This project provides an agentic tool for deep company diligence, generating comprehensive research reports by synthesizing information from multiple sources. It targets users needing detailed company analysis, offering a structured, AI-driven approach to data gathering and report creation.

How It Works

The system employs a multi-agent pipeline, with specialized "Research Nodes" (CompanyAnalyzer, IndustryAnalyzer, FinancialAnalyst, NewsScanner) gathering data. "Processing Nodes" (Collector, Curator, Briefing, Editor) then aggregate, filter (using Tavily's relevance scoring), summarize using Gemini 2.0 Flash for high-context synthesis, and finally format/edit reports with GPT-4.1-mini for precision. This dual-model architecture optimizes for both broad understanding and specific output requirements.

Quick Start & Requirements

• Install: Clone the repo and run ./setup.sh (recommended) or follow manual/Docker setup.
• Prerequisites: Python (version checked by setup script), Node.js, Tavily API Key, Google Gemini API Key, OpenAI API Key. MongoDB URI is optional for persistence.
• Setup: The setup script handles dependency installation and environment variable configuration. Docker setup is also provided.
• Links: Online Demo

Highlighted Details

• Leverages LangGraph for agent orchestration.
• Utilizes Gemini 2.0 Flash for high-context synthesis and GPT-4.1-mini for precise formatting.
• Features real-time progress streaming via WebSockets.
• Employs Tavily's AI relevance scoring for content curation.

Maintenance & Community

The project is maintained by guy-hartstein. Contributions are welcomed via pull requests.

Licensing & Compatibility

Licensed under the MIT License, permitting commercial use and integration with closed-source projects.

Limitations & Caveats

Requires multiple third-party API keys (Tavily, Google Gemini, OpenAI), which may incur costs. The "GPT-4.1-mini" mentioned is likely a reference to a specific OpenAI model tier, and its exact capabilities and availability should be verified.