Skip to main content
Built-in search provider Give your AnythingLLM agents web search with Keenable, a built-in web search provider since AnythingLLM v1.16.2. It works without an API key. → The Keenable provider in AnythingLLM

Turn on Keenable

1

Open the web search skill

Open Settings → Agent Skills and select Web Search.
2

Pick Keenable

Switch the skill on and choose Keenable as the provider. Leave API Key empty to use the public tier, then save.
3

Ask an agent

In a workspace chat, start your message with @agent and ask something that needs the web.

Use your API key

Paste your key (keen_<your_key>, from the console) into API Key (optional) in the same panel. If you run AnythingLLM in Docker, you can set the key as an environment variable instead:
Base URL defaults to https://api.keenable.ai. Change it only if you route requests through a proxy.
If you don’t set a key, searches run on the shared public tier at lower rate limits. A key moves them to your organization’s limits and removes the hourly cap.

ChatGPT

Install Keenable from OpenAI’s Plugins Directory, and keep ChatGPT’s own web search from competing with it.

tgpt

Use Keenable as the web search provider in tgpt, the terminal AI chat, with SEARCH_PROVIDER=keenable. No API key needed, in tgpt 2.16.0 and later.

Claude

Add Keenable to Claude and Claude Code, and keep Claude’s own web search from competing with it.

Connect your agent (MCP)

Connect the Keenable MCP server to Claude Code, Cursor, Codex and other clients for web search and fetch with no key. Sign in for higher limits and Monitors.