docs: add documentation for new providers and update baseUrl references

README.md

@@ -83,8 +83,8 @@ export default {
   profile: false,
   tokenCache: true,
 
-  // Ollama configuration (if using local models)
-  ollamaBaseUrl: 'http://localhost:11434',
+  // Base URL configuration (for providers that need it)
+  baseUrl: 'http://localhost:11434', // Example for Ollama
 };
 ```
 

packages/docs/docs/providers/index.mdx

@@ -13,6 +13,8 @@ MyCoder currently supports the following LLM providers:
 - [**Anthropic**](./anthropic.md) - Claude models from Anthropic
 - [**OpenAI**](./openai.md) - GPT models from OpenAI
 - [**Ollama**](./ollama.md) - Self-hosted open-source models via Ollama
+- [**Local OpenAI Compatible**](./local-openai.md) - GPUStack and other OpenAI-compatible servers
+- [**xAI**](./xai.md) - Grok models from xAI
 
 ## Configuring Providers
 
@@ -52,3 +54,5 @@ For detailed instructions on setting up each provider, see the provider-specific
 - [Anthropic Configuration](./anthropic.md)
 - [OpenAI Configuration](./openai.md)
 - [Ollama Configuration](./ollama.md)
+- [Local OpenAI Compatible Configuration](./local-openai.md)
+- [xAI Configuration](./xai.md)

packages/docs/docs/providers/local-openai.md

@@ -0,0 +1,123 @@
+---
+sidebar_position: 5
+---
+
+# Local OpenAI Compatible Servers
+
+MyCoder supports connecting to local or self-hosted OpenAI-compatible API servers, including solutions like [GPUStack](https://gpustack.ai/), [LM Studio](https://lmstudio.ai/), [Ollama OpenAI compatibility mode](https://github.com/ollama/ollama/blob/main/docs/openai.md), and [LocalAI](https://localai.io/).
+
+## Setup
+
+To use a local OpenAI-compatible server with MyCoder:
+
+1. Install and set up your preferred OpenAI-compatible server
+2. Start the server according to its documentation
+3. Configure MyCoder to connect to your local server
+
+### Configuration
+
+Configure MyCoder to use your local OpenAI-compatible server in your `mycoder.config.js` file:
+
+```javascript
+export default {
+  // Provider selection - use gpustack for any OpenAI-compatible server
+  provider: 'gpustack',
+  model: 'llama3.2', // Use the model name available on your server
+
+  // The base URL for your local server
+  baseUrl: 'http://localhost:80', // Default for GPUStack, adjust as needed
+
+  // Other MyCoder settings
+  maxTokens: 4096,
+  temperature: 0.7,
+  // ...
+};
+```
+
+## GPUStack
+
+[GPUStack](https://gpustack.ai/) is a solution for running AI models on your own hardware. It provides an OpenAI-compatible API server that works seamlessly with MyCoder.
+
+### Setting up GPUStack
+
+1. Install GPUStack following the instructions on their website
+2. Start the GPUStack server
+3. Configure MyCoder to use the `gpustack` provider
+
+```javascript
+export default {
+  provider: 'gpustack',
+  model: 'llama3.2', // Choose a model available on your GPUStack instance
+  baseUrl: 'http://localhost:80', // Default GPUStack URL
+};
+```
+
+## Other OpenAI-Compatible Servers
+
+You can use MyCoder with any OpenAI-compatible server by setting the appropriate `baseUrl`:
+
+### LM Studio
+
+```javascript
+export default {
+  provider: 'gpustack',
+  model: 'llama3', // Use the model name as configured in LM Studio
+  baseUrl: 'http://localhost:1234', // Default LM Studio server URL
+};
+```
+
+### LocalAI
+
+```javascript
+export default {
+  provider: 'gpustack',
+  model: 'gpt-3.5-turbo', // Use the model name as configured in LocalAI
+  baseUrl: 'http://localhost:8080', // Default LocalAI server URL
+};
+```
+
+### Ollama (OpenAI Compatibility Mode)
+
+```javascript
+export default {
+  provider: 'gpustack',
+  model: 'llama3', // Use the model name as configured in Ollama
+  baseUrl: 'http://localhost:11434/v1', // Ollama OpenAI compatibility endpoint
+};
+```
+
+## Hardware Requirements
+
+Running LLMs locally requires significant hardware resources:
+
+- Minimum 16GB RAM (32GB+ recommended)
+- GPU with at least 8GB VRAM for optimal performance
+- SSD storage for model files (models can be 5-20GB each)
+
+## Best Practices
+
+- Ensure your local server and the selected model support tool calling/function calling
+- Use models optimized for coding tasks when available
+- Monitor your system resources when running large models locally
+- Consider using a dedicated machine for hosting your local server
+
+## Troubleshooting
+
+If you encounter issues with local OpenAI-compatible servers:
+
+- Verify the server is running and accessible at the configured base URL
+- Check that the model name exactly matches what's available on your server
+- Ensure the model supports tool/function calling (required for MyCoder)
+- Check server logs for specific error messages
+- Test the server with a simple curl command to verify API compatibility:
+
+```bash
+curl http://localhost:80/v1/chat/completions \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "llama3.2",
+    "messages": [{"role": "user", "content": "Hello!"}]
+  }'
+```
+
+For more information, refer to the documentation for your specific OpenAI-compatible server.

packages/docs/docs/providers/ollama.md

@@ -62,7 +62,7 @@ export default {
   model: 'medragondot/Sky-T1-32B-Preview:latest',
 
   // Optional: Custom base URL (defaults to http://localhost:11434)
-  // ollamaBaseUrl: 'http://localhost:11434',
+  // baseUrl: 'http://localhost:11434',
 
   // Other MyCoder settings
   maxTokens: 4096,

packages/docs/docs/providers/xai.md

@@ -0,0 +1,80 @@
+---
+sidebar_position: 6
+---
+
+# xAI (Grok)
+
+[xAI](https://x.ai/) is the company behind Grok, a powerful large language model designed to be helpful, harmless, and honest. Grok models offer strong reasoning capabilities and support for tool calling.
+
+## Setup
+
+To use Grok models with MyCoder, you need an xAI API key:
+
+1. Create an account at [xAI](https://x.ai/)
+2. Navigate to the API Keys section and create a new API key
+3. Set the API key as an environment variable or in your configuration file
+
+### Environment Variables
+
+You can set the xAI API key as an environment variable:
+
+```bash
+export XAI_API_KEY=your_api_key_here
+```
+
+### Configuration
+
+Configure MyCoder to use xAI's Grok in your `mycoder.config.js` file:
+
+```javascript
+export default {
+  // Provider selection
+  provider: 'xai',
+  model: 'grok-2-latest',
+
+  // Optional: Set API key directly (environment variable is preferred)
+  // xaiApiKey: 'your_api_key_here',
+
+  // Other MyCoder settings
+  maxTokens: 4096,
+  temperature: 0.7,
+  // ...
+};
+```
+
+## Supported Models
+
+xAI offers several Grok models with different capabilities:
+
+- `grok-2-latest` (recommended) - The latest Grok-2 model with strong reasoning and tool-calling capabilities
+- `grok-1` - The original Grok model
+
+## Best Practices
+
+- Grok models excel at coding tasks and technical problem-solving
+- They have strong tool-calling capabilities, making them suitable for MyCoder workflows
+- For complex programming tasks, use Grok-2 models for best results
+- Provide clear, specific instructions for optimal results
+
+## Custom Base URL
+
+If you need to use a different base URL for the xAI API (for example, if you're using a proxy or if xAI changes their API endpoint), you can specify it in your configuration:
+
+```javascript
+export default {
+  provider: 'xai',
+  model: 'grok-2-latest',
+  baseUrl: 'https://api.x.ai/v1', // Default xAI API URL
+};
+```
+
+## Troubleshooting
+
+If you encounter issues with xAI's Grok:
+
+- Verify your API key is correct and has sufficient quota
+- Check that you're using a supported model name
+- For tool-calling issues, ensure your functions are properly formatted
+- Monitor your token usage to avoid unexpected costs
+
+For more information, visit the [xAI Documentation](https://x.ai/docs).