> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/lbjlaq/Antigravity-Manager/llms.txt
> Use this file to discover all available pages before exploring further.

# Kilo Code integration

> Connect Kilo Code with Antigravity Manager for multi-account AI coding assistance

## Overview

Kilo Code is an AI coding assistant that can be configured to use Antigravity Manager for multi-account support and automatic quota management.

<Warning>
  Kilo Code requires specific protocol configuration to work correctly with Antigravity Manager. Always use the Gemini protocol, not OpenAI.
</Warning>

## Prerequisites

* Antigravity Manager installed and running
* Kilo Code installed
* Active accounts with Gemini models

## Configuration

<Steps>
  <Step title="Start Antigravity proxy">
    1. Open Antigravity Manager
    2. Go to **API Proxy** tab
    3. Enable the proxy server
    4. Note the port (default: 8045)
  </Step>

  <Step title="Configure Kilo Code">
    In Kilo Code settings:

    1. **Base URL**: `http://127.0.0.1:8045`
    2. **Protocol**: Select **Gemini** (not OpenAI)
    3. **API Key**: `sk-antigravity` (or your configured key)
  </Step>

  <Step title="Test connection">
    Send a test message to verify the integration works correctly.
  </Step>
</Steps>

## Important: Protocol selection

<Warning>
  **Always use Gemini protocol with Kilo Code.**

  Kilo Code has a known issue where OpenAI mode generates invalid request paths:

  * Correct: `/v1/chat/completions`
  * Kilo Code bug: `/v1/chat/completions/responses`

  This causes 404 errors with Antigravity. The Gemini protocol works correctly.
</Warning>

### Why Gemini protocol?

<Tabs>
  <Tab title="Gemini (Recommended)">
    ```
    ✅ Path: /v1/models/gemini-3-flash:generateContent
    ✅ Works: Correct Gemini API path
    ✅ Result: Successful requests
    ```

    Uses correct Gemini API endpoints that Antigravity handles natively.
  </Tab>

  <Tab title="OpenAI (Broken)">
    ```
    ❌ Path: /v1/chat/completions/responses
    ❌ Error: 404 Not Found
    ❌ Reason: Kilo Code appends invalid path suffix
    ```

    Generates malformed URLs that Antigravity cannot route.
  </Tab>
</Tabs>

## Model configuration

### Recommended models

Configure these models in Kilo Code:

<CardGroup cols={2}>
  <Card title="gemini-3-flash" icon="bolt">
    **Use for**: Quick responses, code completion, simple refactoring

    **Quota**: High free tier limits

    **Speed**: Fastest response times
  </Card>

  <Card title="gemini-3-pro-high" icon="brain">
    **Use for**: Complex analysis, architecture discussions, debugging

    **Quota**: Pro tier required

    **Quality**: Best reasoning capability
  </Card>
</CardGroup>

### Model mapping

If Kilo Code's model names don't match Antigravity's defaults:

<Steps>
  <Step title="Check Kilo Code logs">
    Find the exact model name Kilo Code is requesting:

    ```bash theme={null}
    # In Antigravity, enable debug logging
    # Check logs for incoming model names
    ```
  </Step>

  <Step title="Create custom mapping">
    In Antigravity **Model Routing**:

    1. Add new mapping rule
    2. **From**: Kilo Code's model name
    3. **To**: Your Gemini model (e.g., `gemini-3-flash`)
    4. Save configuration
  </Step>

  <Step title="Test mapping">
    Send a request from Kilo Code and verify it routes correctly.
  </Step>
</Steps>

## Configuration examples

### Basic setup

```json theme={null}
{
  "baseURL": "http://127.0.0.1:8045",
  "protocol": "gemini",
  "apiKey": "sk-antigravity",
  "models": [
    "gemini-3-flash",
    "gemini-3-pro-high"
  ]
}
```

### With model mapping

If Kilo Code uses different model names:

```json theme={null}
// Antigravity model routing config
{
  "mappings": [
    {
      "from": "kilo-fast",
      "to": "gemini-3-flash"
    },
    {
      "from": "kilo-pro",
      "to": "gemini-3-pro-high"
    }
  ]
}
```

### Remote server

For remote Antigravity deployments:

```json theme={null}
{
  "baseURL": "http://192.168.1.100:8045",
  "protocol": "gemini",
  "apiKey": "your-api-key"
}
```

<Note>
  Ensure Antigravity has **Allow LAN Access** enabled for remote connections.
</Note>

## Troubleshooting

<AccordionGroup>
  <Accordion title="404 Not Found errors">
    **Problem**: All requests return 404

    **Most likely cause**: Using OpenAI protocol instead of Gemini

    **Solution**:

    1. Open Kilo Code settings
    2. Change protocol to **Gemini**
    3. Save and restart Kilo Code
    4. Test again
  </Accordion>

  <Accordion title="Connection refused">
    **Problem**: `ECONNREFUSED 127.0.0.1:8045`

    **Solutions**:

    1. Verify Antigravity proxy is running
    2. Check port in Antigravity **API Proxy** tab
    3. Test with: `curl http://127.0.0.1:8045/health`
    4. Check firewall settings
  </Accordion>

  <Accordion title="Model not found">
    **Problem**: `Model 'xyz' not found`

    **Solutions**:

    1. Check model name in Kilo Code matches Antigravity
    2. Create custom model mapping in Antigravity
    3. Enable debug logging to see requested model names
    4. Verify accounts support the requested model
  </Accordion>

  <Accordion title="Slow responses">
    **Problem**: Requests take a long time

    **Solutions**:

    1. Check account quotas in Antigravity dashboard
    2. Verify using appropriate model (Flash for speed)
    3. Check network latency to Antigravity server
    4. Review rate limiting settings
  </Accordion>

  <Accordion title="Authentication errors">
    **Problem**: 401 Unauthorized

    **Solutions**:

    1. Check if authentication is enabled in Antigravity
    2. Use correct API key from **API Proxy** settings
    3. Verify API key in Kilo Code configuration
    4. Test with curl to isolate issue
  </Accordion>
</AccordionGroup>

## Debugging guide

### Enable debug logging

1. In Antigravity, go to **Settings**
2. Enable **Debug Logging**
3. Save configuration

### Check logs

<Tabs>
  <Tab title="macOS">
    ```bash theme={null}
    tail -f ~/Library/Logs/com.lbjlaq.antigravity-tools/antigravity.log
    ```
  </Tab>

  <Tab title="Linux">
    ```bash theme={null}
    tail -f ~/.local/share/com.lbjlaq.antigravity-tools/logs/antigravity.log
    ```
  </Tab>

  <Tab title="Windows">
    ```powershell theme={null}
    Get-Content $env:APPDATA\com.lbjlaq.antigravity-tools\logs\antigravity.log -Wait
    ```
  </Tab>
</Tabs>

### Test manually

Verify Antigravity is working correctly:

```bash theme={null}
# Test health endpoint
curl http://127.0.0.1:8045/health

# Test Gemini endpoint
curl -X POST http://127.0.0.1:8045/v1/models/gemini-3-flash:generateContent \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-antigravity" \
  -d '{
    "contents": [{
      "parts": [{"text": "Hello"}],
      "role": "user"
    }]
  }'
```

## Performance optimization

### Model selection

<CardGroup cols={2}>
  <Card title="Code completion" icon="code">
    Use **gemini-3-flash**

    * Fastest responses
    * Sufficient for completions
    * High quota limits
  </Card>

  <Card title="Complex tasks" icon="brain">
    Use **gemini-3-pro-high**

    * Better reasoning
    * For refactoring/architecture
    * Lower quota, use sparingly
  </Card>
</CardGroup>

### Quota management

1. **Monitor usage**: Check Antigravity dashboard regularly
2. **Enable quota protection**: Prevent exhaustion
3. **Add accounts**: More accounts = better distribution
4. **Smart routing**: Let Antigravity balance load automatically

## Best practices

<Steps>
  <Step title="Always use Gemini protocol">
    Avoid OpenAI protocol due to Kilo Code's path bug
  </Step>

  <Step title="Configure model mappings early">
    Set up custom mappings before extensive use
  </Step>

  <Step title="Enable debug logging initially">
    Helps catch configuration issues early
  </Step>

  <Step title="Test with curl first">
    Verify Antigravity works before debugging Kilo Code
  </Step>

  <Step title="Monitor quotas">
    Regular checks prevent unexpected interruptions
  </Step>
</Steps>

## Related documentation

* [Gemini API format](/api/gemini-format)
* [Model routing configuration](/configuration/model-mapping)
* [API Proxy settings](/configuration/proxy-settings)
* [Troubleshooting guide](/troubleshooting/common-issues)