Skip to main content
Configure Visual Studio Code with AI extensions to use the Comput3 Network API for enhanced coding assistance.

​
Prerequisites

GitHub Copilot

Alternative: Use Comput3 as OpenAI-compatible backend

CodeGPT

Recommended: Native support for custom API endpoints

Continue

Best Choice: Open-source with full Comput3 support

Tabnine

Enterprise: Custom model deployment options
1

Install Continue Extension

  1. Open VSCode Extensions panel (Cmd+Shift+X or Ctrl+Shift+X)
  2. Search for “Continue”
  3. Install the Continue extension by Continue Dev
Continue extension in VSCode marketplace
2

Configure Comput3 API

  1. Open Continue configuration (Cmd+Shift+P → “Continue: Open config.json”)
  2. Replace the configuration with:
config.json
{
  "models": [
    {
      "title": "Comput3 DeepSeek",
      "provider": "openai",
      "model": "hermes4:70b",
      "apiKey": "YOUR_COMPUT3_API_KEY",
      "apiBase": "https://api.comput3.ai/v1"
    },
    {
      "title": "Comput3 Hermes",
      "provider": "openai",
      "model": "hermes4:70b",
      "apiKey": "YOUR_COMPUT3_API_KEY", 
      "apiBase": "https://api.comput3.ai/v1"
    }
  ],
  "tabAutocompleteModel": {
    "title": "Comput3 Autocomplete",
    "provider": "openai",
    "model": "kimi-k2",
    "apiKey": "YOUR_COMPUT3_API_KEY",
    "apiBase": "https://api.comput3.ai/v1"
  },
  "allowAnonymousTelemetry": false
}
Replace YOUR_COMPUT3_API_KEY with your actual API key from the Comput3 dashboard.
3

Test the Setup

  1. Open any code file in VSCode
  2. Highlight some code and press Cmd+Shift+M (or Ctrl+Shift+M)
  3. Ask “Explain this code” or request a code review
You should see responses powered by Comput3’s GPU infrastructure.

​
Setup with CodeGPT Extension

1

Install CodeGPT

  1. Search for “CodeGPT” in VSCode Extensions
  2. Install the CodeGPT extension
  3. Reload VSCode
2

Configure API Settings

  1. Open Settings (Cmd+, or Ctrl+,)
  2. Search for “CodeGPT”
  3. Set the following configurations:
​
API Provider
string
required
Select “OpenAI Compatible”
​
API Base URL
string
required
https://api.comput3.ai/v1
​
API Key
string
required
Your Comput3 API key
​
Model
string
default:"hermes4:70b"
hermes4:70b
hermes4:405b
deepseek-v3.1
kimi-k2
qwen3-coder:480b
qwen3-max
grok-code-fast-1
claude-sonnet-4

​
Environment Variables Setup

For team projects, use environment variables:
Add to your shell profile (~/.bashrc, ~/.zshrc):
export COMPUT3_API_KEY="your_api_key_here"
export OPENAI_API_BASE="https://api.comput3.ai/v1"

​
Features and Usage

​
Code Completion

  • Trigger: Type code and pause for auto-suggestions
  • Accept: Press Tab to accept suggestions
  • Reject: Press Esc or continue typing

​
Code Chat

  • Trigger: Cmd+Shift+P → “CodeGPT: Ask”
  • Usage: Ask questions about your code, request explanations, or get help

​
Code Generation

  • Trigger: Write a comment describing what you want
  • Example: // Create a function to validate email addresses
  • Generate: Press Cmd+Enter or use the command palette

​
Code Review

  • Select: Highlight code you want reviewed
  • Review: Right-click → “CodeGPT: Review Code”
  • Result: Get suggestions for improvements, bugs, and optimizations

​
Troubleshooting

Common Issues:
  • Restart VSCode after configuration changes
  • Check API key is correctly set in settings
  • Verify internet connection and firewall settings
Check the VSCode Developer Console (Help → Toggle Developer Tools) for error messages.
Solutions:
  • Monitor usage in Comput3 dashboard
  • Implement request queuing
  • Consider upgrading your plan
Rate limits reset every minute. Check your current limits at app.comput3.ai.
Checks:
  • Verify model name matches available models
  • Test API key with curl:
curl -H "Authorization: Bearer YOUR_API_KEY" https://api.comput3.ai/v1/models
  • Check Comput3 service status

​
Advanced Configuration

​
Custom Keybindings

Add to your keybindings.json: 
[
  {
    "key": "cmd+shift+a",
    "command": "codegpt.ask",
    "when": "editorTextFocus"
  },
  {
    "key": "cmd+shift+r", 
    "command": "codegpt.review",
    "when": "editorHasSelection"
  }
]

​
Workspace Settings

Create .vscode/settings.json in your project: 
{
  "codegpt.apiKey": "${env:COMPUT3_API_KEY}",
  "codegpt.apiBase": "https://api.comput3.ai/v1",
  "codegpt.model": "hermes4:70b",
  "codegpt.temperature": 0.2,
  "codegpt.maxTokens": 2048
}

​
Benefits

Native Integration

Seamless integration with VSCode’s existing workflow and shortcuts.

Offline Capable

Continue working with cached responses when connectivity is limited.

Team Consistency

Shared configuration ensures consistent AI assistance across your team.

Privacy Control

Your code stays secure within the Comput3 network infrastructure.