Open-source alternatives to Replit

ai-website-cloner-template

Next.js template with an agent skill that rebuilds a website from its URL

A Next.js 16 template (React 19, Tailwind CSS v4, shadcn/ui) that bundles a portable `clone-website` agent skill. Given a URL, the agent maps routes, inspects desktop and mobile pages, extracts assets and fonts, builds editable components, then compares source and local pages and runs `npm run check`. It works with Claude Code, Codex CLI, Cursor and OpenCode.

• TypeScript, Claude Code (Opus 5.5 recommended), Codex CLI, Cursor, OpenCode
• Needs Node.js 24+, AI coding agent with browser access
• GitHub template
• Docker

jeecgboot

Java low-code platform with code generator and built-in AI app builder

JeecgBoot is a Spring Boot 4 and Vue3 platform for building enterprise systems such as OA, ERP and CRM. It pairs an online form builder and code generator with an AI module (model management, knowledge base with RAG, flow orchestration, MCP plugins, chat assistant) built on langchain4j. It runs as a monolith or as Spring Cloud Alibaba microservices.

• Java, ChatGPT, DeepSeek, Qwen, Zhipu
• Needs MySQL 5.7+, Redis, Nacos (microservice mode), MinIO or Aliyun OSS (optional)

dyad

Desktop app that builds apps from prompts on your own machine

Dyad is a local, open-source prompt-to-app builder, positioned as an alternative to Lovable, v0 and Bolt that runs on your own computer. It ships as a downloadable app for Mac and Windows and uses your own AI API keys, with no sign-up. Code outside src/pro is Apache 2.0; src/pro is under the Functional Source License 1.1.

• TypeScript
• Needs Your own AI provider API keys
• env example file

e2b

SDKs for running AI-generated code in isolated cloud sandboxes

E2B provides JavaScript and Python SDKs that start isolated cloud sandboxes and run shell commands inside them. Companion packages add a Code Interpreter (runCode/run_code) and a Desktop SDK for mouse, keyboard and screenshot control. The runtime can be self-hosted with Terraform on AWS, GCP, Azure or a generic Linux machine; the hosted service needs an API key.

• Python
• Needs E2B API key (hosted), Terraform (self-hosting)
• Docker

llamacoder

Next.js app that turns one prompt into a small React app

Llama Coder sends a text prompt to Llama 3.1 405B through Together AI and renders the generated app in a sandboxed iframe using esbuild-wasm and esm.sh. It is a Next.js app router project with Tailwind, Prisma on PostgreSQL, and optional screenshot uploads to S3.

• TypeScript, Llama 3.1 405B
• Needs Together AI API, PostgreSQL (Neon), Prisma, S3 bucket (screenshot uploads), Braintrust (optional), esm.sh

vibesdk

Self-hosted prompt-to-app platform on Cloudflare Workers and Durable Objects

Bun and Vite project that runs a coding agent (Cloudflare Think) in a Durable Object per project, keeps files in a SpaceDO workspace, stores git history in Cloudflare Artifacts, loads previews as Dynamic Workers and gives each generated app SQLite via Durable Object Facets. Models route through AI Gateway; D1 holds platform data. Needs a Workers Paid plan, Workers for Platforms and a custom domain with wildcard DNS.

• TypeScript, Cloudflare AI Gateway (configured providers)
• Needs Cloudflare account with Workers Paid plan, Cloudflare AI Gateway, D1, model provider API key, custom domain with wildcard DNS

open-lovable

Chat-driven React app builder that clones sites via Firecrawl and runs code in sandboxes

Next.js app where you describe a React app in chat and an LLM generates and edits the code inside a remote sandbox (Vercel Sandbox by default, or E2B). It uses the Firecrawl API to scrape existing sites as reference material. The LLM can be Gemini, Anthropic, OpenAI or Groq, with optional Morph for faster edit application.

• TypeScript, Gemini, Anthropic, OpenAI, Groq
• Needs Firecrawl API, Vercel Sandbox or E2B, Morph (optional)
• env example file

fragments

Open-source Claude Artifacts alternative that runs AI-generated apps in sandboxes

Next.js 14 app that takes a chat prompt, has an LLM generate code, and runs it in an E2B cloud sandbox with a live preview. Built-in stacks are Python interpreter, Next.js, Vue.js, Streamlit and Gradio, and more can be added as E2B sandbox templates. It supports OpenAI, Anthropic, Google AI, Mistral, Groq, Fireworks, Together AI and Ollama.

• TypeScript, OpenAI, Anthropic, Google AI, Google Vertex
• Needs E2B API key, LLM provider API key, Supabase (optional, auth), Vercel/Upstash KV (optional), PostHog (optional), Morph API key (optional)
• env example file

monkeycode

AI development platform that runs coding tasks in server-side environments

MonkeyCode is a web platform where AI agents carry out development tasks inside server-side environments, with build, test and preview done remotely. It adds model management, task management, requirement/SPEC management and automated PR/MR review for engineering teams. It can be used online or installed inside a private network with an install script.

• TypeScript, GLM, Kimi, MiniMax, Qwen

Onlook

Visual editor that edits Next.js and Tailwind apps with AI

Its own README calls it an alternative to Replit.

Browser-based editor that loads a Next.js and Tailwind project into a web container, renders it in an iframe and maps DOM elements back to source so you can drag, restyle and edit visually or through an AI chat. Built on Next.js, tRPC, Supabase, Drizzle and the Vercel AI SDK with OpenRouter for models and CodeSandbox for sandboxes. For designers and front-end developers working on Next.js codebases.

• no GPU
• Docker + Compose
• Needs Supabase (auth, database, storage), OpenRouter API key, CodeSandbox SDK, Bun
• Models: OpenRouter-hosted models, Morph Fast Apply, Relace
• README: alternative to Lovable, v0, Bolt.new, Replit