Neko represents a pioneering approach within the Hyperliquid ecosystem, functioning as the first DeFAI (Decentralized Finance + AI) Swarm. It’s architected as an intelligent, hybrid system seamlessly integrating AI Agents with Smart Contracts to interact optimally across both the Hyperliquid L1 Orderbook (HyperCore) and the programmable HyperEVM.

Our core mission is to serve as the Cognitive Gateway to Hyperliquid, transforming complex DeFi operations into intuitive user experiences. Where HyperEVM makes the orderbook programmable, Neko leverages this foundation to make it profoundly more intelligent, automating complexity and optimizing execution.

At a high level, Neko’s architecture can be understood through interconnected layers:

  1. The Interaction Layer (Social Agents):
    • This is the primary user touchpoint. Users interact with Neko via simple commands or natural language mentions on familiar social platforms like X, Discord, and Telegram.
    • This social agent is an Eliza Agent will serve an alpha distillation agent (think AIXBT for Hyperliquid) as well as an ad network
      • compose this tweet: @neko_hl gneko — this will send a link to the application for users to start trading
      • this agent will provide an iFrame X modal (more information soon)
  2. The Coordination Layer (Orchestrator Agent):
    • Sitting at the heart of the swarm, the Neko Orchestrator Agent acts as the central brain. It receives parsed user intent from the Interaction Layer and formulates a strategic plan for execution.
    • It coordinates tasks, manages state, and delegates specific actions to specialized agents within the Execution Layer. It also interfaces with external partner APIs like Hypurr Bot or pvp.trade where necessary.
  3. The Intelligence Layer (AI & ML Core):
    • This layer provides the cognitive power enabling Neko’s intelligent decision-making. It comprises:
      • Proprietary Models: Machine Learning models (e.g., LSTM, ARIMA, Prophet, GNNs) analyze market data, predict trends, assess risk, and optimize strategies.
      • AI Memory & Retrieval (RAG/CAG): Neko utilizes Retrieval-Augmented Generation (RAG) to fetch real-time data, contextual information, and semantic knowledge from vector databases (Vector DB / Semantic Memory). Cache-Augmented Generation (CAG) leverages heuristics and frequently accessed data (like agent transaction history or optimized parameters) for efficient decision-making. This allows agents to recall past actions and learn effective strategies. (Refer to Image 2 for AI Agent System detail).
      • Reinforcement Learning (RL): Models are continuously refined through feedback loops (potentially using techniques like DPO), allowing the system to adapt and improve its execution and risk management over time.
  4. The Execution Layer (DeFi Multiagent System & Contracts):
    • This layer translates the Orchestrator’s plan into on-chain actions.
    • Specialized Agents (Architect Agents / RIG Agents / Neko Bots): These agents possess specific capabilities, such as executing trades via optimal routing (Shogun architecture), managing assets within yield vaults (Nucleus Vaults, Agentic Vaults), handling complex collateralization for perpetuals, or interacting directly with specific HyperEVM protocols (LST, Lending, CDP, AMMs) and the Hyperliquid L1 orderbook via their respective APIs. They employ multi-step workflows involving planning and tool-calling.
    • Smart Contracts: Secure and audited smart contracts (from the Nucleus vault architecture) form the bedrock for holding user assets and executing specific, predefined DeFi logic on HyperEVM.