> ## 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

# OpenClaude web search with Keenable

> Make Keenable the web search backend in OpenClaude with /search keenable or WEB_SEARCH_PROVIDER=keenable. No key needed, in OpenClaude 0.34.0 and later.

*Search backend in OpenClaude*

Keenable is a web search backend in [OpenClaude](https://github.com/Twigpine/openclaude), the open-source coding agent CLI. Select it and OpenClaude's web search tool sends every query to Keenable. It works without an API key.

→ [Keenable in OpenClaude's search provider guide](https://github.com/Twigpine/openclaude/blob/main/src/tools/WebSearchTool/README_SEARCH_PROVIDERS.md#keenable)

## Install

Keenable ships in OpenClaude 0.34.0 and later. Install or update OpenClaude from npm. It needs Node.js 24.22.1 or later:

```bash theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
npm install -g @twigpine/openclaude@latest
```

## Select Keenable

Inside an OpenClaude session, pick the backend:

```text theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
/search keenable
```

To select it from the shell instead, set the variable before you start OpenClaude:

```bash theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
export WEB_SEARCH_PROVIDER=keenable
openclaude
```

`/search status` shows which backend handles searches, and `/search test` runs a test search.

## What OpenClaude sends

Each search is one request with `query` and `max_results` set to 10:

```json theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
{"query": "search terms", "max_results": 10}
```

Without a key, it goes to `POST https://api.keenable.ai/v1/search/public` with an `X-Keenable-Title: OpenClaude` header. With a key, the same body goes to `POST https://api.keenable.ai/v1/search` with the key in `X-API-Key`. OpenClaude reads each result's text from `snippet`, flattens it to one line and cuts it at 800 characters. Domain filters are applied to the returned results.

## Settings

| Setting | Where | What it does |
| - | - | - |
| `/search keenable` | Session command | Uses only Keenable. A failed search returns an error instead of switching backends. |
| `WEB_SEARCH_PROVIDER=keenable` | Environment | Same, from the shell. |
| `KEENABLE_API_KEY` | Environment or `settings.json` | Optional. Sends searches to the keyed endpoint. |
| `/search key keenable` | Session command | Saves a key through hidden input. `/search remove-key keenable` removes it. |
| `WEB_SEARCH_TIMEOUT_SEC` | Environment | Timeout for built-in search backends, in seconds. Default `15`. |

Keenable is explicit-only: it never joins OpenClaude's `auto` chain, so selecting it doesn't change what `auto` does.

> [!NOTE]
>
> Without a key, searches run on the shared public tier at [lower rate limits](https://docs.keenable.ai/rate-limits.md). Add a key with `/search key keenable` to use your organization's limits. See [API keys](https://docs.keenable.ai/api-keys.md).

## Related pages

> [card] [FrontierAgent](https://docs.keenable.ai/integrations/frontier-agent.md)
>
> Set WEB\_SEARCH\_PROVIDER=keenable to send FrontierAgent's web\_search tool to Keenable, up to 50 results per query. Works without an API key.

> [card] [oh-my-pi](https://docs.keenable.ai/integrations/oh-my-pi.md)
>
> Use Keenable as the web search engine in oh-my-pi (omp), the coding agent, with the web/keenable model role. Works without an API key.

> [card] [Claude Octopus](https://docs.keenable.ai/integrations/claude-octopus.md)
>
> Set OCTOPUS\_RESEARCH\_WEB\_SEARCH=keenable so Claude Octopus research runs one Keenable search and hands every perspective the top results. No key needed.

> [card] [Claude](https://docs.keenable.ai/integrations/claude.md)
>
> Add Keenable to Claude and Claude Code, and keep Claude's own web search from competing with it.


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