Staking Letter #11: AI-Powered Staking with Eliza Framework
December 4th, 2024

StaFi LSaaS has taken a significant stride forward with the integration of an advanced Validator Selection AI Agent. This innovative solution leverages leading Large Language Models (LLMs) to optimize validator delegation decisions, now available in the LSaaS Modular App Store.

We're excited to announce StaFi AI's next phase of development. Our team is building a sophisticated bot on the Eliza framework, specifically designed to support Liquid Staking Token (LST) and staking-related actions. We're actively exploring expanded use cases to amplify the agent's utility and impact.

Understanding AI Agent

In a LLM-powered autonomous agent system, LLM functions as the agent’s brain, complemented by several key components:

  • Planning

    • Subgoal and decomposition: The agent breaks down large tasks into smaller, manageable subgoals, enabling efficient handling of complex tasks.

    • Reflection and refinement: The agent can do self-criticism and self-reflection over past actions, learn from mistakes and refine them for future steps, thereby improving the quality of final results.

  • Memory

    • Short-term memory: I would consider all the in-context learning (See Prompt Engineering) as utilizing short-term memory of the model to learn.

    • Long-term memory: This provides the agent with the capability to retain and recall (infinite) information over extended periods, often by leveraging an external vector store and fast retrieval.

  • Tool use

    • The agent learns to call external APIs for extra information that is missing from the model weights (often hard to change after pre-training), including current information, code execution capability, access to proprietary information sources and more.

Introducing Eliza: A Game-Changing Multi-Agent Framework

Eliza is a powerful multi-agent simulation framework designed to create, deploy, and manage autonomous AI agents. Built with TypeScript, it provides a flexible and extensible platform for developing intelligent agents that can interact across multiple platforms while maintaining consistent personalities and knowledge.

The Eliza Era: AI Next Phase Roadmap

Our commitment to the Eliza framework is rooted in its robust crypto-native capabilities. By seamlessly integrating critical tools like the Coinbase SDK and Solana operations (including advanced transaction handling and Jupiter integration), we're setting a new standard for agile crypto application development.

Current AI agents fall short in handling Liquid Staking Token (LST) specific actions. StaFi is exploring solutions to address these limitations by developing comprehensive features that enable:

  • Seamless staking and unstaking processes

  • Intelligent multi-LST combination strategies

  • PayFi Integration: Transforming LSTs into dynamic yield-bearing instruments

We also invite our community to be co-creators in this technological journey. Your feedback, suggestions, and perspectives will be instrumental in shaping the future of StaFi's AI.

About StaFi

StaFi is a leading Liquid Staking infrastructure provider and protocol for PoS chains. Its Liquid Staking as a Service (LSaaS) framework enables developers to create Liquid Staking Tokens (LSTs) and Liquid Re-staking Tokens (LRTs) across ecosystems like ETH, EVM, BTC, CosmWasm, and SOL. By issuing rTokens (e.g., rETH, rMATIC, rBNB), StaFi unlocks the liquidity of staked assets, allowing users to earn staking rewards while retaining the flexibility to engage in DeFi. With support for major blockchains such as Ethereum, Solana, Polygon, BNB Chain, and Cosmos, StaFi bridges liquidity and security in Proof-of-Stake networks.

Read more about StaFi 2.0.

Subscribe to StaFi
Receive the latest updates directly to your inbox.
Mint this entry as an NFT to add it to your collection.
Verification
This entry has been permanently stored onchain and signed by its creator.
More from StaFi

Skeleton

Skeleton

Skeleton