guy-hartstein

company-research-agent: Research Companies with LangGraph and Tavily

Company Research Agent uses LangGraph, Tavily, and OpenRouter to turn a company name into a source-backed research briefing. Its FastAPI backend and React interface stream progress and export reports as PDFs.

Stars
2.3k
Forks
318
Stars, last 30 days
+20
Last commit
15 days ago
Contributors
7

Our take

Activeregular commits and releases

Health score

51/100

How it is scored
Activity
56
Community
33
Issues
46
Pull requests
67

+20 stars in the last 30 days

This is an actively maintained research application with regular releases, but adoption should account for its concentrated contributor base and external API requirements.

Good fit if

  • You want a source-backed company briefing with browser progress and PDF export.
  • Your team can provide Tavily and an LLM provider key, and is comfortable running a Python API with a React frontend.
  • You want to evaluate or extend a LangGraph-based research workflow under the Apache-2.0 license.

Look elsewhere if

  • You need a research tool that works without paid or separately provisioned search and model services.
  • Your adoption policy requires a project whose work is distributed across a broader contributor base.
  • You need documented automated tests or CI as part of the repository's current setup.
All health signals
Last commit2026-10-26 (15 days ago)
Commits, last 90 days37
Releases, last 12 months5 (latest v2.3.0, 2026-10-16)
Contributors7 (top contributor: 83% of commits)
Issues closed, last 90 days1
Pull requests merged, last 90 days16 (typically merged in 0 days)
Project age21 months

Checked on 2026-11-11 with the GitHub API.

Project history

Daily GitHub snapshots since Oct 7, 2026. History covers stars and forks; health signals are not tracked historically.

Selected snapshot

Stars

2,322

Forks

320

Change since Nov 17, 2026: 0 stars·0 forks

Overview

Company Research Agent is a company diligence tool built on LangGraph and Tavily, with OpenRouter providing access to models for research and synthesis. It turns a company name and optional context into a structured, source-backed briefing on the business, industry, financial context, and recent news.

A FastAPI backend coordinates the research workflow, while a React interface tracks progress and supports PDF export. It is aimed at people who need a repeatable starting point for company research, rather than a substitute for checking sources or conducting full diligence.

Key Features

  • Researches a company's business, industry, financial context, and recent news.
  • Uses Tavily search and relevance scoring to gather and curate source material.
  • Runs the research pipeline with an OpenRouter model selected in the app, or direct OpenAI and Gemini keys.
  • Streams job progress to the browser using server-sent events.
  • Exports completed reports as PDFs.
  • Offers an API for starting jobs, checking progress, and retrieving reports.
  • Can persist jobs and reports in MongoDB.

Use Cases

  • Analysts can create an initial company briefing before deeper investment or business diligence.
  • Consultants and strategy teams can gather a structured overview of a prospective client, competitor, or market participant.
  • Founders and business development teams can review a potential partner or customer using cited source material.
  • Developers can integrate company research jobs into another workflow through the FastAPI endpoints.

What you need

Detected in the repository

  • Python (from requirements.txt)
  • A Dockerfile, so it can run in a container; a Compose file sets up the related services

License in plain words

Apache-2.0permissive

  • Commercial use: yes
  • Modify and redistribute: yes
  • You must keep: the license, the NOTICE file and a note of your changes
  • Share your changes: no
  • Includes an explicit patent grant from the contributors:

A summary, not legal advice: the LICENSE file is what applies.

Getting Started

After configuring the backend and frontend environment files, start the services with Docker Compose:

docker compose up --build

See the README for API keys, local setup, configuration, and deployment details.

Considerations

  • Research depends on Tavily and an LLM provider. OpenRouter is the main model route, with direct OpenAI and Gemini keys also supported; these services require API keys.
  • Running locally requires Python 3.11 or later and Node.js 18 or later. MongoDB is optional and only needed for persistent jobs and reports.
  • The project is actively maintained, with recent commits and releases, but most of the code comes from one person, despite several contributors.
  • The repository data reports no tests or CI configuration, so teams should assess how they will validate changes and upgrades.
  • The Apache-2.0 license permits broad use, subject to its license terms.

Found this useful?

Share it with someone who would like company-research-agent.