Open Deep Research
An AI research assistant that performs iterative, deep research on a topic by combining web search, scraping and large language models, refining its research direction between iterations and compiling a sourced markdown report.
Open Deep Research is an AI-powered research assistant that performs iterative, deep research on a topic by combining search engines, web scraping and large language models. It aims to be the simplest implementation of a deep research agent: one that refines its research direction over time and digs deeper into a topic.
Each iteration builds on the previous one's findings, maintaining context of the research goals and what has been learned so far. When research completes, it compiles all findings into a markdown report with sources and references, organized for readability.
The project is written in TypeScript and released under the MIT license, and has a community-built Python reimplementation.