Cross-chain liquid staking comparison: APR rank across major LSDs (stETH, rETH, sfrxETH on Ethereum / mSOL, jitoSOL, bSOL on Solana) for AI agents allocating staked capital. Source: DeFiLlama yields API.

Cross-chain DeFi yield aggregator: top APY pools filtered by symbol / chain / minimum TVL for AI agents optimizing yield-farming allocations. Source: DeFiLlama yields API.

Cross-chain DeFi analytics: protocol TVL with chain breakdown and 7d/30d change for any DeFi protocol (Uniswap, AAVE, Lido, Jupiter, etc.), for AI agents tracking liquidity. Source: DeFiLlama public API.

Cross-chain NFT collection vitals: floor, 24h volume, market cap, holders proxy, and price change for any collection on Ethereum/Polygon/Solana, for AI agents pricing exposure. Sources: CoinGecko NFTs (EVM) / Magic Eden (Solana).

Cross-chain NFT pricing: floor price in native currency and USD across major chains (Ethereum, Polygon, Solana, Arbitrum, Optimism) for any CoinGecko-listed collection. Source: CoinGecko public NFTs API.

Cross-DAO governance activity proxy: proposal velocity, admin/member count, recent voting volume for a Snapshot DAO. NOTE: treasury balance/flow trace requires Etherscan API key (not available in this oracle); this endpoint exposes governance-side signals only. Source: Snapshot Hub.

Cross-DAO governance: voting-power distribution for a Snapshot proposal — top voters by vp, total participation, choice breakdown, for AI agents auditing governance influence. Source: Snapshot Hub GraphQL.

Cross-chain stablecoin tracker: current circulating supply, prev-day/week/month delta, and chain-level distribution for any major stablecoin (USDT/USDC/DAI/PYUSD/FDUSD/etc.). Source: DeFiLlama stablecoins API.

Cross-chain L2 capacity flow proxy: net TVL movement into an L2 chain over 1d / 7d / 30d windows for AI agents tracking capital migration. Note: chain-TVL delta proxy (not raw bridge volume — DeFiLlama's bridges API became paid). Source: DeFiLlama free chain-TVL API.

AI agent support: bias signal detection (gender stereotypes, age stereotypes, nationality blanket statements, profession stereotypes) for agents auditing generated content. Heuristic lexicon, no demographic inference of users, returns per-category counts and a band.

AI agent support: hallucination warning signals in LLM output (fake citations, suspicious URLs, over-precise statistics, contradiction patterns) for agents auditing chained generations. Heuristic-only, no external fact-check; flags candidates for human review.

AI agent support: translation quality coarse score (length-ratio plausibility, numeric/URL/code-block preservation, target script consistency) for agents pre-filtering machine translations. Local-only, no reference corpus, no LLM.

Verify any url using the Cybercentry Web Application Verification (CWAV) API. Returns a scan_id and scan_url for verification via the proxy endpoint

AI agent support: structural JSON diff between two payloads for agents validating tool output drift. Returns categorized additions, removals, type changes, and value changes with JSON-pointer paths (RFC 6901) — no LLM needed, deterministic.

AI agent support: validate an API response against a JSON Schema (draft-07 subset) for agents wiring tools together. Returns per-violation paths, expected vs actual types, and a pass/fail flag — fully local, deterministic, no LLM.

AI agent support: lightweight language detection with confidence score for short texts, for agents routing multilingual input. Returns top-N candidate languages and a normalized confidence — script-distribution heuristic, no external API, deterministic.

AI agent support: validate a multi-agent handoff document against required structure (frontmatter, mandatory sections, no leaked secrets) for collaborative agent workflows. Returns missing sections, parsed frontmatter, and a pass/fail flag — fully local.

AI agent support: compute recommended concurrency, delay, and exponential backoff parameters for a target API given its rate limit, for agents orchestrating bulk calls. Returns concurrency, baseBackoffMs, capBackoffMs, jitter, and expected throughput — purely deterministic.

AI agent support: explain a regular expression in plain English by parsing its AST into atoms (anchors, char classes, quantifiers, groups, alternations) for agents debugging tool patterns. Returns ordered element list with descriptions — fully local, no LLM.

AI agent support: multilingual sentiment scoring via built-in mini-lexicon (en/ja/es/de/fr) for agents triaging user messages. Returns numeric score, normalized polarity (positive/neutral/negative), and detected language hint — local-only, no model API.