# Keenable

> Web search and knowledge access for AI agents.

- [Quickstart](https://docs.keenable.ai/index.md): Install the Keenable CLI, log in, wire the MCP server into your agents, and run your first search.
- [Authentication](https://docs.keenable.ai/authentication.md): Get an API key, pass it to the API, CLI and MCP server, and read the error responses.
- [Rate limits](https://docs.keenable.ai/rate-limits.md): How fast you can call search and fetch — the per-second and hourly limits for authenticated and unauthenticated requests, and how they differ from the credit allowance.
- [Credits](https://docs.keenable.ai/credits.md): The free allowance of 100,000 requests a month, how authenticated usage is metered against it, and what happens when it runs out.
- [MCP](https://docs.keenable.ai/mcp-server.md): Connect Keenable APIs as tools to clients that support MCP
- [CLI](https://docs.keenable.ai/cli.md): Authenticate, configure MCP, and search from the terminal
- [API reference](https://docs.keenable.ai/api-reference.md): The HTTP API behind the Keenable CLI, MCP server, and integrations.
- [Search](https://docs.keenable.ai/api-reference/search.md): Search the web and return ranked results
- [Fetch](https://docs.keenable.ai/api-reference/fetch.md): Fetch webpage contents
- [Changelog](https://docs.keenable.ai/changelog.md): Product updates and announcements from Keenable.
- [Integrations](https://docs.keenable.ai/integrations.md): Connect Keenable web search to your agent stack — LangChain, LlamaIndex, Haystack, MCP, and more.
- [LangChain](https://docs.keenable.ai/integrations/langchain.md): langchain-keenable — KeenableSearch and KeenableFetch tools for any LangChain agent.
- [LlamaIndex](https://docs.keenable.ai/integrations/llamaindex.md): A Keenable ToolSpec so LlamaIndex agents can search and read the web.
- [Haystack](https://docs.keenable.ai/integrations/haystack.md): Keenable web search and page-fetch components for Haystack pipelines.
- [Mastra](https://docs.keenable.ai/integrations/mastra.md): @keenable/mastra — keenable-search and keenable-fetch tools for any Mastra agent.
- [Vercel AI SDK](https://docs.keenable.ai/integrations/vercel-ai-sdk.md): @keenable/ai-sdk — keenable_search and keenable_fetch tools for the Vercel AI SDK.
- [NVIDIA NeMo Agent Toolkit](https://docs.keenable.ai/integrations/nemo-agent-toolkit.md): A Keenable function group (keenable__search, keenable__fetch) for the NVIDIA NeMo Agent Toolkit.
- [OpenCode](https://docs.keenable.ai/integrations/opencode.md): opencode-keenable — a native plugin giving OpenCode agents web search and page fetch.
- [Pi](https://docs.keenable.ai/integrations/pi.md): A Keenable web-search and page-fetch package for the Pi coding agent.
- [Claude](https://docs.keenable.ai/integrations/claude.md): Keenable is a listed MCP connector in Claude — connect it from Settings → Connectors.
- [ChatGPT and Codex](https://docs.keenable.ai/integrations/chatgpt.md): Keenable is published in OpenAI's Plugins Directory — install it from the catalog shared by ChatGPT and Codex.
- [LibreChat](https://docs.keenable.ai/integrations/librechat.md): Keenable is the keyless search provider and content scraper built into LibreChat's web search.
- [n8n](https://docs.keenable.ai/integrations/n8n.md): A Keenable web-search and page-fetch community node for n8n workflows.
- [Dify](https://docs.keenable.ai/integrations/dify.md): Keenable web search and page fetch as a plugin in the Dify marketplace.
- [Langflow](https://docs.keenable.ai/integrations/langflow.md): A drag-and-drop Keenable search component for the Langflow canvas.
- [RAGFlow](https://docs.keenable.ai/integrations/ragflow.md): A Keenable web-search agent tool built into RAGFlow, usable in the visual agent builder.
- [Convex](https://docs.keenable.ai/integrations/convex.md): @keenable/convex — a Convex component exposing search and fetch as component actions.
- [SearXNG](https://docs.keenable.ai/integrations/searxng.md): A keenable search engine built into SearXNG (shortcut !keen), enabled in settings.yml.
- [Lightpanda](https://docs.keenable.ai/integrations/lightpanda.md): Keenable is the keyless search engine behind the search tool in the Lightpanda headless browser.
- [ketch](https://docs.keenable.ai/integrations/ketch.md): Keenable as a built-in search backend in the ketch agent CLI (Go).
- [Nanobot](https://docs.keenable.ai/integrations/nanobot.md): Keenable web search built into Nanobot, with a DuckDuckGo fallback.
- [Omnigent](https://docs.keenable.ai/integrations/omnigent.md): Keenable as a built-in web_search backend in Omnigent, selectable via the tool's search_provider config.
- [Vellum Assistant](https://docs.keenable.ai/integrations/vellum-assistant.md): Keenable as a built-in web-search provider in Vellum Assistant, alongside Brave, Perplexity, Tavily and Firecrawl.
- [WeKnora (Tencent)](https://docs.keenable.ai/integrations/weknora.md): Keenable as a built-in web-search provider in Tencent WeKnora.
- [OpenClaw](https://docs.keenable.ai/integrations/openclaw.md): A web-search provider for OpenClaw, installable from ClawHub or npm.
- [web-search-plus (Hermes)](https://docs.keenable.ai/integrations/web-search-plus.md): Keenable as a web-search and extract provider in the web-search-plus community plugin for the Hermes agent.
- [Hermes Agent](https://docs.keenable.ai/integrations/hermes-agent.md): hermes-keenable-web — a standalone Keenable web-search and page-fetch provider for the Hermes agent runtime.
- [de-anthropocentric research engine](https://docs.keenable.ai/integrations/de-anthropocentric-research-engine.md): Keenable is one of the MCP servers the de-anthropocentric research engine ships with, pre-wired in its bundled config.
- [Pipecat](https://docs.keenable.ai/integrations/pipecat.md): KeenableWebSearch — low-latency web search for Pipecat voice agents.

## OpenAPI Specs

- [openapi](/api-reference/openapi.json)