Octen Docs | The Search infrastructure for AI

For AI agents: docs.octen.ai/integrations/octen-cli.md

@octen.ai/cli is the official command-line tool for Octen. One command wires Octen’s MCP server and Agent Skills into your AI client. It also brings the full Octen API straight to your terminal.

Get API Key

Create a key from the API Platform.

GitHub

View the source and releases.

npm

The @octen.ai/cli package.

Install

npm
Homebrew

Requires Node.js 18+.

npm i -g @octen.ai/cli

Or run without installing: npx @octen.ai/cli <command>.

brew install Octen-Team/tap/octen

Authenticate

You’ll need an Octen API key first. Create one from the API Platform.

Set your key as an environment variable — every command picks it up automatically:

export OCTEN_API_KEY="your-key"          # add to ~/.zshrc or ~/.bashrc to persist

You can also pass --api-key <key> on any single command. To point at a staging or self-hosted endpoint, set OCTEN_API_URL or pass --base-url <url>.

Set up your AI agent

One command merges the Octen MCP server or Agent Skills into your client.

Agent Skills
MCP server

Install the Octen Skills into your AI agent:

octen configure-skills --claude-code --set-key

Supported: Claude Code, Cursor, Codex, OpenClaw, Hermes. For Claude Desktop, use —claude-code.

Add the Octen MCP server:

octen configure-mcp --claude-code

Supported: Claude Code, Claude Desktop, Cursor, Windsurf, VS Code, Codex.

--all configures every client found on your machine at once.

Use Octen from the terminal

Command	What it does
`octen broad-search <query>`	Broad, multi-angle web search across auto-generated sub-queries.
`octen search <query>`	Live web search with highlights and optional full content.
`octen news <query>`	News search for current events and headlines.
`octen image-search <query>`	Image search by text or a reference image. Beta — contact us for access.
`octen video-search <query>`	Video search by text query. Beta — contact us for access.
`octen extract <urls...>`	Content extraction from 1–20 URLs into clean, LLM-ready markdown or text.
`octen chat [prompt]`	Chat completions from leading models, with optional live web search.
`octen embed [text...]`	Text embeddings for semantic search, RAG, and recommendations.
`octen vl-embed <content...>`	Multimodal embeddings from text, images, and video for cross-modal search.

Get API Key

GitHub

npm

​Install

​Authenticate

​Set up your AI agent

​Use Octen from the terminal

Install

Authenticate

Set up your AI agent

Use Octen from the terminal