🚀 Your AI Product Manager & Architect - Transform ideas into complete development plans with AI coding prompts in 60-180 seconds

Open-source AI agents for penetration testing

Open-source, secure environment with real-world tools for enterprise-grade agents.

🔥 Clone and recreate any website as a modern React app in seconds

Kiro is an agentic IDE that works alongside you from prototype to production.

The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.

Official code repo for the O'Reilly Book - "Hands-On Large Language Models"

Tersa is an open source canvas for building AI workflows.

Free, local, open-source AI app builder ✨ v0 / lovable / Bolt alternative 🌟 Star if you like it!

No fortress, purely open ground. OpenManus is Coming.

Build Anything with AI Agents

An open-source implementaion for fine-tuning Qwen-VL series by Alibaba Cloud.

Tool for generating high quality Synthetic datasets

Multi-modal OCR pipeline optimized for ML training (text, figure, math, tables, diagrams)

FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae, Traycer AI…

An AI-powered task-management system you can drop into Cursor, Lovable, Windsurf, Roo, and others.

Riona Ai Agent 🌸 is built using Node.js and TypeScript 🛠️, designed for seamless job execution 📸. It's lightweight, efficient, and still evolving 🚧—exciting new features coming soon! 🌟

A visual no-code theme editor for shadcn/ui components

LAYRA—an enterprise-ready, out-of-the-box solution—unlocks next-generation intelligent systems powered by visual RAG and limitless visual multi-step agent workflow orchestration.

An open source TypeScript deep research implementation

Pocket Flow: Codebase to Tutorial

🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。

Improved file parsing for LLM’s

Open Machine Learning course

🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization, with PyTorch/CUDA

Python-based turnstile solver using the patchright library, featuring multi-threaded execution, API integration, and support for different browsers.