Binny.AI - VS Code Extension

🤖 Binny.AI is an intelligent AI-powered pair programming assistant for Visual Studio Code that integrates with local Ollama models to provide advanced coding assistance, debugging, and code analysis features.

Features

🚀 AI-Powered Autocomplete

Intelligent code completions powered by local AI models
Context-aware suggestions based on your current code
Configurable delay and token limits
Works with all programming languages

🔍 Code Analysis & Debugging

Explain Code: Get clear explanations of selected code snippets
Debug Code: Identify potential bugs, issues, and vulnerabilities
Improve Code: Receive suggestions for code optimization and best practices
Generate Tests: Automatically create unit tests for your functions

💬 Interactive Chat Interface

Built-in chat panel for conversational AI assistance
Persistent conversation history
Beautiful, VS Code-themed interface
Real-time typing indicators

⚙️ Local AI Integration

Connects to your local Ollama installation
No data sent to external servers - complete privacy
Support for multiple AI models (CodeLlama, Llama2, etc.)
Configurable model selection for different tasks

Prerequisites

Before using Binny.AI, you need to have Ollama installed and running on your system.

Installing Ollama

Download Ollama from https://ollama.ai

Install recommended models:

# For code assistance
ollama pull codellama:7b

# For chat conversations
ollama pull llama2:7b

# Alternative models you can try
ollama pull codellama:13b
ollama pull llama2:13b
ollama pull mistral:7b

Start Ollama (it usually runs automatically after installation)
```
ollama serve
```

Installation

Clone or download this extension
Open the extension folder in VS Code
Install dependencies:
```
npm install
```
Compile the extension:
```
npm run compile
```
Press F5 to run the extension in a new Extension Development Host window

Configuration

Configure Binny.AI through VS Code settings:

{
  "binny-ai.ollamaUrl": "http://localhost:11434",
  "binny-ai.model": "codellama:7b",
  "binny-ai.chatModel": "llama2:7b",
  "binny-ai.enableAutoComplete": true,
  "binny-ai.autoCompleteDelay": 500,
  "binny-ai.maxTokens": 2048
}

Settings Description

ollamaUrl: URL where your Ollama server is running (default: http://localhost:11434)
model: AI model to use for code assistance (default: codellama:7b)
chatModel: AI model to use for chat conversations (default: llama2:7b)
enableAutoComplete: Enable/disable AI-powered autocomplete (default: true)
autoCompleteDelay: Delay in milliseconds before triggering autocomplete (default: 500)
maxTokens: Maximum number of tokens for AI responses (default: 2048)

Usage

Commands

Access Binny.AI features through the Command Palette (Ctrl+Shift+P / Cmd+Shift+P):

Binny.AI: Open Chat - Open the interactive chat panel
Binny.AI: Explain Selected Code - Get an explanation of selected code
Binny.AI: Debug Code Issues - Analyze selected code for bugs and issues
Binny.AI: Suggest Code Improvements - Get suggestions for code optimization
Binny.AI: Generate Unit Tests - Create unit tests for selected code

Right-click on selected code to access Binny.AI features directly from the context menu.

Autocomplete

Simply start typing, and Binny.AI will provide intelligent code completions after the configured delay.

Supported Languages

Binny.AI works with all programming languages supported by VS Code, including:

JavaScript/TypeScript
Python
Java
C/C++
C#
Go
Rust
PHP
Ruby
And many more!

Troubleshooting

Common Issues

1. "Cannot connect to Ollama" error

Ensure Ollama is installed and running
Check that Ollama is accessible at the configured URL
Verify the Ollama service is not blocked by firewall

2. "Model not found" error

Make sure you have pulled the required models using ollama pull <model-name>
Check that the model names in settings match exactly with installed models

3. Slow autocomplete responses

Try using smaller models (7B instead of 13B)
Increase the autoCompleteDelay setting
Reduce the maxTokens setting

4. Extension not activating

Check the VS Code Developer Console for error messages
Ensure all dependencies are installed (npm install)
Try recompiling the extension (npm run compile)

Checking Ollama Status

You can verify Ollama is working by running:

curl http://localhost:11434/api/tags

This should return a list of installed models.

Development

Building from Source

Clone the repository
Install dependencies: npm install
Compile TypeScript: npm run compile
Run in development: Press F5 in VS Code

Project Structure

binny-ai-extension/
├── src/
│   ├── extension.ts          # Main extension entry point
│   ├── ollamaClient.ts       # Ollama API client
│   ├── completionProvider.ts # Autocomplete provider
│   ├── chatProvider.ts       # Chat interface
│   └── codeAnalyzer.ts       # Code analysis features
├── package.json              # Extension manifest
├── tsconfig.json            # TypeScript configuration
└── README.md                # This file

Privacy & Security

100% Local: All AI processing happens on your machine
No Data Collection: No code or personal data is sent to external servers
Open Source: Full source code available for inspection
Secure: Uses local Ollama installation with no external dependencies

Contributing

Contributions are welcome! Please feel free to submit issues, feature requests, or pull requests.

License

This project is licensed under the MIT License.

Acknowledgments

Built with Ollama for local AI model hosting
Powered by CodeLlama and other open-source language models
Inspired by the need for privacy-focused AI coding assistants

Happy Coding with Binny.AI! 🚀

Binny.AI

binny-ai