repowiserepowise

MCP server

assafelovic / gpt-researcher

An autonomous agent that conducts deep research on any data using any LLM providers

★ 30,708stars on GitHubPythonApache-2.0

This connects Repowise to assafelovic/gpt-researcher's code. It does not install gpt-researcher.

Repowise maps public repos from their source. Not affiliated with assafelovic. What is Repowise?

github.com/assafelovic/gpt-researcherIndexed at 5d84d2f

What is gpt-researcher?

gpt-researcher is an autonomous agent that conducts deep research on any data using any LLM provider. It produces detailed research reports with citations from web sources and local documents. A planner agent generates research questions, execution agents gather and summarize information for each question, and a publisher combines the findings into a final report. The project is written mainly in Python, with a Next.js frontend. To install it, run git clone https://github.com/assafelovic/gpt-researcher.git and follow the steps below. Its code health is 7.3 out of 10 (Good), ranked #126 of 4,000+ indexed repos. The last commit to gpt-researcher was on Jul 14, 2026, and 285 people have contributed.

As of commit 5d84d2f, indexed Aug 12, 2026. What it is comes from a model reading the README; the rest is measured from the source and git history, not from the maintainer.

For agentsgpt-researcher.md

Repo facts: type, license, health, rank, contributors
gpt-researcher facts
TypeMCP server
LicenseApache-2.0
Code health7.3 / 10 (Good)
Health rank#126 of 4,000+ indexed repos
Last commitJul 14, 2026
Contributors285
Bus factor3
Size614 files, 63,716 lines

Install gpt-researcher

Commands copied from the README

  1. 1Clone the gpt-researcher repository.
    git clone https://github.com/assafelovic/gpt-researcher.git
  2. 2Move into the gpt-researcher folder.
    cd gpt-researcher
  3. 3Set your API keys by exporting them or storing them in a .env file.
    export OPENAI_API_KEY={Your OpenAI API Key here}
  4. 4Install the dependencies.
    pip install -r requirements.txt
  5. 5Start the server.
    python -m uvicorn main:app --reload

Releases on GitHub (latest v3.8.0, Nov 9, 2026)

Full install notes on GitHub

Explore gpt-researcher

Ask about this code in your agent

This connects Repowise to gpt-researcher's code. It does not install gpt-researcher. To install gpt-researcher, use the install steps.

Useful if you want to change or fork gpt-researcher: your agent can ask how it is put together and get answers that cite its files.

Ask about gpt-researcher

Answers come from gpt-researcher's README and source, with the files they cite. Two free answers a day without an account.

Want this for your own codebase? Map your repo free

About this page

Get a page like this for your own codebase

Repowise built this map of assafelovic/gpt-researcher from its source and git history. It parses every symbol, draws the dependency graph, scores each file's health from complexity, duplication, coverage and churn, finds hotspots and owners in the history, and writes documentation for every module. Your coding agent reads the same index over MCP, so its answers cite real files.

Free for 2 public repos, with a page like this one. No card. See how Repowise works

Prefer local? pip install repowise && repowise init indexes your own checkout, no account needed. Star Repowise on GitHub

assafelovic/gpt-researcher FAQ

What is gpt-researcher?

gpt-researcher is an autonomous agent that conducts deep research on any data using any LLM provider. It writes research reports with citations from web sources and local documents.

How does gpt-researcher work?

gpt-researcher uses planner and execution agents. The planner generates research questions, the execution agents gather information for each question, and a publisher aggregates the findings into a report.

How do I install gpt-researcher?

gpt-researcher is installed by cloning the repository and installing Python 3.11 or later. You then set API keys such as OPENAI_API_KEY, run pip install -r requirements.txt and start the server with python -m uvicorn main:app --reload. See the install steps

What language is gpt-researcher written in?

gpt-researcher is written mainly in Python. Its frontend code uses TypeScript and JavaScript.

How is the gpt-researcher code organized?

gpt-researcher keeps its core research engine in the gpt_researcher directory. The backend directory holds the server and report types, and the frontend directory holds the Next.js client.

When should I use gpt-researcher?

gpt-researcher is for producing a research report on a topic from web sources or your own local documents, with citations. It suits tasks that need sourced findings combined into one document.

What license does gpt-researcher use?

gpt-researcher is licensed under Apache-2.0.

Code health

7.2out of 10Good

Hotspots average 2.0, the place fixes pay off most.

On the leaderboards:#3 of 5 Agent frameworks#30 of 71 Python repos

Key features of gpt-researcher

  • Generates detailed research reports from web sources and local documents.
  • Scrapes web pages that rely on JavaScript.
  • Keeps memory and context throughout a research task.
  • Connects to specialized data sources such as GitHub repositories, databases and custom APIs through MCP integration.
  • Exports reports to PDF, Word and other formats.

How assafelovic/gpt-researcher works

Research requests enter through the server in backend/server/app.py, which hosts the entry points for serving reports. backend/report_type/deep_research/main.py is the entry point for the deep research workflow, which explores a topic as a tree of subtopics with configurable depth and breadth. The gpt_researcher directory is the core engine and wires agents, prompts, configuration, scraping, retrieval and utility services into one research runtime. deep_agents/main.py starts the Deep Agents Runner, which handles corpus building, agent behavior and benchmark execution. The frontend/nextjs directory holds the Next.js client integration points, configuration and helpers for the user interface. The aggregated findings are written into a report that can be exported to PDF, Word and other formats.

The codebase has 614 files and 1,606 symbols in 10 modules, led by Python, TypeScript and JavaScript. Code health is 7.2 out of 10, rated good.