Software
GitHub Copilot can now use local Ollama models, but local doesn’t mean offline
Copilot CLI can now discover your Ollama models. That moves inference to your machine, nothing more: telemetry, GitHub contact and…
Coverage
Category: Software
AI and developer software, examined closely: coding agents, local model runtimes, MCP and the other ways AI tools connect to apps, and new browser AI APIs. What each tool actually does, how the options compare and where their limits are, checked against official documentation.
Software
Chrome can run Gemini Nano inside websites: what the Prompt API actually changes
Websites can now prompt a model that Chrome runs on your computer. Who actually gets Gemini Nano, what stays local,…
Software
MCP vs APIs vs computer use: three ways AI agents connect to software
Function calls, MCP servers and computer use sit at different layers. The same booking task through all three paths, and…
Software
Ollama vs LM Studio vs llama.cpp: which one should you actually use for local AI?
LM Studio for a desktop app, Ollama for scripts and a simple local API, llama.cpp for full control. A decision…