经 AI Skill Hub 精选评估,纳拉达Python SDK 获评「推荐使用」。这款Agent工作流在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 7.5 分,适合有一定技术背景的用户使用。
纳拉达Python SDK 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
纳拉达Python SDK 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
# 方式一:pip 安装(推荐)
pip install narada-python-sdk
# 方式二:虚拟环境安装(推荐生产环境)
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install narada-python-sdk
# 方式三:从源码安装(获取最新功能)
git clone https://github.com/NaradaAI/narada-python-sdk
cd narada-python-sdk
pip install -e .
# 验证安装
python -c "import narada_python_sdk; print('安装成功')"
# 命令行使用
narada-python-sdk --help
# 基本用法
narada-python-sdk input_file -o output_file
# Python 代码中调用
import narada_python_sdk
# 示例
result = narada_python_sdk.process("input")
print(result)
# narada-python-sdk 配置文件示例(config.yml) app: name: "narada-python-sdk" debug: false log_level: "INFO" # 运行时指定配置文件 narada-python-sdk --config config.yml # 或通过环境变量配置 export NARADA_PYTHON_SDK_API_KEY="your-key" export NARADA_PYTHON_SDK_OUTPUT_DIR="./output"
<p align="center"> <picture> <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/NaradaAI/narada-python-sdk/main/static/Narada-logo-dark.png"> <source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/NaradaAI/narada-python-sdk/main/static/Narada-logo.png"> <img alt="NARADA AI Logo." src="https://raw.githubusercontent.com/NaradaAI/narada-python-sdk/main/static/Narada-logo.png" width="300"> </picture> </p>
<p align="center"> <a href="https://narada.ai"><img src="https://img.shields.io/badge/Sign%20Up-Cloud-blue?logo=cloud" alt="Sign Up"></a> <a href="https://docs.narada.ai"><img src="https://img.shields.io/badge/Documentation-Docs-blue?logo=gitbook" alt="Documentation"></a> <a href="https://x.com/intent/user?screen_name=Narada_AI"><img src="https://img.shields.io/badge/Follow-Twitter-1DA1F2?logo=twitter&logoColor=white" alt="Twitter Follow"></a> <a href="https://www.linkedin.com/company/97417492/"><img src="https://img.shields.io/badge/Follow-LinkedIn-0077B5?logo=linkedin&logoColor=white" alt="LinkedIn Follow"></a> </p>
The official Narada Python SDK that helps you launch browsers and run tasks with Narada UI agents.
pip install narada
Important: The first time Narada opens the automated browser, you will need to manually install the Narada Enterprise extension and log in to your Narada account.
After installation and login, create a Narada API Key (see this link for instructions) and set the following environment variable:
export NARADA_API_KEY=<YOUR KEY>
That's it. Now you can run the following code to create a browser environment and ask an agent to download a file for you from arxiv:
import asyncio
from narada import Agent, BrowserEnvironment
async def main() -> None:
# Create the browser environment. It initializes lazily on the first action.
env = BrowserEnvironment()
agent = Agent(environment=env)
try:
# Run a task in this browser environment.
response = await agent.run(
prompt='Search for "LLM Compiler" on Google and open the first arXiv paper on the results page, then open the PDF. Then download the PDF of the paper.',
# Optionally generate a GIF of the agent's actions.
generate_gif=True,
)
print("Response:", response.model_dump_json(indent=2))
finally:
await env.close()
if __name__ == "__main__":
asyncio.run(main())
This would then result in the following trajectory:
<p align="center"> <a href="https://youtu.be/bpy-xnSeboY"> <img src="https://i.imgur.com/TyEuD5d.gif" alt="File Download Example" width="600"> </a> </p>
You can use the SDK to launch browsers and run automated tasks using natural language instructions. For more examples and code samples, please explore the examples/ folder in this repository.
高质量的AI工作流自动化工具
该工具未明确声明开源协议,商业使用前请联系原作者确认授权范围,避免侵权风险。
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
AI Skill Hub 点评:纳拉达Python SDK 的核心功能完整,质量良好。对于自动化工程师和运维人员来说,这是一个值得纳入个人工具库的选择。建议先在非生产环境试用,再逐步推广。
| 原始名称 | narada-python-sdk |
| 原始描述 | 开源AI工作流:Computer Use for Agentic Process Automation。⭐8 · Python |
| Topics | aiai-agentsapallm |
| GitHub | https://github.com/NaradaAI/narada-python-sdk |
| 语言 | Python |
收录时间:2026-06-12 · 更新时间:2026-06-12 · License:未公布 · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端