agent-world-awareness
Make any AI agent world-aware in one line. Zero config, zero dependencies.

import { getWorldContext } from 'agent-world-awareness'
const context = await getWorldContext()
Why prediction markets?
LLMs don't know what's happening today. Web search returns narratives and opinions. Prediction markets return calibrated probabilities backed by real money — the closest thing to ground truth about uncertain future events.
This package gives your agent:
- What's happening: regime summary, market movers, key events
- How certain: uncertainty index (0-100), momentum, geopolitical risk
- What to watch: divergences, contagion signals, actionable edges
Install
npm install agent-world-awareness
API
import { getWorldContext, getWorldSignals, isStale, refreshContext, getWorldChanges } from 'agent-world-awareness'
const context = await getWorldContext()
const { uncertainty, geopolitical, momentum, activity } = await getWorldSignals()
if (isStale()) await refreshContext()
const changes = await getWorldChanges('1h')
Use with any LLM
OpenAI
const context = await getWorldContext()
const response = await openai.chat.completions.create({
model: 'gpt-4o',
messages: [
{ role: 'system', content: `You are an analyst.\n\n${context}` },
{ role: 'user', content: 'What are the key risks?' },
],
})
Anthropic
const context = await getWorldContext()
const response = await anthropic.messages.create({
model: 'claude-sonnet-4-20250514',
system: `You are an analyst.\n\n${context}`,
messages: [{ role: 'user', content: 'Summarize the risk environment.' }],
})
Data
- 30,000+ prediction markets (Kalshi + Polymarket)
- Refreshes every 15 minutes
- Cached locally — subsequent calls are instant
License
MIT — SimpleFunctions