HARPA Grid — Browser Automation API

HARPA Grid lets you orchestrate real web browsers remotely. You can scrape pages, search the web, run built-in or custom AI commands, and send AI prompts with full page context — all through a single REST endpoint.

Prerequisites

The user must have:

1. HARPA AI Chrome Extension installed from https://harpa.ai
2. At least one active Node — a browser with HARPA running (configured in the extension's AUTOMATE tab)
3. A HARPA API key — obtained from the HARPA extension AUTOMATE tab. The key is provided as the

   HARPA_API_KEY

   environment variable.

If the user hasn't set up HARPA yet, direct them to: https://harpa.ai/grid/browser-automation-node-setup

API Reference

Endpoint:

POST https://api.harpa.ai/api/v1/grid

Authorization: Bearer $HARPA_API_KEY

application/json

Full reference: https://harpa.ai/grid/grid-rest-api-reference

Actions

1. Scrape a Web Page

Extract full page content (as markdown) or specific elements via CSS/XPath/text selectors.

Full page scrape:

curl -s -X POST https://api.harpa.ai/api/v1/grid \
  -H "Authorization: Bearer $HARPA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "action": "scrape",
    "url": "https://example.com",
    "timeout": 15000
  }'

Targeted element scrape (grab):

curl -s -X POST https://api.harpa.ai/api/v1/grid \
  -H "Authorization: Bearer $HARPA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "action": "scrape",
    "url": "https://example.com/products",
    "grab": [
      {
        "selector": ".product-title",
        "selectorType": "css",
        "at": "all",
        "take": "innerText",
        "label": "titles"
      },
      {
        "selector": ".product-price",
        "selectorType": "css",
        "at": "all",
        "take": "innerText",
        "label": "prices"
      }
    ],
    "timeout": 15000
  }'

Grab fields:

.class

#id

//h2

auto

css

xpath

text

all

first

last

innerText

textContent

innerHTML

outerHTML

href

value

id

className

attributes

styles

[attrName]

(styleName)

2. Search the Web (SERP)

Perform a web search. Supports operators like

site:

intitle:

curl -s -X POST https://api.harpa.ai/api/v1/grid \
  -H "Authorization: Bearer $HARPA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "action": "serp",
    "query": "OpenClaw AI agent framework",
    "timeout": 15000
  }'

3. Run an AI Command

Execute one of 100+ built-in HARPA commands or a custom automation on a target page.

curl -s -X POST https://api.harpa.ai/api/v1/grid \
  -H "Authorization: Bearer $HARPA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "action": "command",
    "url": "https://example.com/article",
    "name": "Extract data",
    "inputs": "List all headings with their word counts",
    "connection": "HARPA AI",
    "resultParam": "message",
    "timeout": 30000
  }'

• name

  — command name (e.g.

  "Summary"

  ,

  "Extract data"

  , or any custom command)

• inputs

  — pre-filled user inputs for multi-step commands

• resultParam

  — HARPA parameter to return as result (default:

  "message"

  )

• connection

  — AI model to use (e.g.

  "HARPA AI"

  ,

  "gpt-4o"

  ,

  "claude-3.5-sonnet"

  )

4. Run an AI Prompt

Send a custom AI prompt with page context. Use

{{page}}

curl -s -X POST https://api.harpa.ai/api/v1/grid \
  -H "Authorization: Bearer $HARPA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "action": "prompt",
    "url": "https://example.com",
    "prompt": "Analyze the current page and extract all contact information. Webpage: {{page}}",
    "connection": "CHAT AUTO",
    "timeout": 30000
  }'

Common Parameters

scrape

serp

command

prompt

serp

"r2d2"

"r2d2 c3po"

"5"

"*"

command

prompt

Node Targeting

• Omit

  node

  to use the default node

• "node": "mynode"

  — target a specific node by ID

• "node": "node1 node2"

  — target multiple nodes

• "node": "3"

  — use first 3 available nodes

• "node": "*"

  — broadcast to all nodes

Async Results via Webhook

Set

resultsWebhook

{
  "action": "scrape",
  "url": "https://example.com",
  "resultsWebhook": "https://your-server.com/webhook",
  "timeout": 15000
}

Tips

• Scraping behind-login pages works because HARPA runs inside a real browser session with the user's cookies and auth state.
• Use the

  grab

  array with multiple selectors to extract structured data in a single request.
• For long-running AI commands, increase

  timeout

  (max 300000ms / 5 min) or use

  resultsWebhook

  .
• The

  {{page}}

  variable in prompts injects the full page content — use it to give AI context about the current page.