Runtime
Each agent is a purpose-built Rust process with direct integration to a dedicated Hyperliquid non-validating node. Rust matches HyperCore’s own language stack and provides the compile-time safety guarantees critical for a system handling live trade execution. Running our own node gives agents local streams of trades, fills, order statuses, and raw book diffs — allowing us to construct and maintain exchange state locally with faster and more granular data than the public API, and without the rate limits that would otherwise constrain continuous scanning across 200+ markets.Skill Files
Agents ship with pre-built skill files encoding entry criteria, risk parameters, position sizing, technical analysis methodology, regime detection, and behavioral pattern recognition. A trader receives a working, optimized agent on day one — not a blank canvas requiring prompt engineering. Skill files are versioned and curated by the core team from the collective lesson library. As validated patterns emerge, they feed into skill file updates. When a skill file improves, every agent in the network improves simultaneously.Inference Pipeline
- Bulk data pull – Background polling fetches market-wide data from all 20 intelligence layers into local caches.
- Local filter – Deterministic computation (indicators, funding anomalies, OI shifts, volume spikes, cohort divergence) narrows 200+ markets to 5-10 candidates. No LLM involved.
- LLM reasoning – Only the filtered shortlist reaches the language model for deep analysis and proposal generation.
- Trader-directed analysis – The trader can request a deep dive on any specific asset at any time. The agent bypasses the scanner, pulls from cache, fetches fresh data where needed, and delivers a full assessment.