> ## 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

# FrontierAgent web search with Keenable

> 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.

*Search provider in FrontierAgent*

Keenable is a search provider for the `web_search` tool in [FrontierAgent](https://github.com/ApodexAI/FrontierAgent), the terminal agent you launch in any project. Serper stays the default. Set one variable and `web_search` sends its queries to Keenable instead, without an API key.

→ [Global install guide in the FrontierAgent repository](https://github.com/ApodexAI/FrontierAgent/blob/main/docs/install/global-install.md)

## Install

FrontierAgent has no releases yet, so it ships from its `main` branch. Install it as a tool with [uv](https://docs.astral.sh/uv/):

```bash theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
uv tool install --python 3.12 git+https://github.com/ApodexAI/FrontierAgent.git
```

This installs `frontier-agent` and its alias `apodex`.

## Select Keenable

A global install reads settings from `~/.config/apodex/env` (or `$XDG_CONFIG_HOME/apodex/env`), next to your model settings. Add the provider line:

```bash theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
config_dir="${XDG_CONFIG_HOME:-$HOME/.config}/apodex"
mkdir -p "$config_dir"
echo "WEB_SEARCH_PROVIDER=keenable" >> "$config_dir/env"
chmod 600 "$config_dir/env"
```

Open a terminal in a project and run `frontier-agent`. When the agent calls `web_search`, the query goes to Keenable. For a clone run with `uv sync`, put the same line in the repository's `.env`, or export it in the shell.

## Settings

| Setting | What it does |
| - | - |
| `WEB_SEARCH_PROVIDER=keenable` | Sends `web_search` to Keenable, up to 50 results per query. `serper` is the default. |
| `KEENABLE_API_KEY` | Optional. With a key, searches go through your Keenable account at its higher limits and use its credits. |

The setting changes `web_search` only. `web_fetch` keeps its own provider.

The env file takes plain `KEY=value` lines and reads values literally: `${VAR}` is not expanded. `APODEX_ENV_FILE=/path/to/file` points FrontierAgent at a different file.

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

## Related pages

> [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] [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] [Gajae-Code](https://docs.keenable.ai/integrations/gajae-code.md)
>
> Use Keenable as the web search provider in Gajae-Code (gjc), the coding-agent harness, with providers.webSearch set to keenable. No key needed.

> [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.