Lists (1)
Stars
n8n community node for Reduck: run your saved browser scripts and read their results
Stealth browser for AI agents — real Chrome over raw CDP, no Playwright/Puppeteer. TypeScript + MCP-native. Passes sannysoft 57/57, bypasses Cloudflare.
CLI that wraps the Claude Code CLI to use Claude with subscription only
🦆 Real time voice interface to talk to Claude Code
Svelte 5 library for creating forms based on JSON schema.
The official repo for “Dolphin: Document Image Pars DF42 ing via Heterogeneous Anchor Prompting”, ACL, 2025.
[ICLR 2026 Oral] ScaleCUA is the open-sourced computer use agents that can operate on cross-platform environments (Windows, macOS, Ubuntu, Android).
A novel Multimodal Large Language Model (MLLM) architecture, designed to structurally align visual and textual embeddings.
Pioneering Automated GUI Interaction with Native Agents
Awesome GUI Agent Paper List
One local control plane for every AI agent: route across models, fuse new capabilities, orchestrate tools, and stay fully in control.
The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs
An AI-powered task-management system you can drop into Cursor, Lovable, Windsurf, Roo, and others.
A simple task management system for managing AI dev agents
A tutorial website for plain vanilla web development
Full-stack web application template with FastAPI, React, SQLModel, PostgreSQL, Vite, Tailwind CSS, shadcn/ui, FastAPI Cloud, and Docker Compose.
Official code of the ACL 2025 paper "SimGRAG: Leveraging Similar Subgraphs for Knowledge Graphs Driven Retrieval-Augmented Generation"
Drop in a screenshot and convert it to clean code (HTML/Tailwind/React/Vue)
Windows Agent Arena (WAA) 🪟 is a scalable OS platform for testing and benchmarking of multi-modal AI agents.