External KI Integration

Use external AI services via browser automation (ChatGPT, Claude, web‑based LLMs) and APIs (Hugging Face Inference, OpenAI‑compatible endpoints) to augment your capabilities.

When to use this skill

• You need to consult an external AI model (ChatGPT, Claude, Gemini, etc.) for reasoning, analysis, or generation tasks.
• The user has granted access to their chat interfaces (e.g., via Chrome Relay attached tab).
• You want to use Hugging Face Inference API (if token provided) for model inference.
• You need to interact with a free AI demo or Space via browser automation.
• The task benefits from a second opinion or specialized model (coding, creative writing, summarization).

Requirements

1. Browser automation – the browser tool with profile="chrome" (user must have attached a tab to OpenClaw Browser Relay).
2. External AI accounts – user must be logged into the target service (ChatGPT, Claude, etc.) in the attached Chrome tab.
3. Hugging Face token (optional) – for Inference API access, stored in ~/.openclaw/openclaw.json or provided as environment variable.
4. Other API keys (optional) – e.g., OpenAI, Anthropic, if user provides them.

Setup

Chrome Relay Attachment

The user must click the OpenClaw Browser Relay toolbar icon on the desired tab (badge ON). Verify attachment:

openclaw browser status

Or via browser tool: browser(action=status, profile="chrome").

Hugging Face Token

If token already stored in config, it will be used automatically. Otherwise, ask user to provide it.

Environment Variables (optional)

For API‑based access, you may set:

export OPENAI_API_KEY="sk-..."
export ANTHROPIC_API_KEY="sk-ant-..."
export HF_TOKEN="hf_..."

Browser Automation for Web UIs

General Pattern

1. Navigate to the service URL (e.g., https://chat.openai.com, https://claude.ai, https://gemini.google.com).
2. Wait for page load, snapshot with refs="aria" to locate UI elements.
3. Find input area (role="textbox", role="textbox" with name "Message", etc.).
4. Type your query using act with ref or selector.
5. Click send/submit button (role="button", name="Send").
6. Wait for response (poll for new text elements, detect loading indicator disappearance).
7. Extract response from the output container (role="article", class "markdown", etc.).
8. Return the extracted text.

Example: ChatGPT via Chrome Relay

// 1. Navigate
browser(action="open", profile="chrome", targetUrl="https://chat.openai.com");

// 2. Snapshot after load
const snap = browser(action="snapshot", profile="chrome", refs="aria", interactive=true);

// 3. Find textbox (adapt ref based on snapshot)
browser(action="act", profile="chrome", request={ kind: "type", ref: "textbox:Message", text: "Your query here" });

// 4. Click send button
browser(action="act", profile="chrome", request={ kind: "click", ref: "button:Send" });