待验证50% 置信事实精确时间
The overall architecture of the described agent project involves three core components: a Java ERP Backend, Docker Containers on a Linux Server, and a Main Agent Project built with DeepAO framework and HARIS architecture.
1
来源数
50%
置信度
中期 (~90 天)
时效性
2026/7/2
首次发现
有效期至：2026/9/30
来源
相关事实
待验证该方案的整体架构分为三层：Agent Framework层（任务管理和调度）、Claude Agent SDK层（核心Worker）、LiteLLM Proxy层（请求代理转发）75% 相似待验证Mainstream Agent architectures currently include ReAct (Reasoning + Acting), Plan-and-Execute, and state machine-based workflow architectures.73% 相似待验证The agent project described is built on the HARIS architecture and DeepAO framework, and covers key design elements such as sandbox management, Skill persistence, and user memory systems.73% 相似待验证Agent Engineering通过.cursorrules、CLAUDE.md等项目级配置文件来约束AI的代码风格、架构选择和安全底线71% 相似待验证Agentic Backend是一种专为AI Agent设计的后端架构，通过结构化接口描述、MCP协议或Skills机制使AI能够自主理解、调用和编排后端服务70% 相似
引用此条事实
Stable URI
https://kongchang.com/claim/46821API
curl https://kongchang.com/api/v1/knowledge/claims/46821MCP
get_claim(id=46821)