Detect real-time crypto arbitrage opportunities across centralized exchanges

Verify Boundary Guard receipt packages and supplied x402 payment metadata before an agent trusts settlement evidence.

Vault evaluator for Hyperliquid copy-trading vehicles. POST {vault}. Returns composite vault_quality_score (0-100) factoring: leader's own trading skill, depositor concentration (top-1 share = whale-dependent), redemption pressure (withdrawals/deposits ratio), commission rate. Plus lifetime stats and top 5 depositors. Built for copy-trade-vetting bots — NO equivalent service exists; vault data is unique to perps DEXs.

Asset scoring engine. Call this before asset selection or allocation. Returns liquidity, structural stability, role classification, and composite quality scores for candidate assets, shaped by the requested portfolio segment.

Start a deep research job on any longevity or aging topic. Aubrai orchestrates sub-agents for literature synthesis, data analysis, and hypothesis generation — returns a conversation ID to poll for the full report.

Risk policy engine. Call this when portfolio constraints and segment filters must be computed for a supplied risk tolerance, timeframe, and optional portfolio segment. Returns exposure caps, stablecoin floor, risk budget, authorization constraints, and segment-aware universe guidance.

Portfolio rebalance engine. Call this after allocation or on a monitoring schedule with current holdings. Returns target-vs-current drift and the adjustments required to rebalance within policy constraints for the requested portfolio segment.

Audit a multi-step agent workflow for risk, declared spend, missing receipts, and policy evidence before it runs.

Monitor whale movements including buys, sells, and transfers for any token

Basic ERC-8004 agent trust score. Returns score 0-100, component breakdown, and agent metadata. For full Sybil forensics use /trust/ instead.

Full score time-series for an agent. Returns all historical trust score snapshots, trajectory (7d/30d change), and volatility (standard deviation).

OpenAI-compatible chat completions backed by DeepSeek. Answers open-ended questions and returns reasoned analysis. Pass standard {messages: [...]} body. Returns OpenAI-style choices array.

5-day weather forecast with 3-hour intervals including precipitation probability

🎰 LuckyMint: Mint 1 reward token with chances for refunds and jackpots!

Time-bucketed prediction market volume and trade-count by exchange.

PDF to Markdown extraction API. POST {url} to extract any PDF. $0.001 per page.

Look up posts, analyze profile metrics, and measure engagement on Twitter/X

Remove or replace image backgrounds and generate segmentation masks for e-commerce and creative automation

Compare restaurants, build a cart, estimate price, and place a (human-approved) order across multiple restaurants.

Screen text for prompt injection — detects 10 attack categories (instruction override, role hijack, jailbreak, data exfiltration, etc.) with risk level and confidence score