Skip to main content
Search provider in tgpt Keenable answers the web searches in tgpt, the AI chat for the terminal, when you select it as the search provider. It works without an API key and needs neither a search engine ID nor the is-fast page extractor: each result comes with a long page excerpt, which tgpt passes to the model as is. → Keenable in tgpt’s search setup guide

Install

Keenable is a search provider in tgpt 2.16.0 and later. Install or update tgpt with Homebrew, or with Go:
Run tgpt -v to check the version. tgpt’s README lists the other install paths, including an install script, Scoop and Chocolatey.

Search from find mode

Select Keenable, then ask a question in find mode (-f):
tgpt searches with Keenable, gives the results to the model and prints its answer. To use Keenable for one command only, pass the flag instead of the variable:
-if starts interactive find mode with the same provider. Add -vb to see each request: tgpt prints a Calling Keenable: line with the endpoint and the query it sent.

Use it as a tool

Keenable is also a built-in tool, web_search_keenable, for models that call tools. Enable it with -t:
The model decides when to call web_search_keenable and passes it a query.

Settings

Without KEENABLE_API_KEY, searches run on the shared public tier at lower rate limits. Export KEENABLE_API_KEY to use your organization’s limits and remove the hourly cap. See API keys.

AnythingLLM

Keenable is a built-in web search provider for AnythingLLM agents, with no API key required.

LibreChat

Keenable is the keyless search provider and content scraper built into LibreChat’s web search.

ChatGPT

Install Keenable from OpenAI’s Plugins Directory, and keep ChatGPT’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.