I’ve been trying Maccy, a lightweight macOS clipboard manager, and it’s been a great workflow boost. It makes it easy to find and reuse recent copies to my clipboard, which cuts down on searching when I’m building or debugging with AI. If you juggle lots of snippets, links, or commands, a simple clipboard history can save a lot of time. Curious what tools others here use for this kind of thing!

DeepSeek: DeepSeek V4 Flash 0731 just landed - the most significant new AI release of the last few days. It is live on OpenRouter now with a 1,048,576-token context window. Hacker News is already on it: "DeepSeek V4 Flash 0731 Intelligence, Performance and Price Analysis". https://openrouter.ai/deepseek/deepseek-v4-flash-0731

Qwen: Qwen3.7 Flash just landed - the most significant new AI release of the last few days. It is live on OpenRouter now with a 1,000,000-token context window. https://openrouter.ai/qwen/qwen3.7-flash

What started as an experiment has become a very useful little infrastructure. In continuously expanding out my AI-native system, over time I found myself trusting it for more and more different tasks. I had been using it completely headless, but I started to feel that having a small screen would really enhance it's ability to stay in the loop with me, and would also serve as a clear starting point for an Agent OS that controls the entire machine this level, which has been going very well so far (will have updates on that soon). There's so many things I could get into about controlling this from your phone through Termius, and the benefits of being able to throw over tasks to it. Just the ability to use it as a machine that's always on, and invoke Claude Code via terminal on it for cron jobs has been a great convenience. So in total, so far it's earned itself a face. Let's see if it earns itself a voice too.

I've been polishing UI for a client app using a browser feedback loop with Claude Code. The agent takes a screenshot, evaluates it against a style reference, makes changes, screenshots again. No manual review cycles between iterations. The thing that made this work was keeping the frontend as a thin layer with no API routes, so agents can iterate on design without regressing functionality. Anyone else running visual feedback loops with agents?