Expired50% confidenceFactExact time
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.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026(expired)
Sources
Enterprise AI Agent Architecture in Practice: Sandbox Isolation and Skill Management Explained
bilibili凉也要学AI6/12/2026
Related Claims
UnverifiedThe 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.73% similarUnverifiedDeepSeek开源了名为Hanis的Agent框架，提出将Agent解构为模型、工具、提示词、记忆等原子组件并通过配置化方式组装的声明式Agent理念70% similarUnverifiedDeep Agent possesses a closed-loop 'perception-planning-execution' capability, and can not only generate code but also read project file trees, understand module dependencies, invoke terminal commands, parse compilation errors, and autonomously fix problems.69% similarUnverifiedMainstream Agent architectures typically use a large language model as the brain, combined with memory modules, planning modules, and tool interfaces to accomplish complex tasks66% similarUnverifiedThe technology stack of the explored project is: a React-based console for the frontend, HTTP for the communication layer, FastAPI for the backend, and Agent Service (including a control plane module and Agent Runtime) for the service layer.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/46820API
curl https://kongchang.com/api/v1/knowledge/claims/46820MCP
get_claim(id=46820)