Kilo Integration
Use ANT as the backend for Kilo to get intelligent model routing directly in VS Code.
VS Code Settings
Add the following to your VS Code settings.json to point Kilo at ANT:
{
"kilo.provider": "openai-compatible",
"kilo.apiBaseUrl": "https://antbase.ai/v1",
"kilo.apiKey": "your-ant-api-key",
"kilo.model": "ant:best"
}Alternative: Environment Variables
Kilo also reads from standard OpenAI environment variables. Set these in your shell profile or .env file:
export OPENAI_API_BASE=https://antbase.ai/v1
export OPENAI_API_KEY=your-ant-api-keyRecommended Models
Set the kilo.model value depending on your use case:
ant:bestComplex refactoring, architecture decisions, debugging
ant:autoGeneral coding, adapts to prompt complexity
ant:fastQuick completions, inline suggestions
ant:freeZero-cost for experimentation and learning
How to Verify
After configuring Kilo, verify the connection is working:
- Open the VS Code command palette (
Ctrl+Shift+P/Cmd+Shift+P) and runKilo: Test Connection - Or verify the ANT endpoint from your terminal:
curl -s https://antbase.ai/healthzTroubleshooting
- "Provider not recognized" — Make sure to use
openai-compatibleas the provider type inkilo.provider - "401 Unauthorized" — Check your API key in VS Code settings. Make sure it matches your ANT API key exactly.
- "Slow responses" — Try
ant:fastfor quicker completions and inline suggestions