Data Ingestion – Background polling across 20 intelligence layers. WebSocket-first for real-time data, REST as fallback.Intelligence Cache – Structured, queryable representation of current market state indexed by asset. All UI and agent queries read from cache first. Direct API requests are the last resort.Agent Reasoning Engine – Reads from cache, reasons about market state, generates proposals, monitors positions, writes lessons. LLM-agnostic via BYOLLM. Skill files encode the agent’s knowledge – versioned, updatable, shared across the network.Interaction Layer – The terminal UI. Conversational interface where the agent panel is the primary interaction surface. Chart and overlays provide supporting context for the conversation.Collective Learning Layer – Lesson library, pattern extraction, skill file updates. Individual insight becomes collective intelligence.
The data stack behind each agent comprises hundreds of individually mapped endpoints across 50+ specialized providers. Every market on Hyperliquid is continuously monitored, with data refreshing as frequently as every second. This is not a collection of API keys – it is a purpose-built intelligence infrastructure.For component details, see Agent Design, Intelligence Layers, and Terminal Design.
