Installation

Download and install Aethaar DevOp on Windows, macOS, or Linux. Covers system requirements, first-run setup, and automated background updates.

System Requirements

Ensure your system meets the following specifications before installing Aethaar DevOp:

Installing the Client

Follow the installer instructions for your operating system:

• Windows: Download the executable installer (.exe), launch it, and the setup will complete silently. Desktop and start menu shortcuts are generated automatically.
• macOS: Download the universal .dmg disk image, open it, and drag the Aethaar DevOp app into your /Applications directory.
• Linux: Download the AppImage or Debian package (.deb). For AppImage, run chmod +x Aethaar-DevOp.AppImage and execute.

Seamless Background Updates

Aethaar DevOp features built-in background updating. When a new version is released, updates download silently in the background. You will receive a clean prompt to restart and apply updates when ready without interrupting your active coding sessions.

Security & First-Time Launch

Quickstart

Open your first project, prompt the AI assistant, and learn the core interface in under ten minutes.

Opening a Project

Launch Aethaar DevOp and click Open Folder (or press Ctrl + O / Cmd + O). Select the root directory of your project. DevOp instantly detects your framework, dependencies, and begins local semantic indexing in the background.

Making Your First AI Request

Aethaar provides a responsive AI sidebar directly inside the editor:

• Toggle AI Chat (Ctrl + I / Cmd + I): Open the AI Assistant panel. You can ask architectural questions, request code refactors, or ask the AI to implement multi-file features.
• Context Referencing with @: Type @ in the prompt bar to attach specific files, folders, or documentation directly into the model's active reasoning context.
• Autonomous Agent Loops: In Build or Auto mode, the AI can read files, execute terminal commands with your approval, inspect linter results, and edit code across multiple files.

Configuration & Sync

Set your preferred AI model, customize themes and keybindings, and sync preferences securely across devices.

Accessing Settings

Open the Settings dialog via the gear icon in the bottom activity bar or by pressing Ctrl + , / Cmd + ,.

Theme & Appearance

Aethaar DevOp supports high-contrast Dark Mode, clean Light Mode, and Auto (System) theme tracking that responds in real time to your operating system's color scheme.

Migration Guide

Transitioning from VS Code, Cursor, or JetBrains to Aethaar DevOp is immediate and frictionless.

Aethaar DevOp operates directly on your local file system without proprietary workspace schemas, locks, or hidden config wrappers. Simply open your existing repository folder to start coding with full syntax highlighting, terminal support, and AI agent assistance.

AI Chat & Context

Ask questions about your codebase, plan architectures, and execute edits with deep natural language understanding.

Context Referencing (@-mentions)

Reference specific workspace files and assets dynamically in your prompts:

• @filename: Injects the targeted file content directly into the prompt context.
• @folder/: Provides the structural tree and file manifests within a subdirectory.
• @docs: Injects project documentation, READMEs, or external API references.

Codebase Indexing & Semantic Retrieval

How Aethaar DevOp indexes your project for fast, accurate context retrieval without compromising privacy.

DevOp parses your codebase locally using AST analysis and vector embeddings. The index updates incrementally whenever you save a file. When you query the AI, semantic retrieval pulls relevant code snippets into the prompt, ensuring the model understands project-wide relationships without exceeding token limits.

Thinking Trace & Agent Execution

Real-time visibility into the AI's internal reasoning, planning, and autonomous tool execution.

Expandable Thinking Accordion

When using frontier reasoning models (such as GPT-6 Astra, Claude Opus 5, or Gemini 3.1 Pro), the internal chain-of-thought stream is neatly grouped into an interactive Thinking Trace accordion. Animated WebGL Thinking Orbs dynamically reflect what the agent is doing:

Inline Terminal & Tool Controls

When the AI executes shell commands, build scripts, or file edits, output streams directly inside the chat interface. You maintain complete control with one-click approvals, rejections, and direct diff inspections.

Smart Mode (Adaptive Model Routing)

Intelligent routing that automatically selects the most capable and cost-effective AI model for every query.

Routing Strategies

In Smart Mode, DevOp analyzes query intent (e.g. general explanation vs complex algorithm vs direct vision) and routes it to the optimal model:

• Auto Strategy: Balanced intelligent routing between high-speed standard models and frontier reasoning models based on complexity.
• High Strategy: Prioritizes maximum reasoning and flagship models (GPT-6 Astra, Claude Opus 5, Gemini 3.1 Pro) for mission-critical tasks.
• Low Strategy: Prioritizes lightning-fast, cost-effective models (Gemini 3.8 Flash, DeepSeek V4 Flash, GLM 5.3 Flash) for rapid edits.
• Custom Pool: Curate your own candidate model checklist. Smart routing will only pick from your selected pool of models.

Image Mode & Multimodal Vision

Dedicated AI image generation and multimodal vision analysis built directly into your workflow.

Dedicated Image Generation

Switch to Image Mode to generate high-fidelity visual assets, UI mockups, and diagrams:

• Standard Aspect Ratios: Supports square (1:1), landscape (16:9, 4:3), and portrait (9:16) aspect ratios.
• Multi-Image Generation: Request 1 to 4 images in a single prompt with progressive generation and instant download controls.
• Project-Aware UI Generation: When prompting "generate UI for this project", the AI pre-inspects your project’s framework, theme tokens, and existing layouts to ground the generated visual mockups.

Direct-Vision Image Analysis

Drag and drop screenshots, UI designs, error logs, or architectural diagrams directly into the chat prompt. The AI inspects image pixels across Gemini, Claude, Qwen, Kimi, and GPT models to debug visual bugs, explain diagrams, or convert designs into frontend code.

Project Memories & Tech Stack Context

Persistent context intelligence that remembers your project conventions and completed tasks across sessions.

Automated Context Detection

When you open a repository, DevOp reads your workspace manifests (package.json, Cargo.toml, requirements.txt, go.mod) and automatically saves a Project Tech Stack & Context memory card. When you complete major tasks, the AI captures modified files and summaries into its local persistence store.

Managing Memories

Open the Memories Panel in the AI sidebar to search, review, or delete stored project context cards at any time.

Cloud Models & Reasoning Controls

Overview of available Cloud models, interactive preview cards, and fine-grained reasoning effort controls.

Interactive Model Selector

Click the model selector in the chat toolbar to open the combobox. Hovering over any model reveals a live flyout preview card displaying:

• 10-Segment Metric Bars: Visual indicators for Intelligence, Speed, Context Window, and Cost.
• Context Window Specifications: From standard 128K tokens up to 1.3M tokens (Cloudflare GLM 5.3).

Configurable Reasoning & Thinking Effort

Fine-tune how deeply models deliberate before answering:

Cloud Model Lineup Overview

Plan Tiers & Model Access

Understanding model access, token quotas, and tier privileges across Free and Paid plans.

Free Tier Access

Free accounts receive access to over 15 fast, capable Cloud models (including Gemini 3.8 Flash, DeepSeek V4 Pro, Qwen 3.8 Max, Kimi K3, GLM 5.3 Flash, and GPT-5.6 Luna) backed by a 6-day cycle token allowance. Free users also enjoy unlimited Local Model execution and BYOK integrations.

Frontier Paid-Only Models

Expensive frontier reasoning models (such as GPT-6 Astra, Claude Opus 5, Claude Sonnet 5, Claude Fable 5.1, and Gemini 3.1 Pro) are reserved for Starter, Pro, and Ultimate subscribers to ensure guaranteed capacity and uncapped reasoning depth.

Bring Your Own Key (BYOK)

Connect personal API keys for direct model access, zero platform markups, and higher rate limits.

Supported BYOK Providers

You can configure your personal API keys in Settings under the BYOK tab for the following providers:

• Direct Providers: OpenAI Platform, Anthropic Console, Google AI Studio, DeepSeek Platform, Moonshot AI, Alibaba DashScope, and Zhipu AI.
• OpenRouter: Connect a single OpenRouter key to unlock 12 model namespaces (including Meta Llama 3.3, Mistral, MiniMax M3, and custom models).

BYOK Reasoning Controls

When using BYOK mode, all fine-grained reasoning effort controls (including OpenAI X-High and Claude Max thinking) remain fully active and configurable in the chat toolbar.

Local Models & Marketplace

Run open-weight models locally on your own GPU/CPU for 100% offline privacy and zero token costs.

In-App Hugging Face Marketplace

DevOp features an integrated Model Marketplace panel. You can search over 30+ popular open-weight models directly from Hugging Face, inspect parameter counts and quantization sizes, and download them with one click.

1-Click Recommended Models

• Llama 3.3 (8B / 70B): Meta's flagship general-purpose open-weight model.
• DeepSeek Coder & R1 Distill: Specialized models for code completion and mathematical reasoning.
• Phi-3 / Gemma 2 / Mistral: Lightweight, highly efficient models for laptops and resource-constrained environments.

Ollama & GGUF Local Inference

Aethaar DevOp integrates with local inference backends like Ollama and llama.cpp. Select Local Model in the model source selector, set your local endpoint (e.g. http://localhost:11434), and prompt the model offline with zero telemetry.

Cloud Provider Integrations

Connect your cloud services so AI agents can inspect schemas, verify deployments, and assist with infrastructure tasks.

Connecting Your Accounts

Navigate to the Apps & Integrations tab in your Aethaar dashboard to connect your developer accounts using direct Personal Access Tokens (PAT) or OAuth:

AI Agent Tool Access

When integrations are connected to your workspace, the AI agent can safely check connection states, query table schemas, and fetch resources during active tasks with explicit user visibility.

Agent Skills & Effort Meter

Extend the AI agent’s capabilities with specialized skill libraries, developer telemetry, and the open Model Context Protocol.

Effort Meter & Optimization

DevOp includes the built-in Effort Meter system and intelligent agent skills to streamline development and audit code efficiency:

• Effort Meter Analytics: Real-time tracking of engineering velocity, model token utilization, and task complexity metrics.
• Codebase Audit: Scans your workspace for unnecessary dependencies, duplicate utilities, and over-engineered abstractions.
• Debt Ledger: Automatically flags and catalogs technical debt markers and deferred tasks for future refactoring.
• Minimalist Code Review: Evaluates code diffs focusing on simplicity, performance, and standard library alternatives.

Model Context Protocol (MCP)

Aethaar DevOp supports MCP servers. You can connect standard MCP tools (such as database inspectors, local dev tools, and external APIs) directly to the AI assistant, allowing it to call custom tools securely during chat sessions.

Internal Browser Preview & DevTools

Test and preview your web applications directly inside Aethaar DevOp without leaving the editor.

Automatic Port Detection

When you start a development server (e.g. npm run dev, vite, next dev) in the embedded terminal, DevOp automatically detects the active localhost port (e.g. http://localhost:3000 or http://localhost:5173) and updates the internal browser preview.

Built-in DevTools

The internal browser includes an integrated webview inspector with Console, Elements, Network, and Source tabs for fast debugging.

Default Shortcuts

Comprehensive keybinding reference for Windows, macOS, and Linux.