> ## 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

# oh-my-pi web search with Keenable

> 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.

*Search engine in oh-my-pi*

Keenable is a web search engine in [oh-my-pi](https://github.com/can1357/oh-my-pi) (`omp`), the terminal coding agent. Select `web/keenable` and the agent's `web_search` tool sends its queries to Keenable. With no key, an explicit selection uses Keenable's keyless endpoint.

→ [web\_search in oh-my-pi's docs](https://github.com/can1357/oh-my-pi/blob/main/docs/tools/web_search.md)

## Install

Keenable is in oh-my-pi 19.0.0, the current release on 19 November 2026. Install or update omp with Bun:

```bash theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
bun install -g @oh-my-pi/pi-coding-agent
```

oh-my-pi's README also lists an install script and Homebrew (`brew install can1357/tap/omp`).

## Make Keenable the search engine

Search provider choice is the `web` model role. Set it in `~/.omp/agent/config.yml`, or in `<repo>/.omp/config.yml` for one project:

```yaml theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
modelRoles:
  web: web/keenable
```

The agent's `web_search` calls now go to Keenable first. A role you set is an explicit selection, so it runs without a key. To try Keenable for one query without changing settings, pass it as the model:

```bash theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
omp q --model web/keenable "latest Bun release notes"
```

## What omp sends

| Query part | Sent to Keenable as |
| - | - |
| The query text, with quoted phrases kept | `query` |
| `limit` or `num_search_results` | `max_results`, default 10, clamped to 1 to 50 |
| A single `site:` host | `site` |
| `after:` and `before:` | `published_after` and `published_before` |
| `recency` (`day`, `week`, `month`, `year`) | A relative `published_after`: `1d`, `7d`, `1mo`, `1y` |

Other directives, such as `intitle:` or `filetype:`, are applied by omp's own post-filter. A query made only of a date filter is rejected.

## Keys and the automatic chain

| Setup | Behaviour |
| - | - |
| `web/keenable` selected, no key | Calls the keyless `/v1/search/public` with `X-Keenable-Title: oh-my-pi`, rate limited per IP. |
| `KEENABLE_API_KEY` set, or a stored `keenable` credential | Calls `/v1/search` with the key in `X-API-Key`. A credential that fails to resolve returns an error instead of falling back to the keyless endpoint. |
| No role set | The default `web` chain doesn't list Keenable. Add it to `modelRoles.web` or `retry.fallbackChains.web` to use it. |
| `providers.webKeyless: false` | Keenable without a key is skipped, except for a per-request `--model web/keenable`. |

> [!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] [OpenClaude](https://docs.keenable.ai/integrations/openclaude.md)
>
> 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.

> [card] [Devin Desktop](https://docs.keenable.ai/integrations/devin-desktop.md)
>
> Add Keenable to Devin Desktop (formerly Windsurf) over MCP. Config paths for Devin Local and the legacy Windsurf data directory.

> [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] [Agent skill](https://docs.keenable.ai/agent-skill.md)
>
> Install the keenable-web-search agent skill with npx skills add. Your agent searches the web with a bundled script, with no API key and no MCP client.


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