Agent-native memory infrastructure that turns LLM agent conversations and execution into persistent, structured memory for Python and TypeScript apps.
assafelovic/gpt-researcher
An open-source autonomous research agent that plans questions, gathers web and local sources, and writes cited reports with any LLM provider.
Open-source alternative to:Perplexity
ChatGPT Deep Research
- Stars
- 30,167
- Forks
- 4,303
- Open issues
- 42
- Last commit
- 10 days ago
What is it?
GPT Researcher is a Python agent for deep research on a given query. A planner agent breaks the task into research questions, execution agents gather and summarize sources for each one, and a publisher step aggregates the findings into a long report with citations. It can research the open web as well as local documents in PDF, Word, Excel, Markdown and other formats.
The project supports any LLM provider through OpenAI-compatible APIs and includes a context filter that keeps only passages relevant to each question before they reach the model. It also offers a recursive Deep Research mode that explores a topic in breadth and depth, an MCP client for connecting external data sources, and multi-agent workflows built on LangGraph and AG2.
Usage options include a FastAPI server with a lightweight or Next.js frontend, Docker Compose, a pip package with a Python API, and a Claude Skill installation. Reports can be exported to PDF, Word and other formats.
Key features
- 01Generates long research reports with citations from web and local documents.
- 02Filters scraped context by relevance before sending it to the LLM.
- 03Recursive Deep Research mode explores subtopics in tree-like fashion.
- 04Connects to external data sources through an MCP client.
- 05Multi-agent workflows built on LangGraph and AG2.
- 06Exports reports to PDF, Word and other formats.
Use cases
- Producing sourced background reports on a topic from many web pages.
- Researching a private collection of PDFs, spreadsheets or notes.
- Embedding automated research into a Python application via the pip package.
- Giving an AI assistant like Claude deeper web research capabilities.
Quick start
- 1
Install Python 3.12 or later
- 2
Clone the project and enter the directory
git clone https://github.com/assafelovic/gpt-researcher.git cd gpt-researcher - 3
Set API keys as environment variables
export OPENAI_API_KEY={Your OpenAI API Key here} export TAVILY_API_KEY={Your Tavily API Key here} - 4
Install dependencies and start the server
pip install -r requirements.txt python -m uvicorn main:app --reload
Things to know
- Default setup needs an OpenAI API key and a Tavily API key.
- Deep research costs about $0.4 per run and takes about 5 minutes.
Topics
FAQ
- What is gpt-researcher?
- An open-source autonomous research agent that plans questions, gathers web and local sources, and writes cited reports with any LLM provider. GPT Researcher is a Python agent for deep research on a given query. A planner agent breaks the task into research questions, execution agents gather and summarize sources for each one, and a publisher step aggregates the findings into a long report with citations. It can research the open web as well as local documents in PDF, Word, Excel, Markdown and other formats.
- Is gpt-researcher free to use? What license does it have?
- gpt-researcher is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.
- Is gpt-researcher still maintained?
- Actively maintained. The last commit to gpt-researcher was on Oct 10, 2026.
- What can I use gpt-researcher for?
- Producing sourced background reports on a topic from many web pages. Researching a private collection of PDFs, spreadsheets or notes. Embedding automated research into a Python application via the pip package. Giving an AI assistant like Claude deeper web research capabilities.
- How do I install gpt-researcher?
- Install Python 3.12 or later Clone the project and enter the directory: git clone https://github.com/assafelovic/gpt-researcher.git cd gpt-researcher Set API keys as environment variables: export OPENAI_API_KEY={Your OpenAI API Key here} export TAVILY_API_KEY={Your Tavily API Key here} Install dependencies and start the server: pip install -r requirements.txt python -m uvicorn main:app --reload
- Where can I get gpt-researcher?
- The source code and installation instructions are on GitHub: https://github.com/assafelovic/gpt-researcher
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Open-source long-horizon super agent harness that orchestrates sub-agents, memory, and sandboxes to research, code, and create across tasks lasting minutes to hours.
Local-first AI memory system that stores conversation history verbatim and retrieves it with semantic search, exposed as an MCP server and CLI.
Open-source agent chatbot platform that connects LLMs, plugins and agent tools to IM apps like QQ, Telegram, Slack and Discord.
An opinionated, batteries-included agent harness for Python that runs long multi-step tasks out of the box on LangGraph.
An agent framework that connects digital humans (2.5D, 3D, mobile, PC, web) and LLMs (OpenAI-compatible, DeepSeek) to business systems.