langchain_agentx
langchain_agentx 是一组基于 LangChain / LangGraph 的“代码智能体”工具函数,帮助你在自己的项目里快速集成:
- OpenCode 风格的 LangGraph Agent(代码理解、重构、分析)
- DeepAgent 兼容的 Agent 工厂
- 上下文感知中间件、性能监控等基础设施
安装
发布到 PyPI 后,你可以直接通过 pip 安装:
pip install langchain-agentx
快速上手
from langchain_agentx import create_opencode_style_agent, create_opencode_style_deepagent
# 这里省略 LangChain / LangGraph 相关模型与工具配置
agent = create_opencode_style_agent(...)
deep_agent = create_opencode_style_deepagent(...)
具体的能力和使用方式可以参考源码中的 docstring 以及各模块下的 README.md。
发布新版本流程(备忘)
以下命令默认在项目根目录(
c:\git_code\langchain_agentx)并已激活kw_venv。
1. 准备代码与版本号
- 修改版本号:编辑
pyproject.toml:- 把
[project]里的version = "0.x.y"改成新版本(例如0.2.0)。
- 把
- 确认工作区干净:
- 运行
git status,确认只有本次要发版的变更。
- 运行
2. 安装构建与发布工具
只需偶尔执行一次(环境更新或新机器时):
python -m pip install -U build twine
3. 本地构建分发包
在项目根目录执行:
python -m build
构建成功后会生成:
dist/langchain_agentx-<version>.tar.gzdist/langchain_agentx-<version>-py3-none-any.whl
4. 上传到 TestPyPI(可选,推荐先试)
- 在浏览器里登录
https://test.pypi.org/,创建/获取 API token。 - 在本机用户目录创建/编辑
~/.pypirc:
[distutils]
index-servers =
testpypi
[testpypi]
username = __token__
password = pypi-xxxxxxxxxxxxxxxxxxxx
- 运行上传命令:
python -m twine upload --repository testpypi dist/*
- 在一个干净的虚拟环境里测试安装:
python -m pip install -i https://test.pypi.org/simple/ langchain-agentx==<version>
5. 上传到正式 PyPI
- 在浏览器里登录
https://pypi.org/,创建/获取 API token。 - 在
~/.pypirc中增加正式仓库配置(若尚未配置):
[distutils]
index-servers =
pypi
testpypi
[pypi]
username = __token__
password = pypi-xxxxxxxxxxxxxxxxxxxx
[testpypi]
username = __token__
password = pypi-xxxxxxxxxxxxxxxxxxxx
- 上传到 PyPI:
python -m twine upload dist/*
6. 打 Tag 并推送(可选但推荐)
git add .
git commit -m "release: langchain-agentx <version>"
git tag v<version>
git push
git push --tags
下次发布时按本节从上到下依次执行即可。***
Metadata
Release files for langchain-agentx 0.1.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| langchain_agentx-0.1.1.tar.gz | 109.4 kB | Without provenance | Details for langchain_agentx-0.1.1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| langchain_agentx-0.1.1-py3-none-any.whl | Python 3 | none | any | Details for langchain_agentx-0.1.1-py3-none-any.whl |
Total release size: 240.9 kB
Release files / langchain_agentx-0.1.1.tar.gz
| Download URL | langchain_agentx-0.1.1.tar.gz |
|---|---|
| Size | 109.4 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
1778d165b2f0685188f8a44194dd185eb9b65e75806f7d13d279ddbea527f5e8
|
|
BLAKE2b-256 checksum How to use checksums |
775d62ba9509dfdad023acb3df1d976de608bc67395c706aeff3cffe3f3699e5
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.9
|
Release files / langchain_agentx-0.1.1-py3-none-any.whl
| Download URL | langchain_agentx-0.1.1-py3-none-any.whl |
|---|---|
| Size | 131.6 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
5580a040ff2e0f50b9331d3db057d5ee39732a6081beae565a20946f7868b89c
|
|
BLAKE2b-256 checksum How to use checksums |
d032298f07467457e0c9c1e05a845f337f9aa55c1ef81d23e1ff093108c6846c
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.9
|
Security for langchain-agentx 0.1.1
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.