optional Ollama integration profile, and cooperative run cancellation support.
Features
- Live Pipeline Visualization
- Vertical stage display with real-time progress bars showing each agent's status as pending, in-progress, completed, or errored via Server-Sent Events streaming.
- Three-Pane Report Reader
- Searchable report index, auto-generated table of contents, and full reader pane with one-click export to Markdown, HTML, or PDF formats.
- Multi-Session Chat
- Chat interface supporting any configured LLM provider with pinned past reports as grounding context and live token counting with context-window warnings.
- Bloomberg Theme System
- Three built-in themes — Terminal (blue neon), Modern (cyan), and Bloomberg (black amber/green mono-heavy) — persisted in browser localStorage.
- First-Run Setup Wizard
- Auto-detects missing API keys and guides provider selection, key entry, and connection testing with live health diagnostics for Python version and dependencies.
- Cooperative Run Cancellation
- Backend threading.Event enables real stop/cancel functionality polled between LangGraph chunks, with live-run pill visible from any tab showing current agent status.