元铸工坊 yuanzhu
把最佳实践铸成可治理的 AI 工作流资产——AI 提议,人拍板。
一台独立运行的引擎(本体层 + 模板 + 工作流 + 审批),三种用法:
- 深度问答:问一个问题自动走六步流水线(澄清→双视角并行作答→独立审查→综合裁决→人审采纳)
- 一句话铸模板:描述你的日常工作,AI 生成完整工作流模板,评测自动守门
- agent 接入:Claude Code 等经 MCP 直连(
claude mcp add yuanzhu http://127.0.0.1:8600/mcp)
安装与启动
pip install yuanzhu
yuanzhu-server # 打开 http://127.0.0.1:8600
首启自动注册内置模板(深度问答/AIQA 测试/会议追踪),零配置可用。
CLI 同装:yuanzhu status / pending / templates / forge "你的工作描述"。
模型接入:自动读取 dsh 已配 provider;或用环境变量接任意 OpenAI 兼容端点
(YUANZHU_PROVIDER_n_{NAME,BASE_URL,API,KEY,MODELS})。
核心概念
| 概念 | 一句话 |
|---|---|
| 本体层 | 你的业务对象(名词)+ 受治理的动作(动词)——业务世界的数字孪生 |
| staged writes | AI 的所有写操作先进待审区,人批准才生效 |
| 四段式模板 | 对象模型+动作库+工作流+评测集——可安装的"专家经验" |
许可
AGPL-3.0。文档与源码:https://github.com/RavenWangChina/yuanzhu
Metadata
Release files for yuanzhu 0.2.2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| yuanzhu-0.2.2-py3-none-any.whl | Python 3 | none | any | Details for yuanzhu-0.2.2-py3-none-any.whl |
Release files / yuanzhu-0.2.2-py3-none-any.whl
| Download URL | yuanzhu-0.2.2-py3-none-any.whl |
|---|---|
| Size | 172.8 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
a97045d88df89ea510a3499e311333f7185ab5ccb6c22c71b10043238d7236f3
|
|
BLAKE2b-256 checksum How to use checksums |
a9c3455d89db3458c247b08fad63065bf81c5f82e666cfb05ccd1ebb45f88346
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.12.10
|
Security for yuanzhu 0.2.2
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.