Describe a component in natural language and watch it render: OpenUI, from Weights & Biases, is an open alternative to Vercel's v0. Type a prompt like "a dark-themed dashboard with a sidebar and charts" and the LLM renders working HTML with Tailwind styling live in the browser. You then iterate conversationally, asking for changes until the design is right, and convert the result to React, Svelte, or Web Components for use in a real project. The backend is Python with LiteLLM routing, so it works with OpenAI, Anthropic, Gemini, Groq, and Mistral API keys, or fully offline against local Ollama models, including vision models like LLaVA that can generate UI from screenshot input - feed a screenshot and the model reproduces or riffs on an existing interface. Generated markup is inspectable at any point, with light and dark mode toggles, theme selection, and responsive previews across device sizes. The practical effect is compressing the mockup-review-revise loop from hours to minutes: a described layout renders in seconds and iterates through follow-up prompts, and because output converts to real framework code, prototypes feed directly into production codebases instead of staying trapped in a design tool. Self-hosting keeps unreleased product interfaces and prompts on your own server, and LiteLLM routing lets you pick the model per task - a cheap fast model for rough drafts, a stronger one for final passes, or free local models for unlimited experimentation.

AGenUI Studio turns a written description into a working interface card: an AI agent generates the UI, binds it to your APIs and data, and packages it so it runs anywhere, no Studio required. Bring your own model by entering any OpenAI-compatible or Anthropic Messages endpoint and key in the console settings, and generation proceeds contract-first, steered by design rules you publish as versioned Markdown revisions. You preview each card live as it is generated, then refine it over multiple turns while every component, binding, and action you did not target stays protected from accidental edits. The console also manages the supporting cast: a local knowledge base, API definitions, and reusable operators, all starting from bundled demo data you can swap for real services whenever you are ready. When a card is finished, download it as a self-contained Runtime Package carrying its data sources, bindings, actions, and operators, and execute it with the bundled Card Runtime inside your own application, or register a delivery target and publish straight from the workbench over a callback or a message queue. Applications subscribe to native run events over HTTP and SSE, and production deployments can replace the local defaults piece by piece, MySQL for storage, Redis for hot state, MCP services for knowledge and data, while the packages keep the same contracts. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.

Sketch a wireframe, get working code: Draw a UI turns hand-drawn layouts into web interfaces. It pairs the open-source tldraw canvas with an OpenAI vision model: you sketch a layout - boxes, labels, buttons, arrows, whatever communicates the idea - select the drawing, and click Make Real. The app snapshots your selection as a PNG, sends it to the vision API with instructions to return a single HTML file styled with Tailwind CSS, and renders the result in an iframe directly on the canvas next to your sketch. The loop is iterative: annotate the generated prototype or redraw parts of it, select both the sketch and the previous result, and generate again - the model receives the earlier HTML as context and produces an updated version. Built by Figma engineer Sawyer Hood as one of the first viral GPT-4 Vision demos and the basis for tldraw's "Make Real", it is a Next.js app that runs against your own OpenAI API key. Self-hosting matters here: the upstream demo ships without authentication, so a private deployment keeps your API key from being drained by strangers. MIT-licensed.

With over 84,000 GitHub stars since its April 2026 launch, Open Design has emerged as the definitive open-source alternative to Anthropic's Claude Design. Rather than shipping its own language model, Open Design acts as an agent-agnostic design orchestration layer that auto-detects 25+ coding CLI executables on your PATH — including Claude Code, Codex, Cursor, Gemini CLI, OpenCode, Qwen, GitHub Copilot CLI, Hermes, and Kimi — or connects to any OpenAI-compatible endpoint via its built-in BYOK proxy at /api/proxy/stream. The platform introduces a file-based protocol where SKILL.md files define composable design workflows and DESIGN.md files establish version-controlled brand systems, currently shipping 31 first-party skills and 72 brand-grade design systems. Output spans web and mobile prototypes, live dashboards, presentation decks, raster images, video, and HyperFrames motion graphics, with export pipelines for HTML, PDF, PPTX, MP4, and ZIP. The daemon architecture uses SQLite for project state and serves a sandboxed iframe preview renderer with vendored React and Babel for JSX artifacts. Deployment options include the native desktop app for macOS, Windows, and Linux, local daemon mode via pnpm tools-dev, a single-container Docker Compose path serving both API and Next.js frontend on port 7456, and Vercel deployment for the web layer. On RepoCloud, deploy Open Design on a dedicated VPS with full root SSH access, persistent storage for your design systems and generated artifacts, and complete control over which AI providers and agent CLIs your instance connects to, all under the Apache-2.0 license.

Prompt, run, edit, and deploy full-stack Node.js applications from a browser tab: Bolt.diy is the official open-source version of Bolt.new's AI coding agent. Its foundation is StackBlitz's WebContainer technology - a sandboxed in-browser Node.js environment where the AI controls the whole stack: filesystem, npm, dev servers, terminal, and browser console. That means the agent does not just generate code; it installs dependencies, runs Vite or Next.js, reads errors, and fixes them. The defining difference from Bolt.new is model choice per prompt: 19+ providers including OpenAI, Anthropic, Gemini, DeepSeek, Groq, Mistral, Amazon Bedrock, and local models via Ollama or LMStudio, extensible through the Vercel AI SDK. Development ergonomics include live preview, a diff view of AI changes, codebase search, file locking to prevent generation conflicts, 15+ starter templates (React, Vue, Next.js, Astro, Svelte, Expo), and MCP support for external tools. Projects integrate with Git and Supabase, and deploy in one click to Vercel, Netlify, or GitHub Pages.

Describe the small app you keep wishing existed, and Tinykit builds it, gives it a database, and puts it live on your server. Tell it the tool you need and the agent writes the code, creates the data collections behind it, and wires the two together, then steps aside. The result is not a screenshot of an app; it is the app, served from your own server with its data syncing in real time and its files stored beside it. Open the built-in code editor to adjust the single file behind each app, or avoid code entirely: content fields let you edit text like a miniature CMS, and the design system panel restyles colors, fonts, and shadows visually. Every change takes a snapshot, so bold prompts carry an undo button and nothing is one bad idea away from lost. Hosts running errands for a household, an internal team, or a portfolio of side projects can keep adding apps, each reachable on its own domain, with token costs for every prompt shown in real money so the building budget is never a mystery. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Open Lovable from the Firecrawl team delivers the first truly open-source alternative to Lovable.dev — a chat-driven AI copilot that takes any website URL and regenerates it as a complete, editable React application with TypeScript and Tailwind CSS in seconds. The pipeline combines Firecrawl's intelligent web scraping for JavaScript-rendered pages and single-page applications with your choice of AI provider — Claude, GPT-4, Google Gemini, or Groq — to analyze HTML structure, extract layouts and styling, decompose pages into proper React components, and generate production-ready code following modern best practices. Live preview runs in a secure sandbox environment using Vercel Sandbox with OIDC authentication or E2B Cloud, letting you see results immediately and iterate through natural language chat to request changes like Tailwind migration, componentization, SEO improvements, accessibility fixes, or custom form implementations. The optional Morph LLM fast-apply path accelerates small edits by applying diffs directly without full regeneration. The provider-agnostic architecture means you control costs by routing to different models — use Groq for fast iterations and Claude for complex layouts. Project structure follows Next.js conventions with organized app, components, atoms, styles, utils, and hooks directories. Deploy via pnpm with Node.js 18+ requiring only a Firecrawl API key, one AI provider key, and a sandbox provider configuration. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Large language models get a polished front end that can run fully offline: Open WebUI is the self-hosted front end of choice. It talks to local model runners, primarily Ollama, and to any OpenAI-compatible API, so LM Studio, vLLM, Groq, Mistral, OpenRouter, and cloud providers all plug into the same chat interface and can be mixed per conversation. RAG is built in: upload files to knowledge bases or reference them in chat with the # command, backed by a choice of nine vector databases (ChromaDB and PGVector officially maintained) and multiple extraction engines including Tika and Docling, with hybrid BM25-plus-vector search and cross-encoder reranking. Web search results from providers like SearXNG, Brave, and Tavily inject directly into conversations. Extensibility comes from Python tools and functions that run inside the chat, a Pipelines plugin framework, and native MCP support. Multi-user features include RBAC, SSO, and group permissions, and the instance itself exposes an OpenAI-compatible API your own apps can call.

Libre WebUI is a self-hosted AI workspace that keeps chat, notes, personas, and agent tasks in one place you control. Local models run through Ollama, and hosted ones come from OpenAI, Anthropic, Gemini, Groq, Mistral, OpenRouter, or any OpenAI-compatible endpoint added on the provider settings page. Pick a model per conversation. Replies stream, prompts queue, chats fork into branches, and several models can answer side by side. Notes keep Markdown documents with revision history. Personas bundle a system prompt, a model, and memory into a reusable assistant, and prompt templates with typed variables appear when you type a slash in the composer. Knowledge collections ground answers in uploaded documents and cite their sources. The Work area gives each task its own workspace with files, a terminal, diffs, and a live preview, and automations run scheduled prompts that arrive as normal chats. Administrators create users and groups, hand out roles, issue scoped API tokens, and share chats, notes, and personas through one grant model. A private team assistant, a research desk, or a sandbox where agents build small apps all fit here. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.

Every major model provider behind one ChatGPT-style interface: LibreChat spans OpenAI, Anthropic, Google, Azure, AWS Bedrock, Vertex AI, Groq, Mistral, OpenRouter, DeepSeek, and any OpenAI-compatible endpoint including local Ollama. You can switch models mid-conversation and compare providers without changing tools. Its Agents framework builds no-code custom assistants with tool access via Model Context Protocol servers, file search over uploaded documents through an optional pgvector-backed RAG service, and a sandboxed Code Interpreter that executes Python, JavaScript, Go, C++, Java, PHP, and Rust. Artifacts render React components, HTML, and Mermaid diagrams directly in chat, and image generation works through DALL-E and other configured providers. Multi-user support is enterprise-grade, with OAuth, SAML, LDAP, and two-factor authentication, per-user conversation history in MongoDB, and Meilisearch-powered search across all messages and files, plus reusable presets, forkable threads, and persistent memory across conversations. The economics favor teams: instead of a ChatGPT Plus seat per person, everyone shares one instance billed per API token, with access to every provider rather than one - and providers see individual API calls, not your accumulated organizational knowledge. Deployment is Docker Compose; API keys and endpoints are configured through .env and librechat.yaml.

A private ChatGPT built with Next.js: Lobe Chat is the open-source AI chat interface teams self-host instead. Its main advantage is provider breadth: one interface connects to 40+ model providers, including OpenAI, Anthropic Claude, Google Gemini, Mistral, Groq, AWS Bedrock, Azure, and local models served through Ollama, so you can switch models per conversation and compare outputs. It handles multi-modal work: image recognition, image generation, text-to-speech, and speech-to-text. A plugin system based on function calling and the Model Context Protocol (MCP) adds external tools like web search and code execution. Run it in standalone mode as a single container with settings in browser storage, or in database mode with PostgreSQL and S3-compatible storage for persistent history, multi-user auth, and RAG knowledge bases built from uploaded documents with pgvector retrieval. Because tools arrive through function calling and MCP rather than a proprietary plugin format, custom internal tools can be exposed to the assistant with a standard server over STDIO or HTTP. Hundreds of pre-configured assistant roles import from the community marketplace. For teams the cost model matters: provider API keys billed per token typically undercut a ChatGPT Plus seat per person, and self-hosting keeps API keys, uploaded files, embeddings, and conversation history entirely on your own server.

Self-hosting a language model is only half the job; people still need somewhere pleasant to talk to it, and Chat UI is that window, the same interface that powers HuggingChat. Point it at any OpenAI-compatible endpoint, your own Ollama or llama.cpp server, the Hugging Face router, or a hosted gateway like OpenRouter, and the models it serves appear in the picker automatically, with no per-model configuration. Conversations are saved to your database and stay browsable in the sidebar, so a thread from last week can be reopened, continued, and compared against a fresh answer from another model. Multimodal models accept image uploads right in the composer, and models that support it can call MCP tools mid-conversation to fetch data or run actions. For a shared team deployment, OpenID Connect sign-in keeps individual histories and settings separate, and per-user defaults travel with each account. Everything a consumer chatbot would keep on someone else's servers, prompts, uploaded files, and usage history, stays in the MongoDB you control on the same machine. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.

Thirteen-plus LLM providers, one unified client: NextChat (formerly ChatGPT-Next-Web) is an open-source AI chat interface built on Next.js that spans OpenAI GPT-4, Anthropic Claude, Google Gemini, DeepSeek, Groq, Azure endpoints, and self-hosted backends like Ollama, LocalAI, and RWKV-Runner. Its defining trait is minimalism - the first screen loads in about 100 KB, the desktop client is roughly 5 MB, and there is no database or user system to operate; chat history lives locally in the browser with optional WebDAV or UpStash Redis sync. The Mask system saves reusable prompt-template personas you can share and debug, long conversations auto-compress to fit context windows, and Markdown rendering covers LaTeX, Mermaid diagrams, and code highlighting with streaming responses. Plugins add web search and calculators, MCP support enables external tool calling, and Artifacts previews generated content in a separate pane. Ships as a web app, Docker image, and Tauri desktop builds for Windows, macOS, and Linux, translated into 20+ languages. MIT-licensed.

Bring your own API keys and work with OpenAI GPT models, Anthropic Claude, Google Gemini, Mistral, DeepSeek, Grok, Azure endpoints, and local models in one organized workspace: TypingMind is a unified chat frontend for large language models, replacing a browser tab per provider. Parallel chat sends the same prompt to multiple models and compares answers side by side, and models can be switched mid-conversation. A prompt library stores reusable, tagged prompts with variables, and the AI Agents system builds specialized assistants that bundle a base model, custom instructions, assigned plugins, and uploaded knowledge files for RAG. Plugins extend every connected model with web search, image generation (DALL-E, Stable Diffusion), Deep Research, URL reading via Firecrawl, and Zapier automation - plus MCP server integrations for Notion, Atlassian, and other external tools, and a JavaScript extension API for custom behavior. Chats store locally by default with optional sync. Self-hosting puts the interface on your own domain and, for teams, adds branding, member access limits, and shared prompt and agent libraries.

Open-source alternative to OpenAI's Canvas — a collaborative writing and coding environment where AI agents help you draft, edit, and refine documents through an agentic architecture built on LangGraph. The dual-mode editor combines a BlockNote rich text editor for live-rendered markdown with a CodeMirror-based code editor supporting syntax highlighting across multiple programming languages, letting you switch between prose and code artifacts within the same session. The built-in reflection agent automatically generates style rules and user insights from your chat history, storing them in a shared LangGraph memory store that persists across sessions for increasingly personalized assistance. Pre-built quick actions provide one-click access to common writing transformations including summarize, expand, simplify, and translate, while coding actions offer explain, refactor, add comments, and convert between languages. The monorepo architecture separates the Next.js 14 frontend from the LangGraph agent backend, connecting via HTTP and WebSocket protocols through the @langchain/langgraph-sdk client. Seven LLM providers are supported out of the box — OpenAI, Anthropic Claude, Google Gemini, Fireworks AI, Groq, Azure OpenAI, and local Ollama models — with Supabase handling authentication and data persistence. Deploy via Docker or build from source. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

OpenPencil is the open-source design editor that reads and writes native Figma .fig files using the same Kiwi binary format — enabling bidirectional copy-paste between Figma and OpenPencil without data loss. The built-in AI assistant provides 90+ design tools through a chat interface, creating and modifying shapes, fills, strokes, auto-layout, components, variables, and boolean operations from natural language prompts, with BYOK support for Anthropic, OpenAI, Google AI, OpenRouter, Z.ai, MiniMax, and compatible endpoints. A Skia CanvasKit WASM renderer paired with Yoga WASM layout engine delivers Figma-parity rendering with flex and CSS Grid support including gap, padding, and alignment. The headless CLI inspects node trees via XPath queries, lints naming and accessibility, converts between document formats, analyzes color and typography patterns, extracts design tokens, and exports to PNG, SVG, JSX/Tailwind, and HTML. An MCP server exposes all design operations over stdio and HTTP, connecting Claude Code, Cursor, Windsurf, and Gemini CLI for AI-assisted design automation. Real-time P2P collaboration via WebRTC with Yjs CRDT synchronization requires no server and no account. The Vue SDK provides headless components for embedding the editor into custom applications. Ships as a 7 MB Tauri v2 desktop app for macOS, Windows, and Linux, or runs in any browser as a PWA. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.