ChainClaw: A Layered Agent Framework for Reliable On-Chain Execution

2026-08-06

AI Summary

This work addresses three core challenges faced by general-purpose large language model agents in blockchain environments: insufficient reactivity, irreversible operations, and unobservable system states. To overcome these limitations, the authors propose ChainClaw, the first hierarchical agent framework specifically designed for blockchain settings. ChainClaw integrates an event-driven orchestration layer, simulation-based safe reasoning, and on-chain monitoring within a unified runtime architecture, augmented by a cross-layer memory mechanism to ensure coherent decision-making. The framework establishes a secure execution pipeline through key components including event ingestion, transaction simulation, action safeguarding, on-chain read adapters, and transaction monitoring. Evaluated across seven tasks spanning four distinct categories, ChainClaw demonstrates substantial improvements over existing approaches in both safety and task completion rates.

Abstract

General-purpose large language model agents have achieved strong performance on tool-augmented tasks, yet they rely on assumptions break down in blockchain environments. On-chain execution is stateful, adversarial, and economically irreversible, exposing three fundamental gaps: Reactivity, Irreversibility, and Observability. We propose ChainClaw, a blockchain-native agent framework built on OpenClaw, that addresses all three gaps through a layered architecture comprising an event-driven orchestration layer, a simulation-based safety intelligence layer, and an on-chain monitoring runtime layer, unified by a cross-layer memory subsystem. ChainClaw closes the Reactivity gap via event ingestion and simulation feedback, the Irreversibility gap via a pre-execution safety pipeline with transaction simulation and action guard, and the Observability gap via an on-chain read adapter and transaction monitor. We evaluate ChainClaw on a purpose-built benchmark covering seven tasks across four categories and five dimensions. ChainClaw consistently outperforms representative baselines on both safety and task completion.

Problem

• Reactivity
• Irreversibility
• Observability
• blockchain
• on-chain execution

Innovation

• blockchain-native agents
• layered architecture
• transaction simulation
• event-driven orchestration
• on-chain monitoring