IronClaw：基于 Rust 和 WASM 沙箱的安全 AI 代理运行框架

Cool, Transformer co-author Illia Polosukhin presents IronClaw — an OpenClaw, but in Rust!

This framework rewrites the AI agent runtime in Rust to prioritize security. 

It isolates agent activities by running tools in a WASM sandbox and ensures that sensitive credentials are encrypted and never visible to the language model itself.

It solves the critical security vulnerabilities found in OpenClaw, protecting users from prompt injection and data theft while providing a stable, enterprise-ready environment for autonomous agents.

Project：https://t.co/ahOomFGObM