AI-native agent harness for coding workflows by python: multi-model LLM orchestration, stateful sessions, tool governance, traceable delivery, and provider routing for GPT, Claude, DeepSeek, Qwen, Kimi, GLM, and MiniMax.
git clone https://github.com/zhnt/loushang && cp loushang/*.md ~/.claude/agents/Subagents overview
What people ask about loushang
What is zhnt/loushang?
+
zhnt/loushang is subagents for the Claude AI ecosystem. AI-native agent harness for coding workflows by python: multi-model LLM orchestration, stateful sessions, tool governance, traceable delivery, and provider routing for GPT, Claude, DeepSeek, Qwen, Kimi, GLM, and MiniMax. It has 874 GitHub stars and was last updated today.
How do I install loushang?
+
You can install loushang by cloning the repository (https://github.com/zhnt/loushang) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is zhnt/loushang safe to use?
+
zhnt/loushang has not been audited yet by our security agent. Review the original repository on GitHub before using it in production.
Who maintains zhnt/loushang?
+
zhnt/loushang is maintained by zhnt. The last recorded GitHub activity is from today, with 27 open issues.
Are there alternatives to loushang?
+
Yes. On ClaudeWave you can browse similar subagents at /categories/agents, sorted by popularity or recent activity.
Deploy loushang to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/zhnt-loushang)<a href="https://claudewave.com/repo/zhnt-loushang"><img src="https://claudewave.com/api/badge/zhnt-loushang" alt="Featured on ClaudeWave: zhnt/loushang" width="320" height="64" /></a>More Subagents
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
The agent that grows with you
Java 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
The agent engineering platform.
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.