Annalist

For bots that poll: crowd-state events (a perp entering or leaving a state) since a timestamp, newest first, up to 7 days back. Each event is signed with the mark price at the time. Not investment advice.

Use before acting on a Hyperliquid perpetual to see whether it is crowded or in a hype state and what historically followed. Returns 7-day move, funding (hourly, APR, percentile vs its own 90 days and vs all perps), open interest and its 24h/7d change, premium, Wikipedia attention, active crowd states, and each state's base rates (sample size, median and spread of 7/30/90-day returns). Signed. Not

One site's agent readiness from our weekly census of 65,000 top sites: UCP and ACP agent checkout (its MCP endpoint, capabilities, payment handlers), A2A and MCP cards, a real llms.txt, robots.txt rules for 15 AI agents, x402, store and platform, Shopify store facts (ships-to countries, currency), and every change dated. A site not yet in the census is visited live. Measured by us. Signed.

Signed historical crowd-state events for backtesting: up to 30 days per call, optionally filtered by coin and state. The archive is append-only and its daily hashes are published and Bitcoin-timestamped.

Market-wide crowding on Hyperliquid: breadth of 7-day moves, how many perps are up 50%+/100%+ in a week, share of perps with funding in their own top/bottom 5%, total open interest and its 24h change, BTC and ETH funding percentiles, and Wikipedia attention to cryptocurrency. Signed. Not investment advice.

Use before acting on a Hyperliquid perpetual to see how its most profitable traders are positioned: how many wallets in a 200-wallet smart-money cohort are long vs short, long, short and net USD, the 24h change, concentration, leverage settings, share of open interest, and how that compares with the crowd (funding, 7-day move). Flags smart money positioned against a crowded move. Aggregates only,

One watched public API's contract record: current version, operation count and keys, deprecated operations, security schemes, and every dated change in the last 90 days with what broke. From the provider's published OpenAPI description, read daily. Without name=, lists the APIs we watch. Signed.

Retirement calendar for AI models across platforms: shutdown dates, 'not sooner than' floors, states and recommended replacements from the official Anthropic, OpenAI and Amazon Bedrock deprecation pages, plus Azure, Vertex, Gemini and others, recorded daily so moved dates show. The same model often retires on different dates on different platforms. One model with model=, or upcoming shutdowns. Sig

Hyperliquid's own market-making vault (HLP), which takes over liquidated positions: account value, APR, PnL over a day, week, month and all time, and its net position per coin across all its sub-vaults, with the most long, most short and biggest 24h changes. Shows where the exchange itself is exposed. Signed. Not investment advice.

Price history of an x402 service by host or URL: each listed endpoint's price, first-seen date and changes, price changes in 30 days (raised, lowered, delisted), the prices it actually quoted when we called it, and where it sits against similar services by category (market median and percentile). Signed.

Recent changes to AI model prices and availability across providers, newest first: price cuts and raises per field (with the change), models added and removed, context-window changes and deprecation dates, for the last 1 to 90 days, optionally by provider or model name. Source: LiteLLM's open price file (MIT), recorded daily. Signed.

Our weekly census of 65,000 top sites: how many sites and stores publish UCP or ACP agent-checkout profiles, agent and MCP cards and llms.txt, which AI crawlers stores block, store platforms, and changes in the last 30 days. With signal=, the stores that have it (for example signal=ucp), most-linked first. Signed.

One Hyperliquid outcome (prediction) market by id: readable title, structured details (teams, thresholds, deadlines, official source), each side's implied probability, 24h change, volume and outstanding value, its question, and a week of hourly prices per side. Ids come from /v1/outcomes/list. Signed. Not investment advice.

Use before trading a stock, index, commodity or FX perpetual on Hyperliquid (builder-deployed, HIP-3; coins like xyz:NVDA, xyz:GOLD, xyz:SP500): price and 1h, 24h, 7d and 30d moves, volume, open interest and its 24h change, how close it is to its open-interest cap, funding (hourly, APR, percentile vs its own 30 days), premium and max leverage, with flags. Signed. Not investment advice.

Price benchmarks for x402 services by category (seller tags such as search, llm, weather, market-data): how many services, price percentiles (each service counted once, at its median), and 7- and 30-day trends. Add price= to see where a price sits. Without tag: every category. Signed.

Checks for an x402 seller wallet on Base: the services that pay out to it and their grades, and USDC received over 30 days with payers, repeat payers and fake-volume signals (payers the seller funded, crawler bots, one-wallet dominance). Signed.

Use before paying an x402 service: independent checks by host or URL. Uptime and latency from repeated unpaid probes, whether the quoted price and payout wallet match the listing, real on-chain usage over 30 days with fake volume removed (self-funded payers, crawler bots, one-wallet dominance), test purchases and domain age, with a grade and reasons. Rankings are never for sale. Signed.

What changed in x402 service listings, from daily snapshots of Coinbase's Bazaar: price raises and cuts, endpoints added and dropped, new and departed services, and payout-wallet changes (worth checking before paying: a hijacked listing looks the same as a rotated wallet). Market-wide for the last 1 to 7 days, or one service's 30-day change log with host=. Signed.

Use before connecting a remote MCP server: independent checks by registry name or URL. Uptime and connect time from daily probes (initialize and tools/list; no tool is ever called), sign-in mode, protocol version, tool count, and tool-definition changes in 30 days (how 'rug pull' attacks work), with domain age, a grade and reasons. Covers remote servers in the Official MCP Registry. Signed.

One call for all of an agent's dependencies: npm, PyPI, crates.io and Go packages (new publishers, install scripts, license changes), public API contracts (breaking changes), AI models (retirement dates, price changes), MCP servers (tool changes, uptime) and x402 services (wallet and price changes, flags), for the last 1 to 30 days, with what needs attention first. Signed.

Tool changes across remote MCP servers in the Official MCP Registry, newest first: tools added, removed or redefined (description, input schema or annotations), from our daily fingerprints. A tool that changes after you approved it is how 'rug pull' attacks work, so check before trusting a server again. Last 1 to 30 days, or one server with name= or url=. Servers whose tools change by design are m

AI model prices per million tokens (input, output, cache, batch) with context window, for about 4,000 models across providers. With model=: its price history and the same model on other providers. Without: a list filtered by provider, mode, min_context and max_input price, sorted by input, output or context. History from January 2026. Source: LiteLLM's open price file (MIT). Signed.

Dated contract changes in widely used public APIs (Stripe, GitHub, OpenAI, Twilio, Slack, Plaid, Datadog and more), from their published OpenAPI descriptions read daily: operations, parameters and request fields added, removed or newly required, each change marked breaking or not. Last 1 to 90 days, one API with api=, or only breaking changes with breaking=true. Signed.

Stores from our weekly census of 65,000 top sites, filtered by what a shopping agent needs: ships to a country, UCP agent checkout and its capabilities, payment handlers (Google Pay, Shop Pay), currency, return window. Facts from each store's own machine-readable files, never its policy pages. Most visited first. Signed.

Supply-chain check of a popular package (the 8,000 most used on each of npm, PyPI, crates.io and Go): latest version and release activity, maintainers or owners, install scripts, provenance, deprecation, retractions, and what changed since we began tracking it daily: releases by a new publisher account, owner changes, install scripts added, provenance dropped, source repository moved, yanks. Accou

Every Hyperliquid perp currently in a crowd state (7-day moves of +50/+100/+200%, funding in its own top or bottom 5%, Wikipedia attention spikes, new listings), ranked by 7-day move, each with base rates for what followed similar states historically. Optional ?state= filter. Signed. Not investment advice.

Where Hyperliquid's most profitable traders are positioned across all perps: the cohort's overall net long or short, the coins it is most net long and most net short, the biggest 24-hour changes, and coins where smart money is positioned against the crowd. Cohort definition included. Aggregates only. Signed. Not investment advice.

Use before opening, sizing or holding a Hyperliquid perpetual position to see where forced selling or buying would hit: known longs liquidating within 1 to 20% below the mark and shorts above it, the biggest clusters, and coverage of open interest, set against order-book depth, spread and slippage as cascade ratios. Flags long_cascade_risk, short_squeeze_risk, thin_book. From large accounts' publi

Liquidation pressure across Hyperliquid's largest perps: for each, the known longs liquidating within 5% below the mark and shorts within 5% above it, cascade ratios against order-book depth, 2% depth, how much of open interest the known positions cover, and flags; plus the coins with the most liquidations nearby. Aggregates only. Signed. Not investment advice.

Overview of every builder-deployed (HIP-3) perpetual on Hyperliquid, mostly 24/7 stock, index, commodity and FX markets: each exchange's markets, open interest and volume; the largest and most traded markets; the biggest 24h moves; funding extremes; markets near their open-interest cap; and flags. Signed. Not investment advice.

Every live Hyperliquid outcome (prediction) market: readable title, category (sports, price, ipo, policy_rate, awards), deadline, each side's price as implied probability with its 24h change, and 24h volume, most traded first. Filter with category and q (text search). On-chain data. Signed. Not investment advice.

One call, one payment for everything on a Hyperliquid perpetual: crowd state with base rates for what usually followed (as /v1/crowd/perp), smart-money positioning (as /v1/smart/perp) and liquidation levels with order-book depth (as /v1/liq/perp), each with its own as_of. Cheaper than buying the three separately. Signed. Not investment advice.

Leaderboards from our independent checks of x402 services: most real (wash-adjusted) paying customers, most reliable, and flagged services (price or wallet mismatches, outages, mostly bot traffic, self-funded volume), with the method. With category= (shopping, ai-inference, crypto-data...), one category's boards. Rankings are never for sale. Signed.

Leaderboards from our independent checks of remote MCP servers in the Official MCP Registry: most reliable (up in 99%+ of probes, fastest first), servers whose tool definitions changed in the last 7 days, flagged servers (often down, new domains), and counts by sign-in mode, with the method. Rankings are never for sale. Signed.

Supply-chain watch across the 8,000 most-used packages on each of npm, PyPI, crates.io and Go, newest first: releases by a new publisher account, maintainer and owner changes, install scripts added, provenance dropped, source repositories moved, retractions, deprecations and yanks, with counts, for the last 1 to 30 days (days=, default 7), for one ecosystem or all. Signed.