Complete & Visual

Main chat interface with real-time streaming, thinking indicators, command execution, and scheduling.

Utility functions for PDF generation, image handling, command formatting, and secure storage.

AI instructions, commands, capabilities, language maps, and system prompts.

Modal for scheduling AI tasks with cron builder, model selection, and notification options.

Interactive wizard for configuring AI providers and API keys with validation.

Natural language scheduling detection with cron expression extraction.

Secure DOM reading with XSS prevention and structured data extraction.

Visual DOM search results with element highlighting and metadata.

Queue management for AI commands with priority and retry logic.

Robust JSON/shell output parsing with regex fallbacks for AI responses.

Permission dialog for click actions with risk assessment.

Expandable OCR results display with raw text view and confidence scores.

Floating AI assistant overlay for contextual help.

Interactive flowchart rendering with zoom, pan, and node editing.

Animated thinking state display with chain-of-thought visualization.

Chart rendering component supporting bar, line, pie, and scatter charts.

Mermaid diagram renderer with live preview and error handling.

Sidebar panel for browsing past conversations with search.

Animated thinking indicator for loading states.

Action buttons for messages (copy, edit, delete, share).

TypeScript types for AI chat sidebar components.

Helper utilities for AI chat sidebar.

AI command output rendering and formatting.

Main settings container with all configuration sections and theme support.

AI model provider configuration (Gemini, Claude, GPT, Ollama, Groq).

Automation & scheduling settings with task management and permissions.

WiFi/P2P sync configuration for mobile pairing with QR codes.

Auto-update configuration and version info with changelog.

Command permission management by risk level (LOW/MEDIUM/HIGH/CRITICAL).

Plugin management UI with install/enable/disable from marketplace.

Model Context Protocol settings for external tools and services.

Advanced proxy & firewall rules management with presets.

Visual theme configuration with custom gradients and presets.

Browser extension settings with enable/disable toggles.

First-run setup wizard with feature tour and preferences.

API key configuration UI with secure storage indicators.

Performance tuning options (GPU, memory, caching).

Form autofill configuration with secure storage.

Proxy server configuration with auth support.

Default search engine configuration with custom engines.

Custom user agent strings for browser fingerprinting.

Keyboard shortcut customization with presets.

Backend service configuration for P2P sync.

WebView container management with secure context and sandboxing.

Custom window title bar with traffic lights and window controls.

Tab lifecycle management with create, close, restore.

High-performance virtualized tab bar for 100+ tabs.

Spotlight-style universal search overlay with fuzzy matching.

Quick navigation with keyboard shortcuts and recent items.

Visual tab switcher (Cmd+Shift+]) with thumbnails.

Clipboard history with sync support and search.

Browsing history view with search and filtering.

First-time user welcome with feature tour and setup.

Universal search across all content types (web, history, bookmarks).

Authentication login dialog with secure credential storage.

Cross-platform automation abstraction with native OS support.

macOS: steve CLI (accessibility) + AppleScript fallback.

Windows: nut.js/xa11y + PowerShell fallback.

Linux: xdotool + xte/xinput fallback.

Fallback chain: nut.js → xa11y → robotjs.

RobotJS conditional loader for legacy support.

Cross-platform automation engine for mouse/keyboard control.

OCR: uniOCR > RustO! > Native > Tesseract fallback chain.

Screen capture and vision analysis service.

Native OS capability verification for automation.

Records user workflows for automation replay.

Cross-application OCR & click for external apps.

Phone camera integration for document capture.

Permission dialog for click actions.

Quick settings dropdown menu.

PDF creation interface with template selection and preview.

PDF editing workspace with annotation support.

Markdown table parser with overflow handling.

Captures and embeds screenshots into PDFs.

Professional PDF template generation with layouts.

Advanced document generation for PDF, Excel (XLSX), PowerPoint (PPTX), and charts.

Mermaid diagram to PDF/PNG converter with SVG rendering.

Real-time WebSocket sync with QR code pairing over local network.

Peer-to-peer file sync service for large files.

Cloud-based sync service with conflict resolution.

Manages sync methods (WiFi, Cloud, P2P) with fallbacks.

Firebase backend sync for real-time updates.

Contact synchronization across devices.

Peer-to-peer sync manager UI with bandwidth control.

Cloud sync permission dialog.

Orchestrates requests across multiple LLM providers.

Base class for LLM provider implementations.

OpenAI-compatible API provider (Azure, local models).

Ollama local model provider.

Google Gemini API provider.

Anthropic Claude API provider.

Groq fast inference provider.

Base class for all LLM providers.

AI engine with model routing and fallbacks.

AI manager for model selection and configuration.

Registry for available AI models and capabilities.

Reasoning configuration options for AI models.

Offline-capable chatbot with cached responses.

macOS-native visual effect with blur and transparency.

SwiftUI panel for quick settings access.

WKWebView wrapper for Mermaid diagrams.

Native menu bar with settings shortcuts.

Thinking indicator for native macOS sidebar.

Native macOS panel management bridge.

Gmail API integration for email management.

RAG (Retrieval-Augmented Generation) service.

Web search with built-in scraper.

Voice input and TTS integration.

Bridge server for IPC communication.

Model Context Protocol desktop server.

Registry for MCP server connections.

Popular search suggestions service.

Local database management with encryption.

Dynamic skill/command loader for AI.

Shopping cart aggregation service.

Phone call control integration.

OTP generation and verification.

Advanced tab management with optimization.

Tab memory optimization for 50+ tabs.

Device family detection and routing.

Firebase initialization and configuration.

Backend service client.

Third-party service integrations.

File system utility functions.

Dynamic plugin system with lifecycle management (load, unload, enable, disable).

Plugin SDK/framework for building extensions with commands and hooks.

URL scheme handler for comet:// actions.

Browser extension management with hot-reload.

Plugin/extension marketplace UI with categories.

Main Electron process with all IPC handlers, window management, and services.

Context bridge for secure IPC exposure to renderer.

IPC handler registration, system commands, window/clipboard/dialog operations.

Network security configuration, proxy, DNS, ad/tracker blocking.

Window lifecycle, focus management, child windows.

Command validation, shell sanitization, XSS prevention, URL validation.

AI command extraction, JSON parsing, bracket format support.

Security utilities and validation helpers.

Shell command parsing with dangerous command detection.

Store for action logs with search and filtering.

Parse action tags from AI responses for automation.

Browser-specific AI orchestration and state management.

Permission storage with trusted command lists.

Platform detection (macOS, Windows, Linux) for conditional logic.

URL scheme handler for comet-ai:// shortcuts.

Windows Shortcuts, Voice, Copilot integration.

Linux GNOME/KDE desktop integration.

AppleScript voice commands bridge.

macOS Dictation + TTS integration.

Pre-built shortcut templates generator.

macOS-specific integrations and native bridges.

Windows-specific integrations and PowerShell bridges.

Linux-specific integrations and X11 bridges.

Admin control panel for system management.

Development workspace with code editor.

General workspace hub.

Presentation creation studio.

Media management and editing.

Interactive AI feature demonstrations.

Marketing landing page component.

Built-in documentation viewer.

Browser capabilities display.

Offline dinosaur game (Chrome-style).

No-internet game for offline pages.

Content suggestions based on browsing.

Saved passwords manager with secure storage.

Shopping cart aggregator.

Quick navigation overlay.