CodinIT.dev Build With AI In Local Enviroment or With Our Web App

Documentation • Website • Desktop App Docs • Features • Get Started

This is a pnpm workspace monorepo containing two applications:

📚 WORKSPACE.md - Complete workspace guide (commands, deployment, architecture)

• 🚀 AI-Powered Code Generation - Multiple LLM providers (OpenAI, Anthropic, Google AI, and more)
• ⚡ Real-time Code Execution - Secure E2B sandboxes with live preview
• 📊 Multiple Development Environments - Python, Next.js, Vue.js, Streamlit, Gradio
• 💬 Streaming AI Responses - Real-time UI updates with Vercel AI SDK
• 🔐 Secure Authentication - Supabase auth with Row Level Security
• 📦 Package Installation - Install any npm or pip package on the fly

• 🔸 OpenAI (GPT-5, GPT-4)
• 🔸 Anthropic (Claude models)
• 🔸 Google AI (Gemini)
• 🔸 Groq (Fast inference)
• 🔸 Fireworks AI
• 🔸 Together AI
• 🔸 Mistral AI
• 🔸 xAI (Grok)
• 🔸 DeepSeek
• 🔸 Ollama (Local models)

• 🐍 Python Data Analyst - Jupyter-style execution with data visualization
• ⚛️ Next.js Developer - Full-stack React applications
• 🎨 Vue.js Developer - Vue 3 applications
• 📈 Streamlit Developer - Data apps and dashboards
• 🎯 Gradio Developer - ML model interfaces

• Next.js 14 (App Router, Server Actions)
• shadcn/ui + TailwindCSS for beautiful UI
• Vercel AI SDK for LLM streaming
• E2B for secure code execution
• Supabase for database and auth
• TypeScript for type safety

⭐ Give us a star if you like this project!

• git
• Recent version of Node.js and npm package manager
• E2B API Key
• LLM Provider API Key

In your terminal:

git clone https://github.com/Gerome-Elassaad/CodingIT.git

Enter the repository:

cd CodingIT

Run the following to install the required dependencies for both workspaces:

pnpm install

Note: This project uses pnpm workspaces. The command above installs dependencies for both the web app and desktop app.

Create a .env.local file and set the following:

# Get your API key here - https://e2b.dev/
E2B_API_KEY="your-e2b-api-key"

# OpenAI API Key
OPENAI_API_KEY=

# Other providers
ANTHROPIC_API_KEY=
GROQ_API_KEY=
FIREWORKS_API_KEY=
TOGETHER_API_KEY=
GOOGLE_AI_API_KEY=
GOOGLE_VERTEX_CREDENTIALS=
MISTRAL_API_KEY=
XAI_API_KEY=

### Optional env vars

# Domain of the site
NEXT_PUBLIC_SITE_URL=

# Rate limit
RATE_LIMIT_MAX_REQUESTS=
RATE_LIMIT_WINDOW=

# Vercel/Upstash KV (short URLs, rate limiting)
KV_REST_API_URL=
KV_REST_API_TOKEN=

# Supabase (auth)
SUPABASE_URL=
SUPABASE_ANON_KEY=

# PostHog (analytics)
NEXT_PUBLIC_POSTHOG_KEY=
NEXT_PUBLIC_POSTHOG_HOST=

### Disabling functionality (when uncommented)

# Disable API key and base URL input in the chat
# NEXT_PUBLIC_NO_API_KEY_INPUT=
# NEXT_PUBLIC_NO_BASE_URL_INPUT=

# Hide local models from the list of available models
# NEXT_PUBLIC_HIDE_LOCAL_MODELS=

Web App (Next.js):

pnpm dev

Visit http://localhost:3000

Desktop App (Electron + Remix):

pnpm desktop:dev

Or:

cd apps/desktop && pnpm dev

Visit http://localhost:5173

Web App:

pnpm build

Desktop App:

pnpm desktop:build        # Build all platforms
pnpm desktop:build:mac    # macOS only
pnpm desktop:build:win    # Windows only
pnpm desktop:build:linux  # Linux only

As an open-source project, we welcome contributions from the community. If you are experiencing any bugs or want to add some improvements, please feel free to open an issue or pull request.

1. Make sure E2B CLI is installed and you're logged in.

2. Add a new folder under sandbox-templates/

3. Initialize a new template using E2B CLI:

   e2b template init

   This will create a new file called e2b.Dockerfile.

4. Configure the Dockerfile

   Example Streamlit template:

   # Use Debian-based base image
   FROM python:3.11-slim
   
   # Install dependencies
   RUN pip3 install --no-cache-dir streamlit pandas numpy matplotlib requests seaborn plotly
   
   # Set working directory
   WORKDIR /home/user
   COPY . /home/user

5. Set the start command in e2b.toml:

   start_cmd = "cd /home/user && streamlit run app.py --server.port 8501 --server.address 0.0.0.0"

6. Deploy the template

   e2b template build --name <template-name>

   Success message:

   ✅ Building sandbox template <template-id> <template-name> finished.
   

7. Register in templates.json

   Add your template to lib/templates.json:

   "custom-template": {
     "name": "Custom Template",
     "lib": ["dependency1", "dependency2"],
     "file": "main.py",
     "instructions": "Template-specific instructions for the AI.",
     "port": 8080
   }

8. Add template logo (optional)

   Place logo SVG in public/thirdparty/templates/

1. Register the model in lib/models.json:

   {
     "id": "custom-model-id",
     "name": "Custom Model Name", 
     "provider": "Provider Name",
     "providerId": "provider-id",
     "multiModal": true
   }

   Parameters:

   • id: Unique model identifier
   • name: Display name in the UI
   • provider: Human-readable provider name
   • providerId: Provider configuration key
   • multiModal: Whether the model supports images/vision

1. Configure provider in lib/models.ts:

   Add to the providerConfigs object:

   'custom-provider': () => createOpenAI({ 
     apiKey: apiKey || process.env.CUSTOM_PROVIDER_API_KEY, 
     baseURL: baseURL || 'https://api.customprovider.com/v1' 
   })(modelNameString)

2. Set output mode (optional) in getDefaultMode:

   if (providerId === 'custom-provider') {
     return 'json' // or 'tool' or 'object'
   }

3. Add environment variable:

   CUSTOM_PROVIDER_API_KEY="your-api-key"

4. Add provider logo (optional):

   Place SVG logo in public/thirdparty/logos/

1. Fork the repository
2. Create a feature branch: git checkout -b feature/amazing-feature
3. Make your changes and test thoroughly
4. Run linting: npm run lint
5. Commit changes: git commit -m 'Add amazing feature'
6. Push to branch: git push origin feature/amazing-feature
7. Open a Pull Request

This project is licensed under the MIT License - see the LICENSE file for details.

• E2B for secure code execution environments
• Supabase for database and authentication
• Vercel for deployment and hosting
• shadcn/ui for beautiful UI components
• All the amazing AI providers making this possible