🤖 LMLocal

LMLocal is a Visual Studio extension that integrates with LM Studio to provide a lightweight, local AI chat assistant directly inside your IDE.

---

Important

Preview Notice: This extension is currently in preview. Features, behavior, UI, and documentation are subject to change before the final release.

✨ Features

• ☁️ In-IDE Chat UI – Tool window for LLM interaction without switching applications.
• 🌊 Streaming Responses – Real-time token delivery for low-latency feedback.
• 🧠 Thought/Reasoning Support – Support for reasoning models; "thoughts" are displayed in expandable blocks.
• 📊 Live Stats – Status bar metrics: real-time speed (tokens/sec) and total token count.
• 📝 Markdown & Highlighting – Full GFM rendering with syntax highlighting for code blocks.
• 📋 Quick Copy – Dedicated Copy icon above code blocks for clipboard access.
• 🔍 Active Window Context – + button to include active editor content or Output Pane text in the request.

🛠 Requirements

To use LMLocal, ensure you have:

• Visual Studio 2022 or 2026
• LM Studio installed and running
• Local Server enabled in LM Studio at http://127.0.0.1:1234
• A chat-capable LLM loaded

Tip

Make sure the LM Studio server is listening on port 1234. See the LM Studio Server Documentation for details.

🚀 Installation

Option 1: Visual Studio Marketplace (Recommended)

1. Open Visual Studio.
2. Go to Extensions > Manage Extensions.
3. Search for LMLocal and click Download.
4. Restart Visual Studio to complete the installation.

Option 2: Manual VSIX

1. Download the .vsix file from the Marketplace.
2. Double-click the file and follow the VSIX Installer prompts.

🏁 Getting Started

1. Launch: Open the LMLocal tool window from the Extensions menu.
2. Connect: The extension automatically attempts to connect to http://127.0.0.1:1234.
   • If the connection fails, a ↻ (Refresh) icon will appear in the header for manual retry.
3. Context (Optional): Click the + button to attach text from your active window.
4. Chat: Type your message and click Send or hit Enter ⌨️.
5. Monitor: During generation, check the bottom status bar for live performance metrics (tokens and speed).
6. Control:
   • Use Stop ⏹️ to cancel a generation.
   • Use Clear 🗑️ to wipe the current session history.

🔧 Troubleshooting

Issue	Solution
No model shown	Ensure a model is fully loaded in the LM Studio "AI Chat" or "Server" tab.
Connection Error	Check if the LM Studio Server is ON at http://127.0.0.1:1234. Click ↻ to retry.
UI Lag	Restart the tool window or check your local machine resources (CPU/GPU).

---

📜 License & Third-Party

• License: MIT License. See LICENSE.txt for details.
• Components:
  • marked v18.0.0 (MIT)
  • highlight.js v11.9.0 (MIT) & GitHub Dark theme

🙌 Acknowledgments

Special thanks to the LM Studio team for their local inference platform and the open-source community for the libraries that make this extension possible.