Installation

Prerequisites

Before installing HAI Build, ensure you have:

Visual Studio Code

Download and install VS Code version 1.84.0 or higher

API Keys (Optional)

Obtain API keys for your preferred LLM provider:

Anthropic (Claude)
OpenAI
Google AI Studio (Gemini)
OpenRouter (Multiple providers)

Git (Recommended)

Install Git for version control integration features

You can start using HAI Build without API keys by configuring them later. The extension will prompt you when needed.

Install from VS Code Marketplace

The easiest way to install HAI Build is directly from the VS Code Extensions marketplace:

Open VS Code Extensions

Press Ctrl+Shift+X (Windows/Linux) or Cmd+Shift+X (macOS) to open the Extensions view

Search for HAI Build

Type “HAI Build” in the search bar

Install the Extension

Click the Install button next to “HAI Build Code Generator” by Presidio

Verify Installation

Look for the HAI icon in the VS Code activity bar (left sidebar)

Alternative Installation Methods

Install via Command Palette

# 1. Open Command Palette
Ctrl+Shift+P (Windows/Linux)
Cmd+Shift+P (macOS)

# 2. Type: Extensions: Install Extensions
# 3. Search for "HAI Build"
# 4. Click Install

Install from VSIX File

For offline installation or testing pre-release versions:

Download VSIX

Download the .vsix file from GitHub Releases

Install from VSIX

Open Command Palette and run: Extensions: Install from VSIX...

Select File

Browse to your downloaded .vsix file and select it

Reload VS Code

Reload VS Code when prompted to activate the extension

When installing from VSIX files, you won’t receive automatic updates. Check GitHub releases manually for new versions.

Post-Installation Setup

After installing HAI Build, complete these configuration steps:

1. Open HAI Build Interface

Click the HAI icon in the activity bar or press Ctrl+' (Windows/Linux) or Cmd+' (macOS)

2. Configure Your LLM Provider

Open Settings

Click the settings gear icon in the HAI sidebar or use the Settings button

Select Provider

Choose your preferred LLM provider from the dropdown:

Anthropic (Claude Sonnet, Opus, Haiku)
OpenAI (GPT-4, GPT-3.5)
Google (Gemini Pro, Ultra)
OpenRouter (Access to multiple providers)
Ollama (Local models)
AWS Bedrock, Azure, Vertex AI

Enter API Key

Paste your API key in the configuration field

Select Model

Choose the specific model you want to use (e.g., claude-sonnet-4.5)

Start with Claude Sonnet 3.5 or GPT-4 for the best balance of capability and cost. You can switch models anytime.

3. Configure Optional Features

Telemetry Settings

For teams wanting to track AI usage and metrics:

# Langfuse Configuration
langfuse.apiUrl=https://your-langfuse-instance.com
langfuse.apiKey=your-api-key
langfuse.publicKey=your-public-key

# PostHog Configuration
posthog.url=https://app.posthog.com
posthog.apiKey=your-posthog-key

Place this .hai.config file at your workspace root.

The .hai.config file is not git-excluded by default. Avoid committing sensitive API keys to version control.

MCP Servers

Extend HAI with Model Context Protocol servers:

Click MCP Icon

Click the server icon in the HAI sidebar navigation

Browse Marketplace

Explore available MCP servers for databases, APIs, and tools

Install Servers

Click install on servers you want to use with HAI

Configure

Provide any required configuration (connection strings, API keys, etc.)

4. Complete the Walkthrough

HAI Build includes an interactive walkthrough to help you learn key features:

# Open Command Palette (Ctrl+Shift+P / Cmd+Shift+P)
# Type: HAI: Open Walkthrough
# Follow the 5-step guided tour

The walkthrough covers:

Goal-oriented prompting - How to communicate effectively with HAI
Codebase learning - Letting HAI understand your project structure
Model selection - Choosing the right AI models for your needs
MCP tools - Extending capabilities with external integrations
Control & approval - Reviewing and managing AI-generated changes

Verify Your Installation

Confirm everything is working correctly:

Open a Project

Open a workspace or folder in VS Code

Start a New Task

Click the + (New Task) button in the HAI sidebar

Test Simple Query

Ask HAI a simple question about your code: “Explain the structure of this project”

Review Response

Verify that HAI analyzes your codebase and provides a thoughtful response

If HAI doesn’t respond, check that:

Your API key is correctly configured
You have internet connectivity
Your selected model is available (check provider status pages)

Keyboard Shortcuts Reference

Memoize these shortcuts for efficient workflow:

# Focus HAI chat input
Ctrl+'

# Add selected code to HAI
Ctrl+' (with text selected)

# Open Extensions
Ctrl+Shift+X

# Open Command Palette
Ctrl+Shift+P

# Focus HAI chat input
Cmd+'

# Add selected code to HAI
Cmd+' (with text selected)

# Open Extensions
Cmd+Shift+X

# Open Command Palette
Cmd+Shift+P

Troubleshooting

Extension Not Appearing

Reload VS Code

Press Ctrl+Shift+P / Cmd+Shift+P and run: Developer: Reload Window

Check Installation

Go to Extensions view and verify HAI Build is installed and enabled

Check VS Code Version

Ensure you’re running VS Code 1.84.0 or higher

API Key Issues

Verify Key Format

Ensure your API key has no extra spaces or line breaks

Check Provider Status

Visit your LLM provider’s status page to verify service availability

Test Key

Use the provider’s playground or API to verify the key works

Review Quotas

Check that you haven’t exceeded API rate limits or quotas

Performance Issues on Linux

Linux users may need additional system libraries:

sudo apt update
sudo apt install -y \
  dbus \
  libasound2 \
  libatk-bridge2.0-0 \
  libatk1.0-0 \
  libdrm2 \
  libgbm1 \
  libgtk-3-0 \
  libnss3 \
  libx11-xcb1 \
  libxcomposite1 \
  libxdamage1 \
  libxfixes3 \
  libxkbfile1 \
  libxrandr2 \
  xvfb

Next Steps

Now that HAI Build is installed and configured:

Quick Start Guide

Learn how to use HAI Build for your first task

GitHub Repository

Explore source code and contribute

Need Help?

Report an Issue

Found a bug? Let us know on GitHub

Request a Feature

Have an idea? Share it in Discussions

Email Support

Get help from the HAI team

Documentation

Browse comprehensive guides

Get Started

Core Features

Configuration

Usage Guides

Advanced

Prerequisites

Install from VS Code Marketplace

Alternative Installation Methods

Install via Command Palette

Install from VSIX File

Post-Installation Setup

1. Open HAI Build Interface

2. Configure Your LLM Provider

3. Configure Optional Features

Telemetry Settings

MCP Servers

4. Complete the Walkthrough

Verify Your Installation

Keyboard Shortcuts Reference

Troubleshooting

Extension Not Appearing

API Key Issues

Performance Issues on Linux

Next Steps

Quick Start Guide

GitHub Repository

Need Help?

Report an Issue

Request a Feature

Email Support

Documentation

​Prerequisites

​Install from VS Code Marketplace

​Alternative Installation Methods

​Install via Command Palette

​Install from VSIX File

​Post-Installation Setup

​1. Open HAI Build Interface

​2. Configure Your LLM Provider

​3. Configure Optional Features

​Telemetry Settings

​MCP Servers

​4. Complete the Walkthrough

​Verify Your Installation

​Keyboard Shortcuts Reference

​Troubleshooting

​Extension Not Appearing

​API Key Issues

​Performance Issues on Linux

​Next Steps

Quick Start Guide

GitHub Repository

​Need Help?

Report an Issue

Request a Feature

Email Support

Documentation

Prerequisites

Install from VS Code Marketplace

Alternative Installation Methods

Install via Command Palette

Install from VSIX File

Post-Installation Setup

1. Open HAI Build Interface

2. Configure Your LLM Provider

3. Configure Optional Features

Telemetry Settings

MCP Servers

4. Complete the Walkthrough

Verify Your Installation

Keyboard Shortcuts Reference

Troubleshooting

Extension Not Appearing

API Key Issues

Performance Issues on Linux

Next Steps

Need Help?