> ## Documentation Index
> Fetch the complete documentation index at: https://docs.keenable.ai/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> Every page is listed in https://docs.keenable.ai/llms.txt. To pick a product for a job, read https://docs.keenable.ai/choose.md
> Setup steps for agents, covering the SDKs, the MCP server and the CLI: https://docs.keenable.ai/skill.md
> Keenable search and fetch work without an API key. To add them to code, use the official SDK for the project's language: https://docs.keenable.ai/sdks.md
> Without a key, call POST https://api.keenable.ai/v1/search/public or GET https://api.keenable.ai/v1/fetch/public with an X-Keenable-Title header that names your app.
> With a key, send it in the X-API-Key header and read it from the KEENABLE_API_KEY environment variable. Never ask a user to paste a key into chat. Every access method: https://docs.keenable.ai/auth.md
> To get an API key without the console, use device login: https://docs.keenable.ai/authentication.md#device-login
> MCP server: https://api.keenable.ai/mcp (no key, or X-API-Key; keyless Codex uses https://api.keenable.ai/mcp-public), or https://api.keenable.ai/mcp-oauth for OAuth sign-in. These docs are an MCP server at https://docs.keenable.ai/mcp and the OpenAPI spec is at https://docs.keenable.ai/api-reference/openapi.json
> Keenable searches and fetches public web pages. If a question needs no web information, skip the call.
> On 402 with an API key (code insufficient_credits), stop and ask a human to add credits; don't retry. On 429, wait the number of seconds in Retry-After, then retry. Before you ship, follow https://docs.keenable.ai/production.md
> Every error, with its cause and fix, is in https://docs.keenable.ai/errors.md and moving from another search API is covered in https://docs.keenable.ai/migrate.md
> Before you compare Keenable with another search API, read https://docs.keenable.ai/guides/evaluate-search-apis.md

# tgpt terminal web search

> 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.

*Search provider in tgpt*

Keenable answers the web searches in [tgpt](https://github.com/aandrew-me/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](https://github.com/aandrew-me/tgpt/blob/main/SEARCH_SETUP.md)

## Install

Keenable is a search provider in tgpt 2.16.0 and later. Install or update tgpt with Homebrew, or with Go:

> [tab] Homebrew
>
> ```bash theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
> brew install tgpt
> ```

> [tab] Go
>
> ```bash theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
> go install github.com/aandrew-me/tgpt/v2@latest
> ```

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`):

```bash theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
export SEARCH_PROVIDER="keenable"
tgpt -f "latest Go release notes"
```

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:

```bash theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
tgpt -f --search-provider keenable "latest Go release notes"
```

`-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`:

```bash theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
tgpt -t web_search_keenable "What did the Go team announce this week?"
```

The model decides when to call `web_search_keenable` and passes it a `query`.

## Settings

| Setting | Where | What it does |
| - | - | - |
| `SEARCH_PROVIDER=keenable` | Environment | Selects Keenable for find mode. |
| `--search-provider keenable` | Flag | Same, for one command. The flag wins over the variable. |
| `KEENABLE_API_KEY` | Environment | Optional. If set, tgpt calls `/v1/search` with your key instead of the keyless `/v1/search/public`. |
| `-t web_search_keenable` | Flag | Registers Keenable as a tool the model can call. |

> [!NOTE]
>
> Without `KEENABLE_API_KEY`, searches run on the shared public tier at [lower rate limits](https://docs.keenable.ai/rate-limits.md). Export `KEENABLE_API_KEY` to use your organization's limits and remove the hourly cap. See [API keys](https://docs.keenable.ai/api-keys.md).

## Related pages

> [card] [AnythingLLM](https://docs.keenable.ai/integrations/anythingllm.md)
>
> Keenable is a built-in web search provider for AnythingLLM agents, with no API key required.

> [card] [LibreChat](https://docs.keenable.ai/integrations/librechat.md)
>
> Keenable is the keyless search provider and content scraper built into LibreChat's web search.

> [card] [ChatGPT](https://docs.keenable.ai/integrations/chatgpt.md)
>
> Install Keenable from OpenAI's Plugins Directory, and keep ChatGPT's own web search from competing with it.

> [card] [Connect your agent (MCP)](https://docs.keenable.ai/mcp-server.md)
>
> 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.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.