> ## 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

# npcpy web search with Keenable

> Search the web from npcpy with the keenable provider for search_web, or call search_keenable directly. No API key needed, in npcpy 2.1.28 and later.

*Search provider in npcpy*

Keenable is a provider for `search_web` in [npcpy](https://github.com/NPC-Worldwide/npcpy), the Python library for building LLM agents. Pass `provider="keenable"` and the search goes to Keenable. It works without an API key.

→ [npcpy/data/web.py in the npcpy repository](https://github.com/NPC-Worldwide/npcpy/blob/main/npcpy/data/web.py)

## Install

The Keenable provider is in npcpy 2.1.28, the current release on PyPI on 19 November 2026. Install or update npcpy:

```bash theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
pip install -U npcpy
```

## Search the web

Call `search_web` with the provider:

```python theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
from npcpy.data.web import search_web

content, links = search_web("open-source speech recognition models", num_results=5, provider="keenable")

print(content)  # each result's text, followed by "Citation: <url>"
print(links)    # one URL per line
```

`search_web` returns two strings: the results' text with a citation line after each, ready to put in a prompt, and the list of URLs.

For the results as data, call `search_keenable` from the same module:

```python theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
from npcpy.data.web import search_keenable

results = search_keenable("open-source speech recognition models", num_results=5)

for r in results:
    print(r["title"], r["link"])
```

You get a list of dictionaries with `title`, `link` and `content`. `content` is Keenable's `snippet`, the page text, cut to 500 characters. If the request fails, npcpy prints the error and returns an empty list.

## Options

| Argument | Default | What it does |
| - | - | - |
| `provider` | `"startpage"` | `"keenable"` selects Keenable. |
| `num_results` | `5` | Number of results. Values above 50 are sent as 50. |
| `api_key` | `None` | Keenable API key. If `None`, npcpy reads `KEENABLE_API_KEY`. With a key, it calls `/v1/search` with `X-API-Key`; without one, the keyless `/v1/search/public`. |

Every request carries an `X-Keenable-Title: npcpy` header and a 10-second timeout.

> [!NOTE]
>
> Without a 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. See [API keys](https://docs.keenable.ai/api-keys.md).

## Related pages

> [card] [Vercel AI SDK](https://docs.keenable.ai/integrations/vercel.md)
>
> Keyless web search and page fetch for the Vercel AI SDK (`@keenable/ai-sdk`), plus Vercel Connect to keep the API key out of environment variables.

> [card] [AgentField](https://docs.keenable.ai/integrations/agentfield.md)
>
> Run AgentField's deep research example on Keenable web search with SEARCH\_PROVIDER=keenable. No account or API key needed.

> [card] [Agno](https://docs.keenable.ai/integrations/agno.md)
>
> Give Agno agents web search and page reading with KeenableTools, a toolkit built into Agno, with no API key required.

> [card] [Overview](https://docs.keenable.ai/sdks.md)
>
> Install the official Keenable SDK for Python, TypeScript, Go or Rust with one command, search with no key, then add fetch, tool calling and Monitors.


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