Published 2025-10-19.
Last modified 2025-10-21.
Time to read: 2 minutes.
llm collection.
Did you know that all the computers on your LAN can pool their VRAM so your LLM models run across your entire LAN? That means a modest laptop, attached via a solid Wi-Fi connection could employ some extra local horsepower for AI tasks. If this type of topic interests you, please read the entire series.
- Claude Code Is Magnificent But Claude Desktop Is a Hot Mess
- Google Gemini Code Assist
- CodeGPT
- AI Planning vs. Waterfall Project Management
- Renting vs. Purchasing GPUs for LLMs Throughout Canada
- Best Local LLMs For Coding
- Running an LLM on the Windows Ollama app
- Early Draft: Multi-LLM Agent Pipelines
- MiniMax-M2 and Mini-Agent Review
- LLM Societies
CodeGPT features an AI assistant creator (or GPTs), an Agent Marketplace, a Copilot for software engineers, and an API for advanced solutions. The CodeGPT Visual Studio Code extension works with many models from many vendors. Including Claude Sonnet 4.5.
$ code --install-extension DanielSanMedium.dscodegpt
I had to give my GitHub email to Judin Labs to sign up and use the extension.
-
To display the CodeGPT pane, I pressed CTRL+SHIFT+P,
then typed
codegpt. - One of the choices that appeared was View show CodeGPT Chat, which I selected.
- CTRL+ALT+B revealed the alternate sidebar.
- Then I carefully clicked on the CodeGPT heading in the sidebar, and dragged it to the alternate (right) sidebar, where I prefer to chat.
- Clicking on the settings icon displayed the following:
Clicking on the person icon at the top right of the CodeGPT panel displayed this in my web browser:
Ah, yet another money grab. A few days after installation, at 7:30 AM on a Sunday (ET) I saw an alert in Visual Studio saying that the CodeGPT servers were overloaded and that autocomplete might not work. The message urged me to upgrade to Pro; apparently only the free service was affected. That felt bogus, so I deleted the extension instead.
Did you know that all the computers on your LAN can pool their VRAM so your LLM models run across your entire LAN? That means a modest laptop, attached via a solid Wi-Fi connection could employ some extra local horsepower for AI tasks. If this type of topic interests you, please read the entire series.
- Claude Code Is Magnificent But Claude Desktop Is a Hot Mess
- Google Gemini Code Assist
- CodeGPT
- AI Planning vs. Waterfall Project Management
- Renting vs. Purchasing GPUs for LLMs Throughout Canada
- Best Local LLMs For Coding
- Running an LLM on the Windows Ollama app
- Early Draft: Multi-LLM Agent Pipelines
- MiniMax-M2 and Mini-Agent Review
- LLM Societies
