The API key you are mentioning is just ridiculous. Onboarding your company or personal account is a trap. I ended up getting assigned to sales guy just to test their Vertex API because I used a company email.

Of course, we just used OpenRouter for testing and never touched a Gemini model anymore.

Quite happy I moved away from LastPass long time ago. There are many options out there you can use.

Hey, I'm Angel, one of the people behind HolaClaw. We recently had to optimize different prompts for local inference and understanding how much tokens the system and user prompts consume were quite important.

I found several token counters around, but most of them were using estimations. In this tool, all the calculations are real. The website loads the public tokenizer.json files from those models and encode them to count. Everything happens in your browser.

For models / families that don't publish their tokenizer, we had to do an estimation. If you are curious, it worked by compiling the tokenizers library from HuggingFace to Wasm (they already have a demo).

Hope you like it! We plan to add some extra visualizations and stats. Also, feel free to suggest any missing model.

Even though I'm not that familiar with the synth world, I always found it a really interesting field. Websites like this that helps me exploring and learning are amazing :)

There’s a book by Albert Glinsky about Bob Moog called Switched On. If you haven’t read it, I highly recommend it. It’s definitely reverential but does one of the best jobs of explaining the dilemma between innovation and business that I’ve read.

This is why I uninstalled Cursor and moving to the terminal with Claude Code. I felt I had more control to reduce the noise from LLMs. Before, I noticed that some hours were just wasted looking at the model output and iterating.

Not sure if I improved using agents over time, or just having it in a separate window forces you to use them only when you need. Having it in the IDE seems the "natural" way to start something and now you are trapped in a conversation with the LLM.

Now, my setup is:

- VSCode (without copilot) / Helix

- Claude (active coding)

- Rover (background agent coding). Note I'm a Rover developer

And I feel more productive and less exhausted.

Why Helix specifically, besides the fact that it’s cool? I’m looking for a reason to try it, but the value props seem really far down the list of usability issues that are important to me.

Also, Codex Cloud and similar services require you to give fully access to your repository, which might trigger some concerns. If you can run it locally, you still have the control, same development environment, and same permissions.

It doesn’t have access to your repo when the agent is running (unless you give it internet access and credentials). The code is checked out into the sandbox before it’s let loose.

Hey! Angel from Endor / Rover :)

Thanks for your feedback! I faced this in the past. As you mentioned, monorepos are more common these days, but multi-repo is an established approach in many teams. The way I "solved" this situation was to move all the related projects into a single folder with a parent AGENTS.md file (CLAUDE.md, etc.). Then, I run Rover / Claude / Gemini on this folder.

However, this is not ideal. Due to the amount of code, it usually misses many things to do. We are currently exploring specific workflows for these use cases, trying to help agents to prepare a complete plan.

Another similar case we are working on is to support spawning the same task across different repositories. This would help teams to apply refactor or changes in different projects at the same time.

Custom elements are really great for editors and developers. You can provide a rich set of primitives that editors can use to display certain content. In the past, I used MDX [1] extensively so non-technical writers can create a rich UI for a documentation site.

- [1] https://mdxjs.com/

I just wanted to throw some extra :hearts: towards https://mdxjs.com/ it's really the best of both worlds.

May I ask what you are using instead nowadays?

MDX is great and I like to use it.

Hyprland is on my todo list because I think it will the reason why I move to Linux. The level of customization and performance is amazing. You can build the desktop you want.

I’ve been using it for a year and can’t say it does anything I couldn’t do with dwm, xmonad, i3wm over my past 18 years of tiling WM experience.

IMO it's a matter of effort involved. You can get the cool animations in most WMs but for the majority, it's certainly not out of the box.

I like the concept. Many times I look for high quality articles to go deep on some topics. I recommend you the fly.io blog [1], it has really nice articles.

[1] https://fly.io/blog/

Added: https://engineering.fyi/company/fly

Adding to the list!