Adnify

🏗 Architecture Design

Core Module Overview

Renderer UI

• React components in src/renderer own panels, editor surfaces, chat, plan views, and user-facing interaction flows.

Agent Runtime

• src/renderer/agent is now a first-class runtime subsystem covering orchestration, planning, context flow, tool invocation, and application-level coordination.

State and Session

• Renderer-side stores and modes manage UI state, conversation state, checkpoints, branches, and session lifecycle.

Frontend Services

• Lightweight client services in the renderer coordinate terminal UX, completions, workspace/session helpers, and requests that cross into Electron APIs.

Renderer Workers

• Browser workers handle compute-heavy renderer work such as text/diff processing, while Monaco language workers keep editor language features off the UI thread.

Preload Bridge

• src/main/preload.ts exposes a typed contextBridge surface so the renderer can access privileged features without direct Node access.

IPC Handlers

• src/main/ipc/*.ts is the contract boundary where renderer requests are validated and routed into main-process capabilities.

Shared Contracts

• src/shared contains cross-process types, config, utilities, and shared error definitions used by both renderer and main code.

Main Process Services

• src/main owns privileged capabilities: window/app lifecycle, filesystem and shell boundaries, LLM backends, MCP backends, LSP management, indexing, and auxiliary desktop services.

Indexing Worker

• src/main/indexing/indexer.worker.ts moves indexing work onto a Node worker thread so parsing, embedding, and vector-store updates do not block the Electron main thread.

Concurrency Advantages

Process Isolation

• The renderer stays focused on UX and orchestration, while the main process contains privileged operations behind explicit IPC boundaries.

Threaded Work

• Heavy background work is split between renderer workers and a dedicated Node indexing worker, so expensive tasks do not stall the app shell.

Operational Safety

• The preload bridge, shared contracts, and main-process security layers keep capability exposure narrow and auditable.

✨ Core Features

🎨 Stunning Visual Experience

• Multi-Theme Support: 4 carefully designed built-in themes

  • Adnify Dark - Default dark theme, soft and eye-friendly
  • Midnight - Deep midnight blue, focused coding
  • Cyberpunk - Neon cyberpunk style
  • Dawn - Bright daytime theme

• Glassmorphism Design: Global frosted glass style with subtle glowing borders and dynamic shadows

• Immersive Layout: Frameless window, Chrome-style tabs, breadcrumb navigation

🤖 Deep AI Agent Integration

• Three Core Working Modes:

  • Chat Mode 💬: Pure conversation mode for quick Q&A and code discussions, direct responses without active tool calls
  • Agent Mode 🤖: Intelligent agent mode with single-thread task focus, full file system read/write and terminal execution permissions, ideal for clear development tasks
  • Plan Mode 🧠: [NEW] Task orchestration mode supporting multi-turn interactive requirement gathering, automatically creates deep step-by-step execution plans, decomposes complex tasks into multiple sub-tasks with parallel/serial execution, supports task dependency management and progress tracking

• 24+ Built-in Native Core Tools: Building a universal foundation allowing AI to fully take over projects

  • 📂 File System Management: read_file (supports single/batch file reading), list_directory (supports recursive traversal)
  • ✍️ Smart Code Editing: edit_file (9-strategy intelligent matching), write_file, create_file_or_folder, delete_file_or_folder
  • 🔎 Full-scale Search Engine: search_files (ultra-fast regex scan, supports | pattern combination), codebase_search (LanceDB vector semantic insight)
  • 🧠 Language Service (LSP): find_references, go_to_definition, get_hover_info, get_document_symbols, get_lint_errors (supports force refresh)
  • 💻 Sandbox Terminal Control: run_command (supports background execution), read_terminal_output, send_terminal_input (supports Ctrl key combinations), stop_terminal
  • 🌐 Knowledge Networking: web_search (multi-strategy fusion), read_url (Jina deep parsing)
  • 🤝 Human-like Interaction: ask_user (supports manual approval and confirmation)
  • ✨ Task Planning System: create_task_plan, update_task_plan, start_task_execution (supports task dependencies and parallel execution)
  • 🎨 UI/UX Design Search: uiux_search (global design aesthetics knowledge base and industry best practices)
  • 💾 Project Memory Management: read_memory, write_memory (supports manual approval mechanism)

• Smart Context References:

  • @filename - Reference file context with fuzzy matching support
  • @codebase - Semantic codebase search based on AI Embedding
  • @git - Reference Git changes, auto-fetch diff info
  • @terminal - Reference terminal output for quick error analysis
  • @symbols - Reference current file symbols, quick navigation to functions/classes
  • @web - Web search for latest technical documentation
  • Drag & drop files/folders to chat for batch context addition

• Seamless Multi-LLM Switching:

  • Supports OpenAI (GPT-4, GPT-4o, o1 series)
  • Anthropic Claude (Claude 3.5 Sonnet, Claude 3.7)
  • Google Gemini (Gemini 2.0, Gemini 1.5 Pro)
  • DeepSeek (DeepSeek-V3, DeepSeek-R1 with thinking process visualization)
  • Ollama (local models)
  • Custom API (OpenAI-compatible format)

• Quick Model Switching: Dropdown selector at bottom of chat panel, grouped by provider, one-click model switching with custom model parameters

• ⚡ Skills System:

  • Plugin-based system based on agentskills.io standard
  • Search and install community skill packages from skills.sh marketplace
  • Direct installation from GitHub repositories
  • Supports project-level and global-level skills, project-level overrides global
  • Supports Auto mode (AI auto-determines loading) and Manual mode (requires @skill-name reference)
  • Skill packages support YAML frontmatter metadata configuration

• 🔌 Deep MCP Protocol Integration:

  • Full implementation of Model Context Protocol standard
  • Supports external tools, resources, and prompt extensions
  • Built-in OAuth 2.0 authentication flow for third-party service authorization
  • Config hot-rel