The TypeScript AI agent framework. ⚡ Assistants, RAG, observability. Supports any LLM: GPT-4, Claude, Gemini, Llama.

Playwright MCP server

Qwen2.5-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

Native UI testing / controlling with node

🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

A simple screen parsing tool towards pure vision based GUI agent

No fortress, purely open ground. OpenManus is Coming.

🤗 smolagents: a barebones library for agents that think in python code.

LLM training in simple, raw C/CUDA

[CVPR 2025] Open-source, End-to-end, Vision-Language-Action model for GUI Agent & Computer Use.

simple terminal UI for git commands

AI chat assistant for Obsidian with contextual awareness, smart writing assistance, and one-click edits. Features vault-aware conversations, semantic search, and local model support.

A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.

Let your Claude able to think

✨ Use natural language to control your browser, powered by LLM and playwright

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

An LLM-based Web Navigating Agent (KDD'24)

NLP Web Automation

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

Set-of-Mark Prompting for GPT-4V and LMMs

Mobile-Agent: The Powerful Mobile Device Operation Assistant Family

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

SuperPrompt is an attempt to engineer prompts that might help us understand AI agents.

Let AI be your browser operator.

🦜🔗 Build context-aware reasoning applications

AUITestAgent is the first automatic, natural language-driven GUI testing tool for mobile apps, capable of fully automating the entire process of GUI interaction and function verification.

✨ The Next Gen Airtable Alternative: No-Code Postgres

AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps.