Best open-source alternatives to Lovable

Cline is a VS Code extension that acts as an AI coding assistant. It is designed for developers who want help with software tasks that go beyond autocomplete, including understanding project structure, editing code, running commands, and validating changes in a browser. The extension works in a human-in-the-loop style: it proposes and carries out steps while asking for approval before file changes and terminal commands. It can connect to many AI providers or local models, track usage costs, and be extended with MCP tools for workflow-specific automation. It is aimed at users who want an interactive agent for day-to-day development work rather than a fully autonomous script.

Onlook is an open-source, visual-first code editor aimed at helping people craft websites, prototypes, and designs with AI. It focuses on Next.js and TailwindCSS projects, letting users start from scratch, from text or image prompts, or from prebuilt templates, then edit the resulting app visually in the browser. The project is designed for builders who want a tighter connection between design and code. Its editor supports real-time preview, direct DOM editing, code-side navigation, checkpoint-based saving, branching for experimentation, and deployment-oriented features like shareable links and custom domains. The README also indicates a web-based product with local development support, backed by a stack that includes Supabase, tRPC, Bun, Docker, and multiple AI/model providers.

Open Lovable is a developer-facing example app that uses AI to help build React applications through chat. It is positioned as an open example from the Firecrawl team, while also pointing users to Lovable.dev for a complete cloud-based solution. The project is intended for local setup and experimentation. Users clone the repository, install JavaScript dependencies, configure environment variables for Firecrawl, an LLM provider, and a sandbox provider, then run a local development server. The README suggests support for different AI backends and sandbox options, indicating that the app orchestrates external services to generate and edit applications rather than providing a self-contained editor.

bolt.diy is an open source AI coding assistant and the community-driven version of Bolt.new. It is designed for people who want to create and iterate on full-stack Node.js applications with help from large language models, while retaining the freedom to choose among many providers such as OpenAI, Anthropic, Ollama, Gemini, and others. The README emphasizes that the project is extensible and can work with additional models supported by the Vercel AI SDK. The project can be run locally, deployed with Docker, or used as a desktop application via Electron. Its workflow centers on prompt-driven coding inside the browser or desktop app, with features such as an integrated terminal, file locking, diff viewing, code rollback, project snapshots, and ZIP export. It also includes integrations for data visualization, Git operations, Supabase, MCP, and Expo app creation, making it suitable for developers experimenting with AI-assisted application building.

Srcbook is a TypeScript-focused local development platform that combines an AI-assisted app builder with a notebook environment. It is intended for developers who want to prototype, build, and iterate on web applications or interactive TypeScript notebooks from a single tool. The project runs locally as a CLI application with a web interface, and it can also be launched in Docker. For the app builder, Srcbook can generate boilerplate, edit code, fix issues, and provide a hot-reloading preview. For notebooks, it supports creating, running, sharing, exporting to markdown, and adding Mermaid diagrams for richer documentation and experimentation. The README also notes that the project is open source under Apache 2.0, requires the user to supply their own AI API key, and collects behavioral analytics that can be disabled with an environment variable.