bolt.diy: AI-Powered Full-Stack Web Development with Any LLM in Your Browser
This repository profile is provided by osrepos.com, an open source repository discovery platform.

Summary
bolt.diy is an open-source project that empowers developers to prompt, run, edit, and deploy full-stack web applications directly in their browser. It offers unparalleled flexibility by supporting over 19 different Large Language Models (LLMs), allowing users to choose their preferred AI for code generation and development tasks. This tool streamlines the development workflow, making AI-assisted coding accessible and highly customizable.
Repository Information
Topics
Click on any tag to explore related repositories
Use at your own risk
OSRepos shares public repositories for knowledge and discovery only. Any installation, execution, configuration, or use of code from these repositories is the user's own responsibility. Always review the repository, source code, dependencies, licenses, and security implications before running or installing anything. OSRepos is not responsible for issues, damages, or losses resulting from third-party repositories.
Introduction
bolt.diy is the official open-source version of Bolt.new, a revolutionary platform for AI-powered full-stack web development. This project allows you to leverage the power of various Large Language Models (LLMs) to create, modify, and deploy web applications directly from your browser. With support for a wide array of AI providers, including OpenAI, Anthropic, Google, Ollama, and many more, bolt.diy puts you in control of your AI coding assistant. It's designed for NodeJS-based applications and offers a rich set of features for a seamless development experience.
Installation
Getting started with bolt.diy is straightforward, whether you prefer a quick desktop app installation or a manual setup for more control.
Quick Installation (Desktop Application)
For the easiest way to get started, download the native desktop application:
- Visit the latest release page on GitHub.
- Download the binary appropriate for your operating system (Windows, macOS, or Linux).
- Follow the installation instructions for your platform. (For macOS, if you encounter an "app is damaged" error, run
xattr -cr /path/to/Bolt.appin your terminal).
Direct Installation (Node.js)
If you prefer to run bolt.diy directly on your machine using Node.js:
- Install Node.js: Download and install the LTS version from the Node.js Download Page.
- Install pnpm: Open your terminal and run:
npm install -g pnpm - Clone the Repository (for developers):
git clone -b stable https://github.com/stackblitz-labs/bolt.diy.git cd bolt.diy - Install Dependencies:
pnpm install - Start the Application:
pnpm run devThe application will typically be accessible in your browser at
http://localhost:5173.
Examples
bolt.diy excels at providing a comprehensive environment for AI-assisted development. You can:
- Generate Full-Stack Applications: Prompt any of the 19+ supported LLMs to scaffold and develop complete web applications, from frontend to backend.
- Iterative Development: Use the integrated terminal to run commands, revert code to earlier versions, and utilize the diff view to visualize AI-made changes, facilitating rapid iteration.
- Database Integration: Seamlessly integrate with Supabase for database management and querying directly within your project.
- Deployment: Deploy your applications directly to platforms like Netlify, Vercel, or GitHub Pages with built-in tools.
- Advanced Features: Explore capabilities like Git integration, file locking, data visualization, and even voice prompting for a truly modern development workflow. The project also offers an experimental "bolt.diy Expert" agent to assist with common questions.
Why Use bolt.diy?
bolt.diy stands out as a powerful tool for several reasons:
- Unmatched LLM Flexibility: Choose from a vast selection of cloud and local AI providers, allowing you to experiment with different models and find the best fit for your coding needs and budget.
- Integrated Development Environment: It provides a full-stack development experience in the browser, complete with a terminal, code editor, and deployment tools, minimizing context switching.
- Community-Driven Innovation: As an open-source project, bolt.diy benefits from a vibrant community, ensuring continuous improvement, new features, and robust support.
- Comprehensive Feature Set: From Git integration and project snapshots to data visualization and an Electron desktop app, it offers a rich suite of tools to enhance productivity.
- Ease of Use: With options for quick desktop installation and clear setup instructions, it's accessible to both beginners and experienced developers looking to integrate AI into their workflow.
Links
- GitHub Repository: https://github.com/stackblitz-labs/bolt.diy
- Official Documentation: https://stackblitz-labs.github.io/bolt.diy/
- Community Forum: https://thinktank.ottomator.ai
- Roadmap: https://roadmap.sh/r/ottodev-roadmap-2ovzo
- FAQ: FAQ.md
Related repositories
Similar repositories that may be relevant next.

SandBase Harness: Local-First AI Agent Runtime with Sandboxed Sessions
September 13, 2026
SandBase Harness is a local-first, self-hosted runtime for AI agents, offering sandboxed sessions, memory, and credentials. This TypeScript-based project provides a robust infrastructure for managing and observing AI agents, ensuring auditability and secure execution on your own machine or infrastructure.

A3M Router: Biology-Inspired LLM Routing for Cost Savings and Performance
September 13, 2026
A3M Router is an open-source, biology-inspired LLM router designed to optimize costs and performance across over 80 providers. It leverages principles like swarm intelligence and neural plasticity to offer adaptive, resilient, and cost-effective AI routing. This tool helps users save significantly on AI costs by intelligently selecting the best model for each query.

Skill Recorder: Turn Screen Recordings into AI Agent Skills
September 11, 2026
Skill Recorder is a desktop application that captures your on-screen work sessions, including clicks and app switches. It leverages the GitHub Copilot CLI to analyze these recordings, reconstructing them into an intent and ordered steps. This process allows users to generate reusable AI agent skills or automations for platforms like Microsoft Scout, Copilot Cowork, or Copilot Studio.

Apache Maka: A High-Performance Agent Workspace for AI Tasks
September 11, 2026
Apache Maka is an incubating project from The Apache Software Foundation, offering a high-performance agent workspace designed to meticulously record all agent activities. It provides a local-first environment for AI agents, allowing users to bring their own models and ensuring transparent, measurable task completion. This project aims to set a new standard for agent reliability and accountability.
Source repository
Open the original repository on GitHub.
11 counted GitHub visits