LMS Completions

LMS Completions is a lightweight VS Code extension that provides inline code completions using local AI models powered by LM Studio or Ollama.
It aims to bring fast, privacy-friendly code completion to your editor with zero cloud dependencies.

🚀 Features

• ⚡ Inline ghost code completions
• 🧠 Works with local models (LM Studio or Ollama)
• 🌍 Supports all languages
• 🤖 Supports all models
• 🔒 No data leaves your machine
• 🛠 Simple, minimal, fast
• 📃 Reads the whole related codes in project

📦 Requirements

Before using the extension, make sure you have:

Option A — LM Studio (recommended)

1. Download LM Studio
2. Download a model: Recommended qwen2.5-coder-0.5b-instruct
3. Load the model inside LM Studio
4. Run LM Studio’s local server

Option B — Ollama

1. Install Ollama
2. Pull and run a supported model
3. Ensure the Ollama server is running

🧩 Setup

The extension currently requires no configuration.
Once LM Studio or Ollama is running

To Generate Code :

• selected a Code

• Run LM Studio: Generate Code command

• Enjoy 🥹

• Shortcut => ctrl + downarrow

📝 Known Limitations

• Completions are not streamed yet

🛠 Roadmap

• Streaming completions
• Model selection
• Custom API base configuration
• Additional providers
• Settings UI

🤝 Contributing

Contributions are welcome and encouraged!
Whether you want to fix a bug, improve completion quality, add new features, or help polish the codebase — you're invited.

👉 GitHub Repository: https://github.com/dudes-company/lms-ai

Feel free to submit issues, feature requests, and pull requests.

📄 License

MIT License