Awesome AI AgentsAI-Powered Agents

Planetary-Computers/autotab-starter

⭐ 1009 Python repository created 2023-10-06

The project "autotab-starter" by Planetary-Computers is designed to facilitate the creation of browser automation agents for real-world tasks using AI. It enables users to quickly generate auditable browser automation scripts by recording their interactions in a Chrome browser and converting these actions into live Python code. The tool is particularly useful for automating repetitive web tasks, such as logging into websites, clicking buttons, typing text, and other browser interactions. The project is currently in an alpha release stage and actively developed, with frequent updates and potential breaking changes. It requires users to have Chrome installed and recommends setting up a Python virtual environment for dependency management. Users configure their credentials via a YAML file and use commands like `autotab record` to start recording browser actions and `autotab play` to run the generated automation scripts. The recording process involves launching a Chrome session controlled by Selenium, logging into Google, and opening the autotab extension side panel. Users can record clicks, typing, and element selections, which are then translated into Python scripts saved in an agents folder. These scripts can be edited and run to automate the recorded tasks. The project also handles login cookies to manage two-factor authentication and session persistence. The repository includes detailed setup instructions, usage guidelines, and a disclaimer emphasizing responsible use and compliance with website terms of service. It also notes that user data such as application state and DOM information is logged by default during recording but can be disabled. Overall, autotab-starter offers a streamlined approach to building browser automation agents with AI assistance, making it accessible for users to automate complex web workflows efficiently and audibly.

https://github.com/Planetary-Computers/autotab-starter

agentaiautomationautomation-scriptsbrowserbrowser-agentsbrowser-automationchromecookiesopen-sourceplaybackpythonreal-world-tasksrecordingseleniumtwo-factor-authenticationweb-tasksyaml-configuration

Also in AI-Powered Agents

NousResearch/hermes-agent

Hermes Agent is a self-improving AI agent by Nous Research designed to learn from experience, create and refine skills, and maintain knowledge across sessions.

google-gemini/gemini-cli

Gemini CLI is an open-source AI agent that integrates Google's powerful Gemini model directly into the terminal, enabling developers to perform advanced code understanding, automation, and integration tasks efficiently from the command line.

feder-cr/AIHawk

Open-source AI browser agent that follows natural-language instructions to click, type and read a real browser, usable via MCP or a standalone web UI.

earthtojake/text-to-cad

A library providing agent skills for CAD, robotics, and hardware design, enabling AI agents to generate, inspect, and manage various design artifacts.

lsdefine/GenericAgent

GenericAgent is a minimal, self-evolving autonomous agent framework that allows LLMs system-level control over a local computer, growing skills through task execution.

browseros-ai/BrowserOS

BrowserOS is an open-source, privacy-first Chromium-based browser that runs AI agents locally to automate browsing tasks and protect user data.

ChatLab/ChatLab

ChatLab is a local-first desktop application that analyzes chat histories from various platforms using AI agents and a SQL engine for insights and visualizations, prioritizing user data privacy.

Integuru-AI/Integuru

Integuru is an AI agent that generates integration code by reverse-engineering platforms' internal APIs using browser network requests and OpenAI models to automate platform interactions without requiring permission.