Hacker News: angelmm

New comment by angelmm in "Gemini 3.7 Flash"

angelmm — Fri, 14 Aug 2026 05:59:55 +0000

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.

Run OpenClaw with Muse Glimmer Locally on Mac

angelmm — Wed, 12 Aug 2026 15:52:11 +0000

Article URL: https://holaclaw.ai/docs/tutorials/use-muse-glimmer-with-openclaw

Comments URL: https://news.ycombinator.com/item?id=49274362

Points: 2

# Comments: 0

Local and GitHub Code Review TUI

angelmm — Fri, 26 Jun 2026 06:30:05 +0000

Article URL: https://tuicr.dev/

Comments URL: https://news.ycombinator.com/item?id=48683061

Points: 3

# Comments: 1

New comment by angelmm in "LastPass notifies users of yet another data breach"

angelmm — Thu, 25 Jun 2026 14:43:19 +0000

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

New comment by angelmm in "Show HN: In-browser real LLM token counter and cost estimation"

angelmm — Thu, 11 Jun 2026 15:43:16 +0000

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.

Show HN: In-browser real LLM token counter and cost estimation

angelmm — Thu, 11 Jun 2026 15:37:32 +0000

Article URL: https://holaclaw.ai/tools/token-studio

Comments URL: https://news.ycombinator.com/item?id=48491836

Points: 3

# Comments: 1

Maintain your E2E test suite with Claude

angelmm — Mon, 23 Mar 2026 12:59:34 +0000

Article URL: https://twitter.com/endorhq/status/2033569460091498613

Comments URL: https://news.ycombinator.com/item?id=47488878

Points: 2

# Comments: 0

New comment by angelmm in "Building a TB-303 from Scratch"

angelmm — Wed, 11 Mar 2026 15:29:27 +0000

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 :)

Open-source voice cloning app using Qwen3-TTS

angelmm — Thu, 19 Feb 2026 12:25:50 +0000

Article URL: https://github.com/jamiepine/voicebox

Comments URL: https://news.ycombinator.com/item?id=47073053

Points: 4

# Comments: 0

Claude prefers JSON over Markdown

angelmm — Thu, 12 Feb 2026 15:45:00 +0000

Article URL: https://capsule.endor.dev?gist=40cb2bb9e073fadd772c92232c6016c8

Comments URL: https://news.ycombinator.com/item?id=46990230

Points: 2

# Comments: 0

Rebuilding our documentation site using AI

angelmm — Fri, 05 Dec 2025 11:01:05 +0000

Article URL: https://endor.dev/blog/rebuilding-our-docs

Comments URL: https://news.ycombinator.com/item?id=46159657

Points: 2

# Comments: 0

A simple open-source OIDC provider that only support passkeys

angelmm — Tue, 28 Oct 2025 09:07:59 +0000

Article URL: https://pocket-id.org/

Comments URL: https://news.ycombinator.com/item?id=45730634

Points: 2

# Comments: 0

New comment by angelmm in "Embracing the parallel coding agent lifestyle"

angelmm — Fri, 10 Oct 2025 08:24:59 +0000

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.

New comment by angelmm in "Embracing the parallel coding agent lifestyle"

angelmm — Fri, 10 Oct 2025 08:17:11 +0000

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.

New comment by angelmm in "Vibe engineering"

angelmm — Wed, 08 Oct 2025 13:47:28 +0000

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.

Rover: Coding Agent Manager

angelmm — Thu, 02 Oct 2025 13:30:09 +0000

Article URL: https://endor.dev/blog/introducing-rover

Comments URL: https://news.ycombinator.com/item?id=45449352

Points: 8

# Comments: 4

SvelteKit Experimental Remote Functions

angelmm — Mon, 11 Aug 2025 20:28:37 +0000

Article URL: https://svelte.dev/docs/kit/remote-functions

Comments URL: https://news.ycombinator.com/item?id=44869085

Points: 4

# Comments: 0

New comment by angelmm in "The Joy of Mixing Custom Elements, Web Components, and Markdown"

angelmm — Mon, 11 Aug 2025 18:01:49 +0000

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/

New comment by angelmm in "Hyprland – An independent, dynamic tiling Wayland compositor"

angelmm — Sun, 10 Aug 2025 14:32:27 +0000

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.

New comment by angelmm in "Show HN: Engineering.fyi – Search across tech engineering blogs in one place"

angelmm — Sun, 10 Aug 2025 14:31:27 +0000

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/