Expired95% confidenceFactTime unknown
Claude-Claw uses Claude Code as the cognitive decision-making layer (brain) and OpenClaw as the GUI automation execution layer (hands), forming a decoupled architecture.
1
Sources
95%
Confidence
Medium-term (~90 days)
Relevance
6/1/2026
First Seen
Valid until: 8/30/2026(expired)
Sources
Claude-Claw开源项目解析：大脑+双手的AI智能体编排架构
githubhuyuelin
Related Entities
Related Claims
UnverifiedClaude-Claw's differentiation lies in its explicit two-layer "orchestration + automation" architecture design and deep integration of Claude Code's reasoning capabilities.79% similarUnverifiedClaude Code的子智能体设计将探索任务和修改任务隔离开来，主智能体可以并行派出多个独立的Claude实例进行探索76% similarUnverifiedClaude Code的工具调用机制将模型的思考能力与执行能力解耦，模型输出结构化的工具调用指令，由外部运行时负责实际执行76% similarVerifiedThe core architecture of Claude Code is a dual-loop system, with the outer layer being the user interaction layer and the inner layer being the tool execution layer.74% similarUnverifiedClaude Code 的子智能体实现通过 CLAUDE.md 配置文件为每个智能体注入专属知识库、行为规范和工具调用权限74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/29174API
curl https://kongchang.com/api/v1/knowledge/claims/29174MCP
get_claim(id=29174)