# 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.

Repository: https://github.com/guy-hartstein/company-research-agent
Canonical: https://ross.abutalabs.com/products/company-research-agent
Homepage: https://companyresearcher.tavily.com
Language: Python
License: Apache-2.0
License Family: permissive
Topics: agents, ai, company, gemini, langgraph-python, research, tavily, tavily-api, tavily-search, financial-analysis, langchain, multi-agent-systems, openai, python, gemini-3-flash
Last push: 2026-08-12T03:29:03+00:00

## Health v2 (maintenance only)
Score: 75/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 97, release rhythm 67, longevity 40
- inputs: {"age_days": 567, "days_push": 21, "days_rel": 60, "gap_med": 97, "n_releases_24m": 4}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2250, forks 313 (observed 2026-08-28T04:06:30.941544+00:00)

## What it is
A multi-agent company research application built with LangGraph and Tavily that generates comprehensive due-diligence reports on any company. It orchestrates specialized research and processing nodes using Gemini 2.5 Flash for synthesis and GPT-5.1 for report editing, with a React frontend for progress tracking.

## Use cases
- research a company before an interview
- generate due diligence reports on companies
- gather financial and news data about a competitor
- automate company background research
- compile industry and market analysis for a target company
- produce structured company briefing documents

## When to choose
- you need automated, multi-source company research reports
- you want a customizable LangGraph agent pipeline for deep research
- you want a self-hosted alternative to hosted research tools with a ready web UI

## When to avoid
- you need general web research beyond company profiles
- you don't want to manage API keys and costs for Gemini and OpenAI models
- you need a lightweight single-call summarizer rather than a multi-agent pipeline

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, rag, search-engine, llm-inference, web-scraping, nlp
- domain: artificial-intelligence, fintech
- platform: python, self-hosted
- tags: langgraph, tavily, multi-agent, company-research, due-diligence, gemini, openai, react-frontend, ai-agents, natural-language-processing, research, web-server, docker

## Member repositories
- guy-hartstein/company-research-agent (main) score 75

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:30.941544+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:43:52.296342+00:00, confidence not recorded.
  - readme: https://github.com/guy-hartstein/company-research-agent (fetched 2026-08-28T04:06:30.941544+00:00, sha d7dac275ac73)
  - homepage: https://companyresearcher.tavily.com (fetched 2026-08-29T10:24:06.651187+00:00, sha a7facdbf0cc4)
- Data as of 2026-08-30T08:39:29.467469+00:00.