{"config":{"lang":["en"],"separator":"[\\s\\-]+","pipeline":["stopWordFilter"]},"docs":[{"location":"","title":"Welcome to Bolt DIY","text":"

Bolt.diy allows you to choose the LLM that you use for each prompt! Currently, you can use OpenAI, Anthropic, Ollama, OpenRouter, Gemini, LMStudio, Mistral, xAI, HuggingFace, DeepSeek, or Groq models - and it is easily extended to use any other model supported by the Vercel AI SDK! See the instructions below for running this locally and extending it to include more models.

Join the community!

https://thinktank.ottomator.ai

"},{"location":"#whats-boltdiy","title":"Whats Bolt.diy","text":"

Bolt.diy is an AI-powered web development agent that allows you to prompt, run, edit, and deploy full-stack applications directly from your browser\u2014no local setup required. If you're here to build your own AI-powered web dev agent using the Bolt open source codebase, click here to get started!

"},{"location":"#what-makes-boltdiy-different","title":"What Makes Bolt.diy Different","text":"

Claude, v0, etc are incredible- but you can't install packages, run backends, or edit code. That\u2019s where Bolt.diy stands out:

Whether you\u2019re an experienced developer, a PM, or a designer, Bolt.diy allows you to easily build production-grade full-stack applications.

For developers interested in building their own AI-powered development tools with WebContainers, check out the open-source Bolt codebase in this repo!

"},{"location":"#setup","title":"Setup","text":"

Many of you are new users to installing software from Github. If you have any installation troubles reach out and submit an \"issue\" using the links above, or feel free to enhance this documentation by forking, editing the instructions, and doing a pull request.

  1. Install Git from https://git-scm.com/downloads

  2. Install Node.js from https://nodejs.org/en/download/

Pay attention to the installer notes after completion.

On all operating systems, the path to Node.js should automatically be added to your system path. But you can check your path if you want to be sure. On Windows, you can search for \"edit the system environment variables\" in your system, select \"Environment Variables...\" once you are in the system properties, and then check for a path to Node in your \"Path\" system variable. On a Mac or Linux machine, it will tell you to check if /usr/local/bin is in your $PATH. To determine if usr/local/bin is included in $PATH\u00a0open your Terminal and run:

echo $PATH\u00a0.\n

If you see usr/local/bin in the output then you're good to go.

  1. Clone the repository (if you haven't already) by opening a Terminal window (or CMD with admin permissions) and then typing in this:
git clone https://github.com/stackblitz-labs/bolt.diy.git\n
  1. Rename .env.example to .env.local and add your LLM API keys. You will find this file on a Mac at \"[your name]/bolt.diy/.env.example\". For Windows and Linux the path will be similar.

If you can't see the file indicated above, its likely you can't view hidden files. On Mac, open a Terminal window and enter this command below. On Windows, you will see the hidden files option in File Explorer Settings. A quick Google search will help you if you are stuck here.

defaults write com.apple.finder AppleShowAllFiles YES\n

NOTE: you only have to set the ones you want to use and Ollama doesn't need an API key because it runs locally on your computer:

Get your GROQ API Key here: https://console.groq.com/keys

Get your Open AI API Key by following these instructions: https://help.openai.com/en/articles/4936850-where-do-i-find-my-openai-api-key

Get your Anthropic API Key in your account settings: https://console.anthropic.com/settings/keys

GROQ_API_KEY=XXX\nOPENAI_API_KEY=XXX\nANTHROPIC_API_KEY=XXX\n

Optionally, you can set the debug level:

VITE_LOG_LEVEL=debug\n

Important: Never commit your .env.local file to version control. It's already included in .gitignore.

"},{"location":"#run-with-docker","title":"Run with Docker","text":"

Prerequisites:

Git and Node.js as mentioned above, as well as Docker: https://www.docker.com/

"},{"location":"#1a-using-helper-scripts","title":"1a. Using Helper Scripts","text":"

NPM scripts are provided for convenient building:

# Development build\nnpm run dockerbuild\n\n# Production build\nnpm run dockerbuild:prod\n
"},{"location":"#1b-direct-docker-build-commands-alternative-to-using-npm-scripts","title":"1b. Direct Docker Build Commands (alternative to using NPM scripts)","text":"

You can use Docker's target feature to specify the build environment instead of using NPM scripts if you wish:

# Development build\ndocker build . --target bolt-ai-development\n\n# Production build\ndocker build . --target bolt-ai-production\n
"},{"location":"#2-docker-compose-with-profiles-to-run-the-container","title":"2. Docker Compose with Profiles to Run the Container","text":"

Use Docker Compose profiles to manage different environments:

# Development environment\ndocker-compose --profile development up\n\n# Production environment\ndocker-compose --profile production up\n

When you run the Docker Compose command with the development profile, any changes you make on your machine to the code will automatically be reflected in the site running on the container (i.e. hot reloading still applies!).

"},{"location":"#run-without-docker","title":"Run Without Docker","text":"
  1. Install dependencies using Terminal (or CMD in Windows with admin permissions):
pnpm install\n

If you get an error saying \"command not found: pnpm\" or similar, then that means pnpm isn't installed. You can install it via this:

sudo npm install -g pnpm\n
  1. Start the application with the command:
pnpm run dev\n
"},{"location":"#adding-new-llms","title":"Adding New LLMs:","text":"

To make new LLMs available to use in this version of Bolt.diy, head on over to app/utils/constants.ts and find the constant MODEL_LIST. Each element in this array is an object that has the model ID for the name (get this from the provider's API documentation), a label for the frontend model dropdown, and the provider.

By default, Anthropic, OpenAI, Groq, and Ollama are implemented as providers, but the YouTube video for this repo covers how to extend this to work with more providers if you wish!

When you add a new model to the MODEL_LIST array, it will immediately be available to use when you run the app locally or reload it. For Ollama models, make sure you have the model installed already before trying to use it here!

"},{"location":"#available-scripts","title":"Available Scripts","text":""},{"location":"#development","title":"Development","text":"

To start the development server:

pnpm run dev\n

This will start the Remix Vite development server. You will need Google Chrome Canary to run this locally if you use Chrome! It's an easy install and a good browser for web development anyway.

"},{"location":"#tips-and-tricks","title":"Tips and Tricks","text":"

Here are some tips to get the most out of Bolt.diy:

"},{"location":"CONTRIBUTING/","title":"Contribution Guidelines","text":""},{"location":"CONTRIBUTING/#default_num_ctx","title":"DEFAULT_NUM_CTX","text":"

The DEFAULT_NUM_CTX environment variable can be used to limit the maximum number of context values used by the qwen2.5-coder model. For example, to limit the context to 24576 values (which uses 32GB of VRAM), set DEFAULT_NUM_CTX=24576 in your .env.local file.

First off, thank you for considering contributing to Bolt.diy! This fork aims to expand the capabilities of the original project by integrating multiple LLM providers and enhancing functionality. Every contribution helps make Bolt.diy a better tool for developers worldwide.

"},{"location":"CONTRIBUTING/#table-of-contents","title":"\ud83d\udccb Table of Contents","text":""},{"location":"CONTRIBUTING/#code-of-conduct","title":"Code of Conduct","text":"

This project and everyone participating in it is governed by our Code of Conduct. By participating, you are expected to uphold this code. Please report unacceptable behavior to the project maintainers.

"},{"location":"CONTRIBUTING/#how-can-i-contribute","title":"How Can I Contribute?","text":""},{"location":"CONTRIBUTING/#reporting-bugs-and-feature-requests","title":"\ud83d\udc1e Reporting Bugs and Feature Requests","text":""},{"location":"CONTRIBUTING/#code-contributions","title":"\ud83d\udd27 Code Contributions","text":"
  1. Fork the repository
  2. Create a new branch for your feature/fix
  3. Write your code
  4. Submit a pull request
"},{"location":"CONTRIBUTING/#becoming-a-core-contributor","title":"\u2728 Becoming a Core Contributor","text":"

We're looking for dedicated contributors to help maintain and grow this project. If you're interested in becoming a core contributor, please fill out our Contributor Application Form.

"},{"location":"CONTRIBUTING/#pull-request-guidelines","title":"Pull Request Guidelines","text":""},{"location":"CONTRIBUTING/#pr-checklist","title":"\ud83d\udcdd PR Checklist","text":""},{"location":"CONTRIBUTING/#review-process","title":"\ud83d\udc40 Review Process","text":"
  1. Manually test the changes
  2. At least one maintainer review required
  3. Address all review comments
  4. Maintain clean commit history
"},{"location":"CONTRIBUTING/#coding-standards","title":"Coding Standards","text":""},{"location":"CONTRIBUTING/#general-guidelines","title":"\ud83d\udcbb General Guidelines","text":""},{"location":"CONTRIBUTING/#development-setup","title":"Development Setup","text":""},{"location":"CONTRIBUTING/#initial-setup","title":"\ud83d\udd04 Initial Setup","text":"
  1. Clone the repository:
git clone https://github.com/stackblitz-labs/bolt.diy.git\n
  1. Install dependencies:
pnpm install\n
  1. Set up environment variables:
  2. Rename .env.example to .env.local
  3. Add your LLM API keys (only set the ones you plan to use):
GROQ_API_KEY=XXX\nHuggingFace_API_KEY=XXX\nOPENAI_API_KEY=XXX\nANTHROPIC_API_KEY=XXX\n...\n
VITE_LOG_LEVEL=debug\n
DEFAULT_NUM_CTX=32768\n

Some Example Context Values for the qwen2.5-coder:32b models are.

Important: Never commit your .env.local file to version control. It's already included in .gitignore.

"},{"location":"CONTRIBUTING/#running-the-development-server","title":"\ud83d\ude80 Running the Development Server","text":"
pnpm run dev\n

Note: You will need Google Chrome Canary to run this locally if you use Chrome! It's an easy install and a good browser for web development anyway.

"},{"location":"CONTRIBUTING/#testing","title":"Testing","text":"

Run the test suite with:

pnpm test\n
"},{"location":"CONTRIBUTING/#deployment","title":"Deployment","text":"

To deploy the application to Cloudflare Pages:

pnpm run deploy\n

Make sure you have the necessary permissions and Wrangler is correctly configured for your Cloudflare account.

"},{"location":"CONTRIBUTING/#docker-deployment-documentation","title":"Docker Deployment Documentation","text":"

This guide outlines various methods for building and deploying the application using Docker.

"},{"location":"CONTRIBUTING/#build-methods","title":"Build Methods","text":""},{"location":"CONTRIBUTING/#1-using-helper-scripts","title":"1. Using Helper Scripts","text":"

NPM scripts are provided for convenient building:

# Development build\nnpm run dockerbuild\n\n# Production build\nnpm run dockerbuild:prod\n
"},{"location":"CONTRIBUTING/#2-direct-docker-build-commands","title":"2. Direct Docker Build Commands","text":"

You can use Docker's target feature to specify the build environment:

# Development build\ndocker build . --target bolt-ai-development\n\n# Production build\ndocker build . --target bolt-ai-production\n
"},{"location":"CONTRIBUTING/#3-docker-compose-with-profiles","title":"3. Docker Compose with Profiles","text":"

Use Docker Compose profiles to manage different environments:

# Development environment\ndocker-compose --profile development up\n\n# Production environment\ndocker-compose --profile production up\n
"},{"location":"CONTRIBUTING/#running-the-application","title":"Running the Application","text":"

After building using any of the methods above, run the container with:

# Development\ndocker run -p 5173:5173 --env-file .env.local bolt-ai:development\n\n# Production\ndocker run -p 5173:5173 --env-file .env.local bolt-ai:production\n
"},{"location":"CONTRIBUTING/#deployment-with-coolify","title":"Deployment with Coolify","text":"

Coolify provides a straightforward deployment process:

  1. Import your Git repository as a new project
  2. Select your target environment (development/production)
  3. Choose \"Docker Compose\" as the Build Pack
  4. Configure deployment domains
  5. Set the custom start command: 
    docker compose --profile production up\n
  6. Configure environment variables
  7. Add necessary AI API keys
  8. Adjust other environment variables as needed
  9. Deploy the application
"},{"location":"CONTRIBUTING/#vs-code-integration","title":"VS Code Integration","text":"

The docker-compose.yaml configuration is compatible with VS Code dev containers:

  1. Open the command palette in VS Code
  2. Select the dev container configuration
  3. Choose the \"development\" profile from the context menu
"},{"location":"CONTRIBUTING/#environment-files","title":"Environment Files","text":"

Ensure you have the appropriate .env.local file configured before running the containers. This file should contain:

"},{"location":"CONTRIBUTING/#notes","title":"Notes","text":""},{"location":"FAQ/","title":"Frequently Asked Questions (FAQ)","text":""},{"location":"FAQ/#how-do-i-get-the-best-results-with-boltdiy","title":"How do I get the best results with Bolt.diy?","text":""},{"location":"FAQ/#how-do-i-contribute-to-boltdiy","title":"How do I contribute to Bolt.diy?","text":"

Check out our Contribution Guide for more details on how to get involved!

"},{"location":"FAQ/#what-are-the-future-plans-for-boltdiy","title":"What are the future plans for Bolt.diy?","text":"

Visit our Roadmap for the latest updates. New features and improvements are on the way!

"},{"location":"FAQ/#why-are-there-so-many-open-issuespull-requests","title":"Why are there so many open issues/pull requests?","text":"

Bolt.diy began as a small showcase project on @ColeMedin's YouTube channel to explore editing open-source projects with local LLMs. However, it quickly grew into a massive community effort!

We\u2019re forming a team of maintainers to manage demand and streamline issue resolution. The maintainers are rockstars, and we\u2019re also exploring partnerships to help the project thrive.

"},{"location":"FAQ/#how-do-local-llms-compare-to-larger-models-like-claude-35-sonnet-for-boltdiy","title":"How do local LLMs compare to larger models like Claude 3.5 Sonnet for Bolt.diy?","text":"

While local LLMs are improving rapidly, larger models like GPT-4o, Claude 3.5 Sonnet, and DeepSeek Coder V2 236b still offer the best results for complex applications. Our ongoing focus is to improve prompts, agents, and the platform to better support smaller local LLMs.

"},{"location":"FAQ/#common-errors-and-troubleshooting","title":"Common Errors and Troubleshooting","text":""},{"location":"FAQ/#there-was-an-error-processing-this-request","title":"\"There was an error processing this request\"","text":"

This generic error message means something went wrong. Check both:

"},{"location":"FAQ/#x-api-key-header-missing","title":"\"x-api-key header missing\"","text":"

This error is sometimes resolved by restarting the Docker container. If that doesn\u2019t work, try switching from Docker to pnpm or vice versa. We\u2019re actively investigating this issue.

"},{"location":"FAQ/#blank-preview-when-running-the-app","title":"Blank preview when running the app","text":"

A blank preview often occurs due to hallucinated bad code or incorrect commands. To troubleshoot:

"},{"location":"FAQ/#everything-works-but-the-results-are-bad","title":"\"Everything works, but the results are bad\"","text":"

Local LLMs like Qwen-2.5-Coder are powerful for small applications but still experimental for larger projects. For better results, consider using larger models like GPT-4o, Claude 3.5 Sonnet, or DeepSeek Coder V2 236b.

Got more questions? Feel free to reach out or open an issue in our GitHub repo!

"}]}