This project is a **proof of concept** that aims to replicate the reasoning capabilities of OpenAI's newly released O1 model.

🤖 LLM-powered computer control through local and Docker environments. Features VNC integration, automated interactions, and a chat interface for natural language system control.

Desktop app powered by Claude’s computer use capability to control your computer

How about this fun fact: "Did you know that this app created with dnlib has the power to bypass login systems? Say goodbye to frustrating login screens and hello to effortless access!"

The OpenAI Chat Extension is a Chrome extension that generates responses to a user's input using OpenAI's chat API. It allows users to select text on a webpage and generate a response based on that…

Sophia AI Assistant is a Python-based desktop AI that performs a variety of tasks, including answering questions, opening applications, browsing websites, and making calls via phone or WhatsApp. It…

💻 A curated list of papers and resources for multi-modal Graphical User Interface (GUI) agents.

Desktop AI Assistant powered by o1, o3, GPT-4, GPT-4 Vision, Gemini, Claude, Llama 3, DeepSeek, Bielik, DALL-E, chat, vision, voice control, image generation and analysis, agents, command execution…

I leverage OpenAI and ChatGPT to do hackerish things

Data & AI Notebook templates catalog organized by tools, following the IMO (input, model, output) framework for easy usage and discovery..

Superduper: Build end-to-end AI applications and agent workflows on your existing data infrastructure and preferred tools - without migrating your data.

Rapidly build AI apps in Python

A user-friendly, multi-platform GUI for managing and running CrewAI agents and tasks. Supports Conda and virtual environments, no coding needed.

List of useful crews

Multi AI Agents System from Scratch in pure python without any frameworks.

Gradio UI to load crewAI configuration from excel xls and generate the python code. The source of the crews is in the xls. It allows for quick prototyping and iterations without having to edit code,

Web browser automation through agentic workflows.

Browser automation system that uses AI-driven planning to navigate web pages and perform goals.

This project is a server that exposes terminal commands and file editing functionality as an API for ChatGPT Actions. In essence, it allows you to control any machine where you install this with Ch…

📦🚀 Fully automated version management and package publishing

Automating Playwright steps using ChatGPT.

A versatile multi-modal chat application that enables users to develop custom agents, create images, leverage visual recognition, and engage in voice interactions. It integrates seamlessly with loc…

A tool to build a graph from a codebase

What can be said can be automated

🗜️ Codebase-digest is your AI-friendly codebase packer and analyzer. Features 60+ coding prompts and generates structured overviews with metrics. Ideal for feeding projects to LLMs like GPT-4, Clau…

AI powered automatic software healing agent

The recursive internet scanner for hackers. 🧡

A framework for LLM's that works as a GPS to reduce hallucinations in production [WIP] - The Linux Kernel for Agents

Open Agent Computer Interface

MiniGroqqle is a minimalist web search component that allows Python developers to easily integrate web search capabilities into their applications. With just a few lines of code, you can perform Go…