Today's featured cutting-edge AI information, welcome to read 👇

📱 Agent S: A new open-source automation agent framework that supports OpenAI, Claude, and other models, capable of autonomous interaction with computer interfaces to accomplish complex graphical operation tasks.

📚 ToastFish is a clever vocabulary learning tool that ingeniously utilizes the Windows notification bar for fragmented vocabulary learning, supporting custom word libraries and vocabulary testing functions.

🤖 Cerebellum: An LLM-based browser automation tool that can control keyboard and mouse through agents to complete web data scraping and automation testing, supporting all Selenium browsers.

Cutting-edge Technology

1. Another open-source automation agent framework: Agent S.

Enables autonomous computer interaction through agents interfacing with computer interfaces, capable of executing complex graphical interface operation tasks.

GitHub: https://github.com/simular-ai/Agent-S

Supports various mainstream large language models such as OpenAI, Claude, etc., and also supports OCR recognition using Paddle-OCR.

Open Source Projects

1. An open-source tool for learning vocabulary during spare time: ToastFish.

For students wanting to learn English, this tool allows vocabulary learning through the Windows notification bar, enabling safe and discreet vocabulary learning whether you're at work or in class.

GitHub: https://github.com/Uahh/ToastFish

Moreover, it supports practical features like custom word libraries, setting vocabulary learning quantities, and vocabulary testing.

2. An agent-based browser automation tool: Cerebellum.

Achieves automated keyboard and mouse operations through LLM-built agents to complete tasks such as web data scraping and automation testing.

GitHub: https://github.com/theredsix/cerebellum

Compatible with any Selenium browser, though currently only supports using the Claude 3.5 Sonnet model.