I love this one: https://github.com/LearningCircuit/local-deep-research

I tied it together with qwen3 30b thinking. Very easy to get it up and running, but lots of the numbers are shockingly low. You need to boost iterations and context. Especially easy if you already run searxng locally.

I havent finished tuning the actual settings, but for the detailed report it'll take ~20 minutes and so far has given pretty good results. Similar to openai's deep research. Mine often has ~100 sources.

But something I have noticed. It didnt seem to me the model was important. The magic was moreso in the project. Getting deep with higher iterations and more results.