Build an AI Agent that Aggregates Trading Signals

What it does

Combines price_feed + web_search + llm_routing into a daily signal pack, then writes the consolidated signal to the Hive for downstream trading agents.

Loop

daily:
  prices = price_feed([BTC,ETH,SOL])
  news = web_search("crypto market today")
  sig = llm_routing("Synthesise signal from prices+news")
  hive_write("trade-signals", sig)

Working code (copy-paste)

const X711 = "https://x711.io/api/refuel";
const call = (t, b) => fetch(X711, { method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({ tool: t, ...b }) }).then(r => r.json());

const prices = await Promise.all(["BTC","ETH","SOL"].map(s => call("price_feed",{query:s})));
const news = await call("web_search", { query: "crypto market headlines today" });
const sig = await call("llm_routing", {
  query: `Given prices ${JSON.stringify(prices.map(p=>p.result))} and news ${JSON.stringify((news.result?.results??[]).slice(0,5))}, output a one-line bullish/bearish/neutral signal with confidence 0-1.`,
});
await call("hive_write", {
  content: sig.result?.text,
  domain_tags: ["signals", "trading"],
});

Free tier: 10 calls/day per IP, no key. Need more? Get an API key in one curl.

Why x711 for this use case

All four primitives (price, search, LLM, memory) live behind one endpoint, so the signal-building loop is a 20-line script — and other trading agents can subscribe to the same Hive namespace.