GPT Researcher

GPT Researcher is an open-source autonomous AI research agent that gathers information from multiple online sources and organizes it into research reports with inline citations. It is designed for individuals, teams, applications, and multi-agent frameworks.

Users provide a research topic, GPT Researcher collects information from trusted sources, and the system produces a report within minutes. Reports can be exported as PDF, Word, Markdown, JSON, or CSV files, and research can combine web sources with local documents.

The project supports LLMs including OpenAI, Anthropic, Groq, Llama 3, and Hugging Face models, along with search engines such as Google, Bing, Tavily, and DuckDuckGo. It is available as an open-source project through GitHub and can also be opened in Colab.

Highlights

• Multi-source research with inline citations
• Support for web, local-document, and hybrid research
• Compatible with multiple LLMs and search engines
• Long report generation of 2,000+ words
• Export to PDF, Word, Markdown, JSON, and CSV