← 开源
Planetary-Computers

autotab-starter

Build browser agents for real world tasks

ApplicationsProductivityPython
在 GitHub 打开
增长势头
+024 小时新增 Star0.0%
1.01k
Star
66
Fork
+-1
本周
3
贡献者
创建于 2023-10-06 · 更新于 2026-10-13 · 今日第 12109 名
主要开发者
jonasalexanderalexijsteel2

Planetary-Computers/autotab-starter 排名第 12,109,有 1,007 个星标。

同类别比较

Planetary-Computers/autotab-starter 排名第 12,109,此处有 8 个同类条目;jingyunstudio/jingyun-dsh 排名第 12,112。

同类别比较
名称排名指标
wang-rui/phishguard-scaffold12,090
语言:
Python
星标数:
1,012
分叉数:
169
简介:
Joint Semantic Detection and Dissemination Control of Phishing Attacks on Social Media via LLama- Based Modeling
274056675/springboot-openai-chatgpt12,092
语言:
Java
星标数:
1,011
分叉数:
243
简介:
超级AI大脑一个基于SpringCloud微服务架构,已对接GPT-3.5、GPT-4.0、百度文心一言、stable diffusion AI绘图、Midjourney绘图等。支持web,Android,IOS,H5多端应用,使用了OpenAI的ChatGPT模型实现了智能聊天机器人。用户可以在界面上与聊天机器人进行对话,聊天机器人会根据用户的输入自动生成回复。同时也支持画图,用户输入文本,便可以自动制作文生文生图。持续更新中,更多功能等着你来解锁
ShuaixinHuang/image-multiple-angles-3d-camera12,094
语言:
Python
星标数:
1,011
分叉数:
21
简介:
🎬 Generate images from any camera viewpoint via 3D interactive control. Drag the camera in 3D space or use sliders to set azimuth/elevation/distance, then generate. Built with Three.js + Gradio, bilingual ZH/EN UI.
ZTE-AICloud/Co-Sight12,097
语言:
Python
星标数:
1,010
分叉数:
278
jingyunstudio/jingyun-dsh12,112
语言:
TypeScript
星标数:
1,007
分叉数:
41
简介:
基于 Jingyun Studio + DeepSeek Harness (DSH) 打造的一站式 AI 商业化桌面客户端,一个将 AI 智能体 / 技能 / 工作流转化为可交易商品的完整商业化平台客户端。 井云为 DSH 注入了完整的商业闭环:登录注册 → 会员体系 → 订阅支付 → 云端资产 → 多端同步,让 AI 开发者 30 分钟内将自己的智能体封装为独立的商业产品。
disler/always-on-ai-assistant12,133
语言:
Python
星标数:
1,002
分叉数:
215
简介:
A pattern for an always on AI Assistant powered by Deepseek-V3, RealtimeSTT, and Typer for engineering
TreborNamor/TradingView-Machine-Learning-GUI12,138
语言:
Python
星标数:
1,001
分叉数:
265
简介:
HyperView is a terminal-first TradingView strategy lab for downloading market data, backtesting Python strategies with Pine-like behavior, and optimizing SL/TP parameters.
J3n5en/EnsoAI12,147
语言:
TypeScript
星标数:
998
分叉数:
120
简介:
Multiple Agents, Parallel Flow
关键参数与规格
关键参数与规格
参数值
语言Python
类别Applications
子类别Productivity
关键词Browser, Computer use
星标数1,007
分叉数66
贡献者3
创建日期2023-10-06
更新日期2026-10-13
1 天星标数0
7 天星标数-1
排名12,109
上次排名12,039
排名变化-70
7 天星标排名17,375
上次 7 天星标排名17,355
7 天星标排名变化-20
总星标排名11,096
上次总星标排名11,081
总星标排名变化-15
README 摘录

Update (Dec 12, 2023) Thanks for trying out autotab! Over the last few weeks we’ve learned from so many of you and are excited to start rolling out a smoother and more user-friendly autotab V1 (no dependencies! As we transition, this repo will no longer be supported. The good news is that any Python code you’ve generated with autotab will of course work as usual. Join our Discord channel to follow along and for a chance to

be one of the first to try out new updates! autotab makes it easy to create auditable browser automations using AI. Go from a point & click demonstration in the browser to live code for those actions in seconds. Note: This project is alpha release and actively being developed. Expect breaking changes and exciting new features regularly! Quickstart It usually takes 5-10 minutes to get everything set up (including gathering passwords and installing dependencies). You must have the Chrome browser

installed, and we recommend setting up a Python virtual environment: Configuration Configure your credentials: Create a file following the example in . (~3 minutes) Run Run to open a new browser window where you can start recording your actions. Note: When you run , an automation will first try to log you in to autotab using the from your file. You need to be logged in to autotab to use the extension (and our Open AI API key). You log in to

using your autotab API key which you can get for free at autotab. Usage Recording an automation To record a new automation, run . This will launch a Chrome session controlled by Selenium and then log you in to Google and open the autotab extension in the sidepanel. If the sidepanel does not open, type to open the sidepanel. Once the sidepanel is open, you can use record mode to record clicks and typing ( ) or select mode ( ) to select an element

to be hovered, copied to clipboard or to inject text into. At the end of recording make sure to copy all the code. autotab will have created a file in the folder with boilerplate code. Paste the code in there, format it and then your agent is ready to run! Running an automation To play an automation you've already created, run . This just runs the Python script, so you can set debug as you would any other Python script. Often

times interactions fail if the Chrome window running the automation isn't focused. We are working on a headless version that runs in the cloud which we hope to release soon to address this. Setup Installation See the quickstart above (Steps 1 and 2). Running installs all the dependencies as well as the local package which enables the and commands. Secrets Create a file in the root folder and populate it with the variables listed in the file. The first time

an agent logs into Google, it may require 2FA depending on your settings. The script will store the relevant cookies

常见问题

记录了多少星标和分叉?

Planetary-Computers/autotab-starter 有 1,007 个星标和 66 个分叉。

仓库排名是多少?

Planetary-Computers/autotab-starter 排名第 12,109。

记录的语言和类别是什么?

Planetary-Computers/autotab-starter 有 1,007 个星标,语言为 Python,类别为 Applications。

哪个仓库排名最接近?

Planetary-Computers/autotab-starter 与 jingyunstudio/jingyun-dsh 比较,后者排名第 12,112,有 1,007 个星标。

README

Update (Dec 12, 2023)

Thanks for trying out autotab! Over the last few weeks we’ve learned from so many of you and are excited to start rolling out a smoother and more user-friendly autotab V1 (no dependencies!).

As we transition, this repo will no longer be supported. The good news is that any Python code you’ve generated with autotab will of course work as usual.

Join our Discord channel to follow along and for a chance to be one of the first to try out new updates!

autotab

Welcome to autotab! autotab makes it easy to create auditable browser automations using AI. Go from a point & click demonstration in the browser to live code for those actions in seconds.

Note: This project is alpha release and actively being developed. Expect breaking changes and exciting new features regularly!

Quickstart

It usually takes 5-10 minutes to get everything set up (including gathering passwords and installing dependencies). You must have the Chrome browser installed, and we recommend setting up a Python virtual environment:

git clone https://github.com/Planetary-Computers/autotab-starter.git
cd autotab-starter
# Recommended: Setup a Python virtual environment
make install
brew install --cask chromedriver

Configuration

Configure your credentials: Create a .autotab.yaml file following the example in .example.autotab.yaml. (~3 minutes)

Run

Run autotab record to open a new browser window where you can start recording your actions.

Note: When you run autotab record, an automation will first try to log you in to autotab using the autotab_api_key from your .autotab.yaml file. You need to be logged in to autotab to use the extension (and our Open AI API key). You log in to autotab record using your autotab API key which you can get for free at autotab.com/dashboard.

Usage

Recording an automation

To record a new automation, run autotab record. You can optionally add a --agent argument. This will launch a Chrome session controlled by Selenium and then log you in to Google and open the autotab extension in the sidepanel.

If the sidepanel does not open, type Command - Shift - Y to open the sidepanel.

Once the sidepanel is open, you can use record mode to record clicks and typing (Command - E) or select mode (Command I) to select an element to be hovered, copied to clipboard or to inject text into.

At the end of recording make sure to copy all the code. autotab will have created a .py file in the agents/ folder with boilerplate code. Paste the code in there, format it and then your agent is ready to run!

Running an automation

To play an automation you've already created, run autotab play --agent . Leaving out --agent has it default to run agents/agent.py. This just runs the Python script, so you can set debug as you would any other Python script. Often times interactions fail if the Chrome window running the automation isn't focused. We are working on a headless version that runs in the cloud which we hope to release soon to address this.

Setup

Installation

See the quickstart above (Steps 1 and 2).

Running make install installs all the dependencies as well as the local package which enables the autotab record and autotab play commands.

Secrets

Create a .autotab.yaml file in the root folder and populate it with the variables listed in the .example.autotab.yaml file.

The first time an agent logs into Google, it may require 2FA depending on your settings. The script will store the relevant cookies to avoid 2FA in subsequent runs. Please note that these cookies are stored in a google_cookies.json file, which should be handled with care as it contains sensitive information (we store only the logged-out cookies, so even if someone gets those cookies they still need your password to gain access).

Disclaimer

This repository is provided as-is, with no guarantees. Before using any code, please review it thoroughly. If considering a scraper, familiarize yourself with the target website's guidelines and Terms of Service. Avoid any unauthorized or illegal activities. We hold no responsibility for any potential issues or outcomes.

Note: By default autotab logs user data including the application state, DOM and model responses for recorded events while running autotab record. You can disable state and DOM logging by going to Settings.

排名相邻
同类项目