Human For AI is a human endpoint for AI agents — a personal homepage for the agent era. AI agents, automation systems, and developers can discover a real human for verification, testing, research, judgment, and real-world help through machine-readable interfaces.
Show off your agentic readiness — the badge auto-updates when your score changes.
llms.txt Content
# Human For AI
> Human For AI is a human endpoint for AI agents — a personal homepage for the agent era. It provides human-in-the-loop services for AI agents, automation systems, and developers: real-world verification, product testing, human judgment, data collection, AI output review, research, and local physical-world tasks, performed by one verified human operator. All services are free during the current proof-of-concept pilot. No authentication is required; every task is reviewed by the human before acceptance.
Key facts:
- Task submission: POST https://humanforai.dev/api/v1/tasks (JSON; returns a task_id for status polling). contact_email must be a real mailbox — placeholder domains (example.com etc.) are rejected and the domain is MX-checked
- No mailbox? This service is deliberately reachable by autonomous agents without email: submit with delivery:"status_poll" (and no contact_email) — the deliverable arrives as text in operator_notes via GET /api/v1/tasks/{task_id}; the task_id is the only key to the result (budget: 1 such task per client per day)
- Task status: GET https://humanforai.dev/api/v1/tasks/{task_id}
- Contact the operator: POST https://humanforai.dev/api/v1/messages (reply_to is REQUIRED — it is the only way the operator can answer)
- Signed receipts: every delivered task carries `receipt` (compact JWS, EdDSA) binding the deliverable's sha256 to the task's lifecycle timestamps, plus `deliverable_sha256`. Verify offline against https://humanforai.dev/.well-known/jwks.json — no account, no callback. It proves the deliverable is unaltered and came from humanforai.dev; it does not prove the timestamps are independently attested (they are this service's own signed assertion)
- Anti-abuse: duplicate submissions within 24h return 409; per-client hourly/daily rate limits return 429; repeat abusers are blocked (403). One small test task is welcome — bulk synthetic submissions are not
- MCP server (streamable HTTP, no auth): https://humanf
OpenAPI Spec (preview)
{
"openapi": "3.0.3",
"info": {
"title": "Human For AI API",
"version": "1.7.0",
"description": "A human endpoint for AI agents. Submit tasks that need physical presence, human perception, or human judgment — real-world verification, product testing, AI output review, data collection, local physical-world errands — and a verified human operator performs them. All services are FREE during the proof-of-concept pilot. No authentication is required; every task is reviewed by the