05 december 2025
Three Brained Searches
This tool works in four steps:
- Step 1: performs three searches on Searxng (“query_1” “query_2” and “query_3”)
- Step 2: For each query independently, LLM 1 selects a defined number of URLs from those in the searxng response based on “long_query” if it exists, otherwise based on “query_x”
- Step 3: The selected URLs are scraped by a cloud scraper (Jina) for query 1 and by an internal scraper (beautifulsoup) for queries 2 and 3; if for queries 2 and 3 there are URLs ending in .pdf, they are sent to the Jina scraper (because beautifulsoup cannot scrape PDFs)
- Step 4: The pages scraped by Jina from query 1 and those scraped by BeautifulSoup from queries 2 and 3 are sent together to LLM 2, which selects the interesting information based on “long_query”.
The default LLM 2 is fast and free, but if you are doing scientific or complicated research, I recommend using an LLM such as Deepseek V3.2 or Kimi K2 Thinking (for deepseek you can activate “Llm 2 Enable Reasoning”).
Jina scraper without Jina API key scrapes 2 URLs at the same time. With Jina API key, it scrapes 5 URLs at the same time.
The function of this tool is: tree_smart_searches
This version also has two additional functions:
- summarize_url: scrapes and summarizes web pages
- scrape_url: scrapes only web pages.
So you can provide URLs in the prompt and the agent will ask for a summary or the entire web page. You can tell it to scrape if there is a lot of important information but it take more tokens.
Tree Brained Searches Xng OR
A special version for OpenRouter that allows you to configure fallback models and prioritize providers using a list (provider IDs are separated by commas without spaces) or by enabling “Llm 2 Enable Throughput Sort.” If you enable this option, you disable the list of providers to prioritize and enable prioritization based on throughput, and you also enable the ability to disable providers that are too expensive (some are fast but expensive).
The function of this tool is: three_smart_searches
Tree Brained Searches LangSearch
This one uses LangSearch search instead of SearXNG, so there is no need to have a SearXNG local server, but there are fewer options, notably there are no academic search engines (category: science).
Various
Requirements (those that are not already pre-installed, above the tool version): they install themselves when you install the tool, provided that the person who created the tool did not forget to put them in “requirements”.
If you modify it and share it in the Open WebUI community or elsewhere, please share the link here (comments soon), and if it’s specific to a domain in the domains pages.