opendeepresearcher

We have hosted the application opendeepresearcher in order to run this application in our online workstations with Wine or directly.

Quick description about opendeepresearcher:

OpenDeepResearcher is a notebook-based AI research agent that searches the web iteratively until it has enough context to produce a final report. A user provides a research topic, and the system generates search queries with an LLM. It then runs concurrent searches, deduplicates links, fetches page content, evaluates whether each page is useful, and extracts relevant context. After each round, the model decides whether more searches are needed or whether the available evidence is enough. The final output is a comprehensive research report based on the gathered material. The project uses services such as SERPAPI, Jina, and OpenRouter, with an optional Gradio notebook for a more usable interface.

Features:

• Iterative AI research loop
• LLM-generated search queries
• Concurrent search and extraction
• Duplicate link filtering
• Usefulness evaluation for pages
• Final report generation

Categories: