Continue AI Assistant | VSCode & JetBrains Setup Guide

Continue AI Assistant - IDE Integration Guide

Continue is an open-source AI code assistant that works in VSCode, JetBrains IDEs, and Vim. It provides context-aware code completion, generation, and refactoring.

Overview

Continue focuses on:

• IDE integration - Native experience in your editor
• Universal provider support - Works with any LLM provider
• Context awareness - Understands your open files and project
• Chat + autocomplete - Both features in one extension

Key Features

Feature	Description
Autocomplete	Real-time code suggestions as you type
Chat interface	Ask questions about your code
Cmd+K actions	Quick actions for common tasks
Context awareness	Sees your open files and cursor position
Custom models	Use any OpenAI-compatible endpoint

Installation

VSCode

1. Open Extensions (Cmd/Ctrl+Shift+X)
2. Search “Continue”
3. Click Install

JetBrains

1. Open Settings > Plugins
2. Search “Continue”
3. Install and restart IDE

Vim/Neovim

" Using vim-plug
Plug 'continuedev/continue'

Configuration

Config File (~/.continue/config.json)

{
  "models": [
    {
      "title": "GPT-4o",
      "provider": "openai",
      "model": "gpt-4o",
      "apiKey": "${OPENAI_API_KEY}"
    },
    {
      "title": "Claude",
      "provider": "anthropic",
      "model": "claude-sonnet-4-20250514",
      "apiKey": "${ANTHROPIC_API_KEY}"
    }
  ],
  "customCommands": [
    {
      "name": "test",
      "prompt": "Write unit tests for the selected code"
    }
  ],
  "tabAutocompleteModel": {
    "title": "Autocomplete",
    "provider": "openai",
    "model": "gpt-4o-mini",
    "apiKey": "${OPENAI_API_KEY}"
  }
}

Environment Variables

export OPENAI_API_KEY="sk-..."
export ANTHROPIC_API_KEY="sk-ant-..."
export GEMINI_API_KEY="..."
export GROQ_API_KEY="gsk_..."

Usage

Keyboard Shortcuts

Action	Shortcut
Open chat	Cmd/Ctrl+L
Toggle autocomplete	Opt/Alt+Shift+Space
Quick action	Cmd/Ctrl+K
Accept suggestion	Tab
Dismiss suggestion	Esc

Chat Interface

1. Press Cmd/Ctrl+L to open chat
2. Type your question or request
3. Continue sees your current file and cursor position
4. Press Enter to send

Example queries:

• “Explain this function”
• “How do I improve this code?”
• “Generate tests for this class”
• “What does this regex do?”

Cmd+K Actions

Highlight code and press Cmd/Ctrl+K:

• “Refactor this”
• “Add error handling”
• “Convert to async/await”
• “Document this function”

Autocomplete

• Just start typing
• Continue suggests completions in gray text
• Press Tab to accept
• Press Esc to dismiss

Provider Configuration

OpenAI

{
  "title": "GPT-4o",
  "provider": "openai",
  "model": "gpt-4o",
  "apiKey": "${OPENAI_API_KEY}"
}

Anthropic

{
  "title": "Claude",
  "provider": "anthropic",
  "model": "claude-sonnet-4-20250514",
  "apiKey": "${ANTHROPIC_API_KEY}"
}

Google Gemini

{
  "title": "Gemini",
  "provider": "gemini",
  "model": "gemini-2.5-pro",
  "apiKey": "${GEMINI_API_KEY}"
}

Groq

{
  "title": "Groq",
  "provider": "groq",
  "model": "llama-3.3-70b-versatile",
  "apiKey": "${GROQ_API_KEY}"
}

Local Models (Ollama)

{
  "title": "Local",
  "provider": "ollama",
  "model": "codellama:13b",
  "apiBase": "http://localhost:11434"
}

Custom Endpoint

{
  "title": "Custom",
  "provider": "openai",
  "model": "custom-model",
  "apiBase": "https://api.custom-provider.com/v1",
  "apiKey": "..."
}

Custom Commands

Add custom slash commands:

{
  "customCommands": [
    {
      "name": "explain",
      "description": "Explain the selected code",
      "prompt": "Explain what this code does in simple terms: {{selectedCode}}"
    },
    {
      "name": "test",
      "description": "Generate tests",
      "prompt": "Write comprehensive unit tests for: {{selectedCode}}"
    },
    {
      "name": "fix",
      "description": "Fix code issues",
      "prompt": "Fix any bugs or issues in this code: {{selectedCode}}"
    }
  ]
}

Use with: /explain, /test, /fix

Context Providers

Continue automatically includes context from:

• Current file
• Open files
• Cursor position
• Selected code
• File tree

Add custom context:

{
  "contextProviders": [
    {
      "name": "docs",
      "params": {
        "directory": "docs/"
      }
    }
  ]
}

Autocomplete Settings

{
  "tabAutocompleteModel": {
    "title": "Autocomplete",
    "provider": "openai",
    "model": "gpt-4o-mini",
    "apiKey": "${OPENAI_API_KEY}"
  },
  "tabAutocompleteOptions": {
    "maxSuggestions": 3,
    "debounceDelay": 200,
    "multilineCompletions": "always"
  }
}

Troubleshooting

Suggestions not appearing

• Check autocomplete is enabled in config
• Verify API key is set
• Try pressing Opt/Alt+Shift+Space to toggle

”API error”

• Verify API key is correct
• Check provider status
• Try a different model

Slow responses

• Switch to faster model (Groq or GPT-4o-mini)
• Reduce context window
• Disable autocomplete if not needed

Context not working

• Make sure file is saved
• Check file is in the workspace
• Restart Continue extension

Comparison

Feature	Continue	Copilot	Cursor	Cody
Price	Free	$10/mo	$20/mo	$9/mo
Open Source	✅	❌	❌	Partial
Multi-provider	✅	❌	Partial	✅
Autocomplete	✅	✅	✅	✅
Chat	✅	✅	✅	✅
Self-hosted	✅	❌	❌	Partial

Best Practices

1. Set up multiple models - Switch between fast/cheap and powerful models
2. Use specific prompts - Clear instructions get better results
3. Select relevant code - Highlight code for context-aware answers
4. Customize commands - Create shortcuts for common tasks
5. Try local models - Use Ollama for offline/secure coding

Resources

• Official Website
• GitHub Repository
• Documentation
• Discord Community