How to Create Crypto AI Agents With ElizaOS & Gelato
Gelato Team
•
Feb 25, 2025
Introduction
AI agents have ushered in a golden age of interface simplification. Intuitive, user-friendly interfaces accessible to all. The AI agent framework landscape has evolved significantly, with platforms like Eliza, Virtuals, and arc.fun (built on rig framework) leading the way in autonomous AI agent development. These platforms and frameworks are driving the growth of the agentic economy, particularly in Decentralized Finance AI (DeFAI), where AI agents can independently own assets, trade, and form DAOs.
Web3-native AI frameworks, while promising, are held back by fundamental limitations. Data fragmentation across platforms, high gas costs, and limited cross-chain functionality create significant barriers to widespread adoption.
Frameworks such as Eliza are bridging this gap. ElizaOS is a blockchain-agnostic framework that simplifies the creation and deployment of autonomous AI agents across both Web2 and Web3 platforms. ElizaOS has seen significant growth in recent months, with increasing adoption and expanding use cases in areas such as automated trading and community management.
ElizaOS's capabilities can be significantly enhanced through integration with Gelato's Web3 Services infrastructure. Gelato provides key infrastructure components that address common challenges in onchain AI agent development: automated transaction management across EVM chains, gasless operations through its Relay network, verifiable random number generation, and decentralized automation through Web3 Functions. This integration offers developers a practical foundation for building onchain AI agents that can operate effectively across blockchain networks while maintaining security.
Understanding the ElizaOS Framework and Plugins
ElizaOS features a decoupled structure with a core runtime and four key components: adapters, characters, clients, and plugins. Each interfaces with the runtime independently, enabling extensibility without breaking other components.
This modular approach ensures simplicity and extensibility, supporting various model providers, platform integrations, chain compatibilities, and advanced functions.
Understanding ElizaOS Without Reading the Docs
The runtime environment is TypeScript-based and manages the agent's core operations: state, memory, and message processing. It serves as the foundation where all components interact.
How ElizaOS Processes & Parses
ElizaOS implements a flexible architecture combining LLMs with retrieval-augmented generation (RAG) and a modular plugin system. Through its runtime environment, agents can dynamically compose context from conversation history and retrieve knowledge, while extending their capabilities through pluggable components.
Intelligent Components of ElizaOS
Character files use JSON configurations to define agent behavior and capabilities, maintaining traits, knowledge, and interaction patterns.
Integration & Extensibility of ElizaOS
The client module manages message interactions across platforms like Discord, Twitter, Telegram, and Farcaster. Plugins expand the system’s capabilities—adding features like media generation or blockchain integrations—without disturbing the core runtime.
AI Agents & Environments of ElizaOS
Adapters standardize data between runtime and blockchain networks. Agents process messages, maintain state, and execute actions consistently across platforms.
Actions define how agents interact with messages and perform complex tasks like smart contract interactions. Providers supply dynamic context and data. Evaluators assess conversations, build memory, and track goals.
Key Capabilities of ElizaOS
Multi-chain support
ElizaOS supports multiple blockchains via plugins, including Ethereum-compatible chains, Solana, Aptos, Flow, Near, Sui, TON, ICP, zkSync, and more. It integrates GOAT for cross-chain operations and Gelato Relay for gasless transactions across 40+ EVM chains.
Social platform integration
Agents can operate across major platforms like Discord and Twitter while maintaining consistent behavior and memory.
Token/NFT operations and management
Plugins manage token/NFT transfers, swaps, collection deployment, and market calculations. Token and wallet providers handle trading and portfolio management.
Trust score evaluation system
ElizaOS assesses transaction safety by combining token performance data with recommender credibility to calculate trust scores, blocking unsafe swaps or interactions.
Intent recognition system
Eliza’s intent system uses direct action matching and contextual evaluation in parallel to parse both explicit and implied user intent, reducing risks in financial or smart contract interactions.
What ElizaOS V2 Will Bring
The V2 roadmap introduces a separation between platform core and plugin extensions, plus a new Agent Marketplace for token launches and no-code AI creation. It also features a custom liquidity provider solution integrated with the ecosystem’s tokenomics.
Gelato Web3 Services - Enabling AI Agent Infrastructure
Gelato provides foundational infrastructure to bridge deterministic blockchains with dynamic off-chain environments. Its Web3 Functions, Relay, and VRF enable automation, gasless ops, and verifiable randomness.
Notable integrations include SingularityFi, Freysa, and Anomaly—demonstrating Gelato’s role in powering AI-driven Web3 applications.
Core Functionalities
Gelato Functions
Web3 Functions (W3F) automate smart contract tasks with on-chain Solidity, off-chain TypeScript, or fixed transaction automations. Executors trigger them based on contract events.
Gelato Relay
Relay enables gasless transactions via message signing, supported by the 1Balance system that unifies gas costs across chains. Security is ensured with EIP-712 (signed message integrity) and ERC-2771 (forwarder verification).
Gelato VRF
VRF provides verifiable off-chain randomness with cryptographic proofs, using Drand as a beacon. AI agents can use VRF for provably random decision-making.
How to Build a Crypto AI Agent Using Gelato
Open-source code & docs:
What is Coinflip AI?
CoinFlip AI is a demo game showing ElizaOS integrated with Gelato’s Web3 services. Players interact with FlipMaster to place bets on heads/tails, while INK Sepolia contracts handle game logic. Gelato Relay enables gasless bets, Gelato Functions manage round timing, and Gelato VRF determines outcomes.
Setup Developer Environment
Requirements: Node.js 23.3.0, PNPM, and `.env` setup for wallet key, Relay API key, and optionally OpenAI API. Run:
Behind the Scenes
The implementation leverages Relay (gasless), W3F (round automation), and VRF (random outcomes). ElizaOS plugins integrate the agent with blockchain logic, creating an accessible AI-driven UX.
Outlook
AI agents are evolving from basic automation to adaptive participants in finance, gaming, prediction markets, and commerce. Examples include onchain KOLs like $aiXBT and prediction markets like Olas Predict. As agent frameworks expand, they will increasingly drive sophisticated decentralized applications.
Conclusion
ElizaOS combines modular AI frameworks with Gelato Web3 Services, addressing major challenges in cross-platform agent design. The CoinFlip AI game demonstrates practical integration of AI with decentralized infrastructure, showcasing the future of interactive, autonomous, onchain applications.
Developer Library
For developers looking to integrate their applications with Gelato Web3 Services, check out Web3 Functions, Relay, and apply for beta access to VRF! Visit our Discord server for support and follow us on X for updates.