Lovable Project Management

# Lovable Project Management Manage Lovable projects via browser automation — rename projects, configure knowledge, set up domains, publish, and control settings. ## Prerequisites - Chrome MCP browser tools available - Logged in to lovable.dev ## Accessing Project Settings ``` 1. Navigate to the project: lovable.dev/projects/<project-id> 2. Open settings via the gear icon in the top toolbar, or navigate directly: lovable.dev/projects/<project-id>/settings/project 3. The settings sidebar has these sections: - Project: Project settings, Domains - Workspace: Local Media Concepts, People, Plans & credits, Cloud & AI balance, Workspace domains, Privacy & security - Account: Your account, Labs - Knowledge: Knowledge - Connectors: Connectors ``` ## Rename a Project ``` 1. Go to Project settings (Settings > Project settings) 2. Find "Project name" with a pencil/edit icon next to it 3. Click the pencil icon to make the name editable 4. Clear the existing name and type the new name 5. Press Enter or click away to save ``` The project settings page also shows: - URL subdomain - Owner email - Created date - Messages count, AI edits count, Credits used ## Set Project Knowledge Knowledge gives Lovable context about your project so it generates better code. ``` 1. Go to Settings > Knowledge URL: lovable.dev/projects/<id>/settings/knowledge 2. You'll see two sections: a) Project knowledge — specific to this project - Text area with placeholder: "Describe your project, its tech stack, and any specific guidelines..." - Fill in: app purpose, target users, APIs, database schema, architecture, rules/constraints - Click "Get inspiration" button for examples b) Workspace knowledge — shared across all projects - Text area with placeholder: "Set coding style, conventions, and preferences for all your projects..." - Fill in: coding style, naming conventions, preferred libraries, behavioral rules (tone, language, formatting) ``` **What to include in project knowledge:** - App purpose and target users - Tech stack preferences (e.g., "Use shadcn/ui components", "Tailwind for styling") - API endpoints or database schema - Design system rules (colors, fonts, spacing) - Any constraints ("No external dependencies", "Must be accessible") ## Configure Project Visibility ``` 1. On the Project settings page, find "Project visibility" 2. Click the dropdown (default: "Workspace") 3. Options: Workspace (team only) or Public (anyone can view/remix) ``` ## Set Project Category ``` 1. On the Project settings page, find "Project category" 2. Click "Select category" dropdown 3. Choose a category to help others find your project ``` ## Manage Domains ``` 1. Go to Settings > Domains URL: lovable.dev/projects/<id>/settings/domains 2. Note: Project must be published first — click "Publish now" if banner shows 3. Buy a new domain: - Lovable suggests domain names based on your project - Click "Buy new domain" to purchase through Lovable 4. Connect existing domain: - Click "Connect domain" - Enter your domain name - Configure DNS: add CNAME record pointing to Lovable's servers - Wait for DNS propagation and verification ``` ## Publish a Project ``` 1. In the project editor, find the "Publish" button in the top-right toolbar 2. Click "Publish" to make the project live 3. After publishing, domains become active 4. The preview URL is always available at the project's lovable.dev URL ``` ## Labs (Experimental Features) ``` 1. Go to Settings > Labs URL: lovable.dev/projects/<id>/settings/labs 2. Available experiments: - Git branch switching: Toggle to select which branch to edit in your Git repo 3. Toggle experiments on/off as needed ``` ## Browser Automation Tips ### Settings Navigation All settings pages are accessible via direct URL: - Project: /settings/project - Domains: /settings/domains - Knowledge: /settings/knowledge - Connectors: /settings/integrations - Labs: /settings/labs - Cloud & AI: /settings/usage ### Text Areas Knowledge text areas are standard textareas — use form_input or click + type. ### Project Name Edit The pencil icon next to the project name toggles an inline editor. Click it, then the name becomes an editable field. ## Running on Mac Minis These instructions can also be executed on the Mac Minis (bots, vault, jarvis) using the mac-control MCP server instead of chrome-in-chrome. ### Via mac-control MCP Server (Port 8200) The mac-control server on each Mac exposes the same GUI automation primitives: ```bash # Take a screenshot to see the screen curl -s http://bots.local:8200/tools/screenshot # Open a URL in Chrome curl -s http://bots.local:8200/tools/open_url -d '{"url": "https://lovable.dev/dashboard"}' # Click at screen coordinates curl -s http://bots.local:8200/tools/click -d '{"x": 500, "y": 300}' # Type text curl -s http://bots.local:8200/tools/type_text -d '{"text": "Build a landing page..."}' # Press keyboard shortcut curl -s http://bots.local:8200/tools/key_press -d '{"keys": "return"}' # Run AppleScript curl -s http://bots.local:8200/tools/applescript -d '{"script": "tell app \\"Google Chrome\\" to activate"}' # Find text on screen (OCR) curl -s http://bots.local:8200/tools/find_on_screen -d '{"text": "Submit"}' ``` ### Via Chrome DevTools Protocol (Port 9222) For direct browser control without GUI coordinates: ```bash # List open tabs curl -s http://bots.local:9222/json # Navigate a tab to a URL curl -s http://bots.local:9222/json/new?https://lovable.dev/dashboard # Execute JavaScript in a tab (via WebSocket — use a CDP client) ``` ### Via SSH + cliclick (Simple Fallback) ```bash # Open URL ssh bots 'open https://lovable.dev/dashboard' # Wait for page load sleep 3 # Screenshot + analyze ssh bots 'screencapture /tmp/screen.png' scp bots:/tmp/screen.png ./screen.png # Click at coordinates ssh bots '/opt/homebrew/bin/cliclick c:500,300' # Type text ssh bots '/opt/homebrew/bin/cliclick t:"Build a landing page..."' # Submit ssh bots '/opt/homebrew/bin/cliclick kp:return' ``` ### Recommended Machine Use **bots** (192.168.86.50) for browser automation — it has full GUI support, screencapture works, and Chrome with remote debugging is running.