loushang

Overview of loushang

What it is

Loushang is an AI-native agent harness for coding workflows, built with Python. It provides multi-model LLM orchestration, stateful sessions, tool governance, traceable delivery, and provider routing for models such as GPT, Claude, DeepSeek, Qwen, Kimi, GLM, and MiniMax. The current focus is loushang code, a CLI and terminal workbench for software development that includes model routing, persistent sessions, tools, extensions, and method-guided delivery.

Key features

• loushang code: a coding-focused CLI and terminal workbench.
• loushang.ai: a provider-aware AI SDK with model registry, streaming, tool calls, and cost helpers.
• Sessions: persistent coding sessions with resume, fork, export, and diagnostics.
• Tools: built-in coding tools and configurable tool surfaces.
• Extensions: project-level extension hooks, custom tools, dynamic resources, and commands.
• Methods and skills: method-guided coding turns and reusable workflow assets.

Use cases

• Software development with AI assistance, from intent to verified delivery.
• Multi-model LLM orchestration for complex coding workflows.
• Persistent, resumable coding sessions with full audit trail.
• Tool governance and extension-based customization for project-specific needs.

Getting started

bashgit clone https://github.com/zhnt/loushang.gitcd loushanguv venv .venvsource .venv/bin/activateuv pip install -e .[dev]loushang --helploushang --list-modelsloushang --list-commandsloushang -p 'Inspect this repository and summarize what it does.'Alternatively, run make bootstrap to create a virtual environment and install in editable development mode.

License and pricing

Loushang is licensed under the Apache License 2.0. It is open source and free to use.

Based on the project's public README and repository metadata.