Awesome AI AgentsInventory Automation Agents

microsoft/UFO

⭐ 9720 Python repository created 2024-01-08

UFO is a UI-Focused multi-agent framework designed to interact with the Windows operating system by navigating and operating within one or multiple applications to fulfill user requests. It consists of several key components: HostAgent, which selects and switches between applications to complete tasks; AppAgent, which executes actions within a chosen application until the task is done; and the Application Automator, which translates agent actions into actual interactions with the application through UI controls, native APIs, or AI tools. The framework leverages the multi-modal capabilities of GPT-4V(o) to understand application UIs and effectively carry out user commands. UFO supports complex workflows that span multiple applications and can perform multiple actions in a single inference step, enhancing efficiency. It also supports learning from human demonstrations, Win32 control backend, keyboard inputs, and native API interactions, with ongoing expansion to support more applications. The project is actively maintained with frequent updates improving features, bug fixes, and performance enhancements. It includes support for bash commands, control filtering to streamline LLM action processes, and the ability to save task completion trajectories to improve success rates. UFO is open-source under the MIT license and provides extensive documentation, technical reports, and media coverage. It aims to create a smarter Windows experience by automating UI interactions through advanced AI agents, making it a significant step towards intelligent, multi-application automation on Windows OS.

https://github.com/microsoft/UFO

agentai-toolsappagentapplication-automatorapplication-interactionautomationcopilotgpt-4vguihostagenthuman-demonstration-learningkeyboard-inputllmmit-licensemulti-action-modemulti-agent-frameworkmulti-application-tasksmulti-modal-ainative-apisopen-sourcetask-completion-trajectoryui-controlsui-focuseduser-requestswin32-supportwindowswindows-os

Also in Inventory Automation Agents

OpenInterpreter/open-interpreter

Open Interpreter is an open-source natural language interface that enables users to run code locally on their computers through a chat-based system, facilitating tasks like multimedia editing, browser control, and data analysis with full user approval and flexibility beyond hosted solutions.

sigoden/aichat

AIChat is an all-in-one command-line interface tool that integrates multiple large language models and provides features like Shell Assistant, Chat-REPL, RAG, AI Tools, and Agents for enhanced AI-driven command-line productivity.

firerpa/lamda

FIRERPA/lamda is a robust and versatile Android RPA framework designed for next-generation mobile automation, supporting a wide range of Android versions and environments with extensive APIs and Python SDK for seamless AI integration and device control.

FellouAI/eko

Eko is a production-ready JavaScript framework that enables developers to build reliable, multi-step agentic workflows using natural language commands across computer and browser environments.

cjo4m06/mcp-shrimp-task-manager

Shrimp Task Manager is an intelligent task management system for AI Agents that converts natural language into structured development tasks with dependency tracking, iterative refinement, and research capabilities to enhance programming workflows.

irgolic/AutoPR

AutoPR is a tool that runs AI-powered workflows over codebases to automate tasks such as documentation, issue tracking, and pull request management.

dariubs/awesome-workflow-automation

A curated list of workflow automation software, tools, articles, and resources aimed at improving productivity and efficiency by automating repetitive tasks for individuals and teams.

OpenBMB/ProAgent

ProAgent is an LLM-based agent system that advances automation by enabling intelligent workflow construction and execution through Agentic Process Automation, surpassing traditional RPA capabilities.