So I guess we (and a lot of other people) have had the same problem, which is managing your agents on the go. I decided to build a plugin[1] for my terminal multiplexer (herdr) to access the sessions via PWA served through a tailnet.
The model is (like Composer 2) based on Kimi K2.5 and they claim SOTA performance for 1/10th of the cost. The tweet also mentions that they've started a new model from scratch on Colossus 2 (xAI/SpaceX Cluster). Really impressive how they've made this jump from being called the vscode fork with no moat just a couple of months ago.
Always thought of this as two cars driving faster than you on the road. After a certain distance it's clear both are faster than you, but really hard to say which one is the fastest.
I see, thanks for explaining and congrats on the launch! After re-reading the description, the ability to use other frameworks might become a USP too.
Just a random remark, what's annoying and a pain point in my workflow are definitely proper development environments for agents . Not just runtimes but also managing secrets etc. Maybe an avenue to explore and use in marketing copy.
I agree with the general sentiment here that this is the future of coding for a lot of tasks. But in terms of a business case for your product I'm really struggling to see how this beats Claude code action? Which integrates directly with GitHub, at no additional cost, and I can use an oauth token to use my subscription.
Haven't used Windsurf yet, but in other tools this is called 'Agent' mode. So you open up the chat modal to talk to an LLM, then select 'Agent' mode and send your prompt.
Cursor recently lost me as a customer. Too many updates that disturb my workflow and productivity, no easy way to roll back versions, super sparse changelogs, lots of magic in context building, really untransparent pricing on max mode. I recently made the switch to Claude Code on the Max plan and I couldn't be happier. The only real thing I'm missing is the diff view across files, but I assume it's just a matter of time until that's properly implemented in Zed or VSCode.
Personally, I've been using Cursor since day 1. Lately with Gemini 2.5 Pro. I've also started experimenting with Zed and local models served via ollama in the last couple of days. Unfortunately, without good results so far.
Really interesting method. I've been calling a similar strategy the library effect. Whenever I work in an environment where other people are productive (or at least look productive) I can focus much better and get in the zone. It's now gotten to a point where I'm actively seeking desks with my screen exposed to the room, so people would be able to see me procrastinate, guilt tripping me to limit this sort of behavior.
I recently tried to implement a workflow automation using similar frameworks that were playwright or puppeteer based. My goal was to log into a bunch of vendor backends and extract values for reporting (no APIs available). What stopped me entirely were websites that implemented an invisible captcha. They can detect a playwright instance by how it interacts with the DOM. Pretty frustrating, but I can totally see this becoming a standard as crawling and scraping is getting out of control.
It depends on what your setup looks like. If your using tailwind and a headless component library like radix or shadcn. LLMs can provide you with pretty decent looking layouts from very simple prompts. If your using plain CSS outputs can vary widely in quality, at least from my own experience.