Awesome AI AgentsLLM-Powered Platforms

X-PLUG/MobileAgent

⭐ 9197 Python repository created 2024-01-26

Mobile-Agent is a comprehensive and powerful mobile device operation assistant family designed to facilitate complex task automation and multi-modal interaction on mobile devices and PCs. The project encompasses several versions and variants, including Mobile-Agent, Mobile-Agent-v2, Mobile-Agent-v3, Mobile-Agent-E, and PC-Agent, each tailored to different aspects of device operation and task complexity. Mobile-Agent focuses on autonomous multi-modal mobile device operation with visual perception capabilities, enabling it to understand and interact with mobile interfaces effectively. Mobile-Agent-v2 introduces effective navigation through multi-agent collaboration, enhancing the assistant's ability to handle mobile device operations more efficiently. Mobile-Agent-E represents a hierarchical multi-agent framework with self-evolution capabilities, allowing the system to improve its performance on complex, long-horizon, and reasoning-intensive tasks by learning from past experiences. PC-Agent extends the concept to PC platforms, supporting both Mac and Windows, and provides a hierarchical multi-agent collaboration framework for automating complex tasks on personal computers. The project is well-documented with multiple research papers published on arXiv, demonstrating its academic and practical significance. It offers demos on platforms like Hugging Face Spaces and ModelScope, allowing users to experience the assistant's capabilities without complex setup. The project has received recognition, including awards and acceptance at prestigious conferences such as NeurIPS 2024 and ICLR 2024 Workshop on Large Language Model Agents. Mobile-Agent supports multi-modal inputs, visual perception, and multi-agent collaboration, making it a versatile tool for automating and assisting with mobile and PC operations. It is open-source and actively maintained, with ongoing updates and improvements. The project also provides video demos showcasing its functionality in real-world scenarios, highlighting its practical applications and user-friendly design.

https://github.com/X-PLUG/MobileAgent

agentandroidappautomationautonomous-multi-modal-agentcomplex-task-automationcopilotdemogpt4vguiharmonyhierarchical-frameworkiclriosmllmmobilemobile-agentsmobile-device-operation-assistantmobile-navigationmulti-agent-collaborationmulti-app-tasksmultimodalmultimodal-agentmultimodal-large-language-modelsneuripsopen-sourcepc-operation-assistantresearch-papersself-evolutiontask-automationvisual-perception

Also in LLM-Powered Platforms

koala73/worldmonitor

World Monitor is a real-time global intelligence dashboard for AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface.

hiyouga/LlamaFactory

LLaMA Factory is a unified platform for efficient fine-tuning and deployment of over 100 large language and vision-language models, supporting advanced training methods, scalable resource management, and fast inference with broad industry adoption.

FoundationAgents/OpenManus

OpenManus is an open-source platform that enables users to create and run intelligent agents using large language models without restrictive access, supporting multiple agents and easy configuration for diverse AI applications.

hugohe3/ppt-master

AI-powered tool that generates natively editable PowerPoint presentations, complete with animations and audio narration, from any document, supporting custom .pptx templates.

zhayujie/CowAgent

CowAgent is an open-source, multi-model AI assistant and agent harness that autonomously plans tasks, utilizes skills, and learns with memory and knowledge, supporting various LLMs and communicatio...

janhq/jan

Jan is an open-source, privacy-focused ChatGPT alternative that runs large language models locally on your computer with optional cloud integration and custom AI assistant capabilities.

MadsLorentzen/ai-job-search

AI Job Search is a powerful, local AI application framework leveraging Claude Code to automate job application tasks, including evaluating postings, tailoring CVs and cover letters, and preparing f...

agno-agi/agno

Agno is a lightweight, model-agnostic library for building advanced AI agents with memory, knowledge, tools, and reasoning capabilities, supporting multi-modal inputs and outputs and featuring an advanced multi-agent architecture.