by zhnt · Codex Skill · ★ 552
Loushang English | 中文 Loushang is a method-native AI work system for running complex work from intent to verified delivery. Current focus: , a CLI and terminal workbench for software development with model routing, persistent sessions, tools, extensions, and method-guided delivery. Why Loushang Modern AI agents can plan and act, but complex work still breaks down when context is lost, execution cannot be resumed, tools are hard to govern, and results are not verified. Loushang treats methods, stages, roles, tools, sessions, and work products as runtime objects.
| Stars | 552 |
| Forks | 104 |
| Language | Python |
| Category | Codex Skill |
| License | Apache-2.0 |
| Quality Score | 64.0110280813611/100 |
| Open Issues | 22 |
| Last Updated | 2026-07-08 |
| Created | 2026-05-29 |
| Platforms | claude-code, cli, codex, python |
| Est. Tokens | ~14k |
Explore other popular codex skill tools:
loushang is 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, K. It is categorized as a Codex Skill with 552 GitHub stars.
loushang is primarily written in Python. It covers topics such as agent, agent-harness, agentic.
You can find installation instructions and usage details in the loushang GitHub repository at github.com/zhnt/loushang. The project has 552 stars and 104 forks, indicating an active community.
loushang is released under the Apache-2.0 license, making it free to use and modify according to the license terms.