guy-hartstein/company-research-agent

An agentic company research tool powered by LangGraph and Tavily that conducts deep diligence on companies using a multi-agent framework. It leverages Google's Gemini 2.5 Flash and OpenAI's GPT-5.1 on the backend for inference.

What it solves

It automates the process of gathering and synthesizing comprehensive research reports on companies, eliminating the need to manually search through multiple websites, news articles, and financial reports.

How it works

The project uses a multi-agent pipeline to process data sequentially:

  1. Research Phase: Specialized agents (CompanyAnalyzer, IndustryAnalyzer, FinancialAnalyst, and NewsScanner) gather core business info, market trends, financial metrics, and recent news.
  2. Curation Phase: A Collector aggregates the data, and a Curator filters content based on relevance scores provided by Tavily AI.
  3. Synthesis Phase: A Briefing node uses Gemini 2.5 Flash to summarize large volumes of data into category-specific briefings.
  4. Finalization Phase: An Editor node uses GPT-5.1 to deduplicate content and format the final report into a structured Markdown document.

The system is powered by a FastAPI backend and a React frontend, using a polling-based architecture to track the progress of asynchronous research tasks.

Related

  • Project
    u14app/deep-research

    An AI-powered research tool that automates the gathering of information from the web and local files to generate comprehensive, in-depth reports.

  • Project
    Nutlope/open-deep-research

    An AI-powered tool that generates comprehensive, sourced research reports by iteratively searching the web and synthesizing information.

  • Project
    johnson7788/MultiAgentPPT

    A multi-agent system that automates the generation of high-quality, editable PPTs by coordinating specialized agents for outlining, parallel research, and quality checking.

  • Project
    assafelovic/gpt-researcher

    An open-source deep research agent that automates web and local document analysis to produce detailed, factual research reports with citations.

  • Project
    shuxiachai/academic-commercialization-agent

    An evidence-constrained AI agent workflow that assesses academic research commercialization by analyzing technical maturity, patents, and market signals to produce cited reports and scorecards.