> ## 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

# PipesHub web search provider

> Use Keenable as the web search provider for PipesHub assistants, from workspace settings or the admin API. No API key needed, in PipesHub 1.1.0 and later.

*Web search provider in PipesHub*

Keenable answers the web searches of assistants in [PipesHub](https://github.com/pipeshub-ai/pipeshub-ai), the open-source workplace search platform, when you add it as a web search provider. It works without an API key. A key raises the rate limits.

→ [Keenable provider in the PipesHub repository](https://github.com/pipeshub-ai/pipeshub-ai/blob/main/backend/python/app/web/search/keenable.py)

## Requirements

* PipesHub 1.1.0 or later. Earlier releases don't list Keenable.
* An admin account in your PipesHub workspace. Only admins can change web search providers.

## Add Keenable in settings

Go to **Workspace settings → Web search** and select the configure button on the **Keenable** row. Leave the API key field empty to search without a key, or paste a Keenable API key. When you save, PipesHub runs one real search through Keenable and saves the provider only if the search succeeds. If no other search provider is the default yet, Keenable becomes the default. Otherwise select **Set as default** on its row.

## Add Keenable with the API

The same change through PipesHub's admin API. Replace the instance URL and send an admin access token:

```bash theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
curl -X POST "https://pipeshub.example.com/api/v1/configurationManager/web-search/providers" \
  -H "Authorization: Bearer $PIPESHUB_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"provider": "keenable", "configuration": {}, "isDefault": true}'
```

A `200` response returns `"status": "success"` and a `details` object with the new `providerKey`, `provider` and `isDefault`. To use a key, send `"configuration": {"apiKey": "keen_<your_key>"}`. A failed test search returns its own status code with a `WebSearchHealthCheckError` body, and nothing is stored.

## What PipesHub sends

| Setting | Value |
| - | - |
| `provider` | `keenable` |
| `configuration.apiKey` | Optional. With a key, PipesHub calls `/v1/search` with `X-API-Key`. Without one, it calls the keyless `/v1/search/public`. |
| `isDefault` | `true` makes Keenable the provider assistants use. Default `false`. |
| Results per search | 10 |
| Snippet | Keenable's `description` when it is set, otherwise the first 500 characters of `snippet`. |

> [!NOTE]
>
> Without a key, searches run on the shared public tier at [lower rate limits](https://docs.keenable.ai/rate-limits.md), counted for your PipesHub server's IP address. Add an 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] [Rakazo](https://docs.keenable.ai/integrations/rakazo.md)
>
> 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.

> [card] [OpenClaw](https://docs.keenable.ai/integrations/openclaw.md)
>
> Add web search to OpenClaw with the Keenable provider, installable from ClawHub or npm.

> [card] [SearXNG](https://docs.keenable.ai/integrations/searxng.md)
>
> Add Keenable results to a SearXNG instance with the built-in keenable engine (shortcut !keen), enabled in settings.yml.

> [card] [Integrations](https://docs.keenable.ai/integrations.md)
>
> Connect Keenable web search to your agent stack: LangChain, LlamaIndex, Haystack, MCP and more.


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