Agent

Agents are the foundational elements of the CYNE AI framework, enabling seamless, intelligent, and autonomous interactions within the Solana ecosystem.

Example: State Methods

Compose Initial State:

const state = await runtime.composeState(message, {
    additionalContext: "custom blockchain context",
});

Update State:

const updatedState = await runtime.updateRecentMessageState(state);

Best Practices:

Use composeState to initialize new states.
Update states dynamically during interactions with updateRecentMessageState.
Cache frequently accessed data to enhance performance.

Memory Systems in CYNE AI

Memory systems provide agents with contextual understanding and continuity.

Types of Memory:

Message History: Tracks past interactions for conversational continuity.
Factual Memory: Stores specific details like wallet activity or token preferences.
Knowledge Base: Retains general knowledge about Solana, DeFi, and NFTs.
Relationship Tracking: Builds rapport by storing user-agent interaction history.

Memory Managers:

CYNE AI provides specialized memory managers:

messageManager: Tracks conversation history.
descriptionManager: Stores user profiles and descriptions.
loreManager: Retains agent knowledge and backstory.

Example: Memory Management

const memoryManager = runtime.getMemoryManager("messages");

// Store memory
await memoryManager.createMemory({
    id: messageId,
    content: { text: "Analyzed a 1M SOL whale transaction" },
    userId: "user123",
    roomId: "room123",
});

Evaluation System

The evaluate method processes input, evaluates responses, and determines actionable outcomes.

Example: Evaluation

const evaluationResults = await runtime.evaluate(message, state, didRespond);

Best Practices for Agent Implementation

Use Randomized Memory: For more dynamic agent responses.
Optimize Memory Usage: Clean old data periodically to avoid performance bottlenecks.
Handle Errors Gracefully: Log errors to maintain stability.
Follow Immutability Principles: For state management to ensure reliability.

Memory Systems in CYNE AI

Evaluation System

Best Practices for Agent Implementation

Further Reading and Resources