# Services from aialign.halowerk.com on Zero

> aialign.halowerk.com serves 10 paid API services for AI agents, indexed by Zero. Each is callable per call with payment handled by Zero.

Canonical page: https://www.zero.xyz/host/aialign.halowerk.com
Live health (JSON, refreshed every minute): https://www.zero.xyz/host/aialign.halowerk.com/health.json

## Services

- [AIAlign Agent Collusion Detector](https://www.zero.xyz/c/aialign-agent-collusion-detector-d05cf2ab/llms.txt): $0.005/call via x402. Computes pairwise action-agreement statistics (observed, expected, and Cohen's kappa) across multi-agent rounds to flag suspiciously high coordination above a configurable threshold.
- [AI Sycophancy Detector](https://www.zero.xyz/c/ai-sycophancy-detector-25170608/llms.txt): $0.004/call via x402. Detects sycophantic drift in AI responses by comparing cosine similarity between a leading user position and paired independent vs. conditioned responses, reporting the positive similarity shift.
- [AI Align Bias Audit](https://www.zero.xyz/c/ai-align-bias-audit-c36ebb65/llms.txt): $0.004/call via x402. Calculates positive-outcome rates per group, compares each against a reference group, and reports rate differences and selection-rate ratios to surface potential disparate impact.
- [AI Calibration Error Calculator](https://www.zero.xyz/c/ai-calibration-error-calculator-beef1bac/llms.txt): $0.003/call via x402. Computes Brier loss, expected calibration error (ECE), and maximum calibration error (MCE) from a set of confidence scores and binary correctness labels, partitioned into equal-width bins.
- [AIAlign Jailbreak Defense](https://www.zero.xyz/c/aialign-jailbreak-defense-224f10b8/llms.txt): $0.004/call via x402. Scans a prompt against defensive regex categories and returns category labels, a bounded risk score, and a block/review recommendation.
- [AIAlign Goal Drift Detector](https://www.zero.xyz/c/aialign-goal-drift-detector-233168b7/llms.txt): $0.003/call via x402. Computes cosine similarity and normalized L1 difference between initial and current goal weight vectors, flagging drift when cosine similarity falls below a supplied threshold.
- [AIAlign Hallucination Rate - Lexical Coverage Screener](https://www.zero.xyz/c/aialign-hallucination-rate-lexical-coverage-screener-35aa057f/llms.txt): $0.004/call via x402. Tokenizes claims and evidence, removes English stop words, and computes the fraction of unique claim tokens found in evidence, flagging claims below a coverage threshold.
- [AIAlign Memory Sanitizer](https://www.zero.xyz/c/aialign-memory-sanitizer-6315c9a6/llms.txt): $0.003/call via x402. Redacts private keys, credentials, emails, payment card numbers, IPv4 addresses, and phone-like digit strings from text, returning sanitized content with per-category match counts.
- [AIAlign Capability Evaluation – Weighted Pass Rate & Score Aggregator](https://www.zero.xyz/c/aialign-capability-evaluation-weighted-pass-rate-score-aggregator-0f16e17f/llms.txt): $0.003/call via x402. Aggregates caller-labeled test cases into weighted pass rates and weighted scores with deterministic per-category summaries for AI capability evaluation.
- [AI Align Resource Hog Detector](https://www.zero.xyz/c/ai-align-resource-hog-detector-d69b6f3c/llms.txt): $0.003/call via x402. Divides observed resource usage (CPU, memory-time, network, tool calls, wall time) by caller-supplied budgets and ranks agents by their worst overrun ratio

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

- [Zero catalog index](https://www.zero.xyz/llms.txt)