keenable engine, then search with the !keen shortcut.
→ View the change on GitHub
Install
No separate install
Keenable ships as a core SearXNG engine (searx/engines/keenable.py), so there is no package to install. SearXNG is a rolling release, and every build since July 30, 2026 includes the engine.
Enable it in settings.yml
SearXNG registers every new engine asdisabled: true and inactive: true, so the instance operator turns it on in settings.yml:
Use it
Restart the instance, then type the!keen bang before a query, or select Keenable in the engine list.
Add
api_key to the engine settings to remove the hourly request cap. If you leave it out, the engine runs on the shared public tier at lower rate limits. On a multi-user instance, everyone behind the instance’s egress address shares that limit.Related pages
Vellum Assistant
Keenable as a built-in web-search provider in Vellum Assistant, alongside Brave, Perplexity, Tavily and Firecrawl.
Rakazo
Keenable as a built-in web provider in Rakazo, the open source self-hosted AI agent. Serves web_search and web_fetch, no key needed.
web-search-plus (Hermes)
Keenable as a web-search and extract provider in the web-search-plus community plugin for the Hermes agent.
Fetch quickstart
Turn any URL into clean markdown your model can read, or get only the part a prompt asks for. Try it with no API key. Code, cost per call and gotchas.