loushang
Loushang is a Python-based AI-native agent framework for coding workflows.
- Region
- Domestic
- Pricing
- Free
- Open source
- Yes
- GitHub Stars
- ★ 1.0k
- Source
- GitHub
- Added
- 2026-08-05
- Last verified
- 2026-08-05
- GitHub
- github.com/zhnt/loushang
Overview
Loushang is an AI-native agent system designed for complex tasks, currently focusing on `loushang code`, a CLI and terminal workspace for software development. It supports multi-model LLM orchestration, persistent sessions, tool governance, traceable delivery, and provider routing. The goal of Loushang is to make complex work more reliable, recoverable, auditable, and deliverable. Users can start and manage coding sessions via a command-line interface and use built-in tools and extensions for development.
Key features
- ▪Multi-model LLM orchestration
- ▪Persistent sessions
- ▪Tool governance
- ▪Traceable delivery
- ▪Provider routing
Use cases
Pros
- ＋Supports multiple LLM models
- ＋Persistent session management
- ＋Rich set of built-in tools
- ＋Highly extensible
Limitations / notes
- －Requires some learning curve
- －Currently in early development stage
Who it's for
This overview was compiled by AI from public sources and may contain inaccuracies — please refer to the official site.
FAQ
Is it free?
Yes, Loushang is open-source and free.
Does it support Chinese?
Documentation is available in Chinese, but specific support details need further confirmation.
Can it be used commercially?
Yes, Loushang is licensed under the Apache License 2.0.
Similar agents
Cursor
FeaturedAI-powered code editor with Agent mode
Dify
FeaturedOpen-source LLMOps + Agent orchestration platform
扣子 Coze
FeaturedByteDance's no-code Agent/Bot building platform
Trae
FeaturedAI IDE (with Agent) from ByteDance
LangChain
FeaturedThe most mainstream LLM/Agent orchestration framework
Devin
FeaturedAutonomous software engineer Agent by Cognition
Something wrong? Let us know on the About page and we'll fix it.