Install
openclaw skills install loopuman-human-tasksConnect your AI agent to real human workers for verification, judgment, content review, or subjective tasks, paid instantly via cryptocurrency.
openclaw skills install loopuman-human-tasksGive your AI agent access to real human workers. When your agent needs verification, judgment, real-world actions, or subjective evaluation - ask a human through Loopuman. Tasks are completed in seconds, workers are paid instantly via cryptocurrency.
curl -X POST https://api.loopuman.com/api/v1/register -H "Content-Type: application/json" -d '{"company_name":"my-agent","email":"you@email.com"}'LOOPUMAN_API_KEY=your_key_hereAsk a human worker to complete a task and wait for their response.
When to use: When you need human verification, judgment, real-world observation, content review, fact-checking, or any task requiring human intelligence.
Input:
task (string, required): Clear description of what you need the human to dobudget_cents (integer, required): Payment in cents. Minimum 10 ($0.10). Typical: 25-100 cents.timeout_seconds (integer, optional): How long to wait. Default: 300 (5 minutes). Max: 3600.Output:
response: The human worker's answerworker_id: Anonymous worker identifiercompleted_at: Timestamp of completionExample:
User: Is this product review genuine or fake? "Amazing product, changed my life, 5 stars!"
Agent: Let me ask a human to evaluate this review.
[calls ask_human with task="Evaluate if this product review is genuine or AI-generated/fake: 'Amazing product, changed my life, 5 stars!' Please explain your reasoning.", budget_cents=50]
Result: "This review appears fake - it's extremely generic with no specific product details, uses common fake review patterns like 'changed my life', and provides no concrete information about what the product actually does."
Post a task for human workers without waiting for completion. Use webhooks or poll for results.
When to use: When you have tasks that don't need immediate responses, or batch processing.
Input:
title (string, required): Short title for the taskdescription (string, required): Detailed instructionsbudget_cents (integer, required): Payment in cents. Minimum 10.category (string, optional): One of: general, data_labeling, content_moderation, transcription, translation, research, writing, image_annotation, surveyOutput:
task_id: UUID of created taskstatus: "open"Check the status and result of a previously posted task.
Input:
task_id (string, required): The task UUID from post_taskOutput:
status: open | in_progress | submitted | completed | cancelledsubmission: Worker's response (if completed)Check your current account balance.
Output:
balance_vae: Balance in VAE (100 VAE = $1.00 USD)balance_usd: Balance in USD