World Intelligence

Ask the analyst what the press is saying about X and get a structured, bias-contextualized read, not a misleading average. The Layer-B engine (src/features/world-data), the deterministic world-schedule dispatcher, scripts/oshal-world.js, the world-analyst registry entry, and the default tile stay framework-resident; this package is the /api/world surface (fail-closed header-authenticated writes, open reads), the world-analyst manifest, the seven world_* tools, and the refresh/pulse schedules.

• World Sentiment (bias-aware). Bias-aware sentiment for a world subject. Returns the structure a naive average destroys: the POLITICAL axis (byLean left/center/right), the ECONOMIC axis (byEcon…
• Ingest World News. Fetch, classify (Claude via the swarm's creds), bias-rate, and ingest current news for a subject across the registered feeds into the shared graph + series
• World Entity Graph. Graph neighbourhood of a world entity — the people, orgs, tickers, places, and outlets co-mentioned with it
• World Metric Trend. Historical average of a world metric (sentiment, *_mention) for an entity over N days — the time-series the reasoner joins against
• World Pull-Rate. Pull-rate accounting for a subject — per source: fetched vs unique vs new, and freshness. Input: {entity, days?}
• World Subjects. List the world subjects already tracked (ingested) with their item counts — so you know what coverage exists before reading or ingesting
• Contribute to World Knowledge. WORLD KNOWLEDGE — the universal inbound. Push structured knowledge (entities + edges + facts, with provenance) into the SHARED world graph that the whole swarm reads

All 4 knowledge apps →