08 november 2025, last modification : 05 december 2025
Brained Search
Now BDS uses Three Brained Searches by default, it’s the same tool with three parallel searches to speed things up.
This tool works in four steps:
- Step 1: It searches the internet using a few keywords (query)
- Step 2: LLM 1 selects the URLs to scrape based on a query related to the cycle (long_query)
- Step 3: It scrapes the URLs selected by LLM 1
- Step 4: LLM 2 selects interesting information from scraped pages based on a query related to the cycle (long_query)
The default LLM 2 (Nova 2 lite free) is fast, free and have big context (if you have time, you can increase the number of URLs scraped), 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”).
Brained Search Xng
This one uses Beautifulsoup scraper (CPU)
The function of this tool is: xng_smart_search
Important: You need to have a local SearXNG server, especially if you make a lot of queries, such as with the BTS1 agent (and even if you don’t make many, most public servers are designed to be used with a browser).
If you don’t want to install a local SearXNG server, use Brained Search DDGS (see below).
Brained Search Xng Jina
This one uses Jina scraper (cloud) instead of Beautifulsoup scraper (CPU).
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: xng_smart_search
This version also has two additional functions:
- summarize_url: scrapes and summarizes web pages
- scrape_url: scrapes only web pages in a particular domain.
So you can provide a web page to the agent (BDS1 or other) and it will ask for a summary or the entire web page. You can tell it to scrape if there is a lot of important information.
Brained Search 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: xng_smart_search (or main_xng_smart_search for the “main” version)
Brained Search 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, and if it’s specific to a domain in the domains pages.