> ## 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

# Keenable recipes: web search apps to build

> Build complete apps on Keenable: RAG with fresh results, Monitors to Slack, competitor watch, fact-checking, SELECT enrichment, x402 payments and more.

Each recipe builds one complete thing on Keenable, from the first call to the production notes. Every recipe has a prompt you can paste into a coding agent, runnable code, an example output, and the limits and errors you hit in production.

## Pick a recipe

| Recipe | What you build | When it runs | Products |
| - | - | - | - |
| [RAG with fresh web results](https://docs.keenable.ai/recipes/rag-with-fresh-web-results.md) | Retrieve pages published in the last 30 days, render them as numbered sources and prompt your model to answer with citations. Runs with no API key. | Each time your app gets a question about recent events | Search |
| [Research loop](https://docs.keenable.ai/recipes/research-loop.md) | Research a broad question with search and fetch: run focused searches at once, merge results without duplicate URLs, read the top pages with a size cap. | Each time your agent gets a question too broad for one search | Search, Fetch |
| [Fact-check with citations](https://docs.keenable.ai/recipes/fact-check-with-citations.md) | Check a claim against the pages that discuss it: search, then fetch each page with a prompt that returns a verdict and the quoted sentence, per URL. | Each time your app needs to check a claim, such as a sentence in a draft answer | Search, Fetch |
| [News monitor to Slack](https://docs.keenable.ai/recipes/news-monitor-to-slack.md) | Post each new page a Keenable monitor finds to Slack: verify the monitor.result.found webhook, then forward the title, link and summary to an incoming webhook. | Minutes after Keenable crawls a matching page | Monitors |
| [Competitor watch](https://docs.keenable.ai/recipes/competitor-watch.md) | Watch a competitor's own domains with a Keenable monitor and get a weekday 9:00 digest of new pages, summarized in your own JSON Schema. | On a schedule: 9:00 Paris time on weekdays | Monitors |
| [Enrich a list with SELECT](https://docs.keenable.ai/recipes/enrich-a-list-with-select.md) | Add web facts to every item in a list with one SELECT query: one search per item, fields extracted by an LLM, one row per item with its source count. | On demand, when you have a list of names and need the same facts for each | SELECT |
| [Agent pays with x402](https://docs.keenable.ai/recipes/agent-pays-with-x402.md) | Give an agent web search and fetch with no account or API key: it pays each call in USDC on Base over x402, and your client refuses offers above a cap. | On every paid call: the 402 offer, then the paid retry | Search, Fetch, Pay per request |

## Build a recipe with your coding agent

Every recipe page starts with a **Recipe prompt**. It points your coding agent at the Markdown version of the page, such as `https://docs.keenable.ai/recipes/research-loop.md`, so the agent reads the same steps, code and limits you do. Paste it into Claude Code, Cursor, Codex or any other agent that can read a URL.

The recipes that only search and fetch run with no API key. Those that use [Monitors](https://docs.keenable.ai/products/monitors) need an [API key](https://docs.keenable.ai/api-keys.md) and SDK version 0.2.0 or later. The [x402](https://docs.keenable.ai/pay-per-request.md) recipe needs a wallet with USDC on Base instead of a key.

## Next steps

* [Cookbook](https://docs.keenable.ai/cookbook.md): search and filter every recipe and guide.
* [Best practices](https://docs.keenable.ai/best-practices.md): query writing, parallel searches and context size.
* [Search](https://docs.keenable.ai/products/search.md), [Fetch](https://docs.keenable.ai/products/fetch.md) and [Monitors](https://docs.keenable.ai/products/monitors): every parameter and cost.
* [SDKs](https://docs.keenable.ai/sdks.md): install the Python, TypeScript, Go or Rust client.


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