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 :)
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
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.
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.