DeepDoc

The README opens with

Oqura's deepdoc is a local deep-research tool that turns your own files into a structured Markdown report. It extracts and indexes the content, plans the report, researches every section against the local collection, and combines the results into one final document.

DeepDoc uses TypeSafe's Jev model to improve the research process without replacing the generative LLM. Jev checks and reranks the chunks returned by Qdrant, then checks whether the collected evidence covers every required subsection. The configured LLM still handles planning, query generation, synthesis, and report writing, while Python uses Jev's probabilities to make explicit filtering and retry decisions.