App Builders

Open-source engine for AI app-builders: one HTTP request spins up an isolated dev container with a live preview URL.

One desktop UI that wires together ComfyUI, OpenAI, Gemini, ModelScope, and a dozen other generative APIs—plus some very opinionated legal terms.

Open CoDesign turns text prompts into prototypes, slides, and PDFs using whichever LLM you already pay for, without leaving your laptop.

A CLI generator that spits out complete FastAPI + Next.js AI apps with agents, RAG, auth, and billing wired in.

Pre-built React components for conversations, messages, and reasoning displays that install via CLI into your codebase.

An open-source vector design tool that turns text prompts into live UI by orchestrating concurrent AI agents to draw, refine, and export code.

OpenUI gives LLMs a compact, streaming-first language to generate structured React interfaces directly, cutting token overhead and skipping the JSON middleman.

Eino brings LangChain-style LLM orchestration to Go, with graph-based workflows, multi-agent teams, and built-in human-in-the-loop support.

An AI-native presentation app that generates styled slide decks from a prompt or document and lets you refine them with natural-language commands instead of menu diving.

Six quickstarts for building deployable Claude agents across support, analysis, browser automation, desktop control, and coding.

Coze Studio open-sources the core engine of ByteDance's commercial agent platform into a self-hosted visual IDE for assembling LLM agents, workflows, and plugins with minimal code.

Dyad is a local, open-source alternative to cloud-based AI app builders like v0 and Bolt, letting you generate applications on your own machine without surrendering your API keys or code.

This Tauri-and-Rust desktop shell exists because the Hermes Agent web dashboard needed a native companion that could manage its own runtime, handle file dialogs, and keep the WebView away from raw network traffic.

Denova is a local-first creative workspace that treats novel-writing and interactive fiction as two sides of the same coin, using structured lore databases and agent workflows to keep long-form AI context from collapsing into token soup.

To run a local-first team of specialist AI agents from your desktop without writing orchestration code.

It keeps generative UIs predictable by forcing LLMs to assemble JSON from a developer-approved component catalog instead of writing raw code.

LunaTranslator hooks into running visual novels—on PC or emulated console—to extract and translate text in real time, so you don’t need fan patches.

MoneyPrinter automates YouTube Shorts from a text topic, using local Ollama models to write scripts and a Dockerized queue to keep rendering reliable.

It is a visual canvas for stitching Firecrawl scraping, LLM reasoning, and human approvals into executable agent workflows without writing orchestration code.

It is a free, multi-stage curriculum that teaches beginners how to turn conversational prompts into shipping products using AI IDEs and agents.