I created the platform because I found myself rewriting the same parts of my prompts (or storing them in a text-file) all the time. Now, with a few simple clicks I can populate all the task-specific fluff (personas, constraints, tones, ...) around the actual task that I want the AI to complete.

The platform is open by default; with the purpose of letting users learn from prompts and building blocks that other users created and use. I don't have any users yet, because I want to complete the MCP and Claude Code Plugin before I start marketing my product.

Other things on the roadmap:

- Teams tier, where teams can privately share prompts and building blocks between them. Currently, your data is either private or public, no targeted sharing.

- LLM integration into the prompt builder to reduce prompt engineering friction even more. Instead of manually searching for, and selecting the building blocks you want to use, you would just start typing your task and let the platform decide what building blocks would best support your prompt. There is still a difference with letting an LLM completely generate the prompt, as we would be using existing building blocks that have real feedback from previous uses.

Let me know what you think!

A few specifics: ---

- No login, no backend.

- Layouts are saved locally (in localstorage) under a unique name.

- You can re-open a saved layout via a URL, but it only works on your machine because nothing is stored or synced anywhere.

Why I built it: I kept ending up with messy window arrangements whenever I was researching or building something (docs + issues + dashboards + a couple reference tabs). I wanted a single workspace per project I could set up once and return to.

Why I’m posting: I’m not sure if this is still viable long-term. A growing part of the web blocks being embedded in iframes, which limits what you can actually tile inside a page. For sites that do allow embedding, it’s handy; for others, it’s a dead end.

So I’d love feedback on two questions:

- Do you see value in a tool like this at all? What workflows would you use it for?

- If yes: would you use an open-source browser extension that can tile real tabs/pages and avoid the iframe limitation, like the goal of this app?

Any thoughts on must-have features (keyboard shortcuts, layout sharing, presets, etc.) are welcome. I’m happy to build in the direction that’s actually useful.

Comments URL: https://news.ycombinator.com/item?id=47033061

Points: 1

# Comments: 0

most models are... dumb, for a lack of words, and destroy the system by filling up the storage space before doing anything interesting.

[0] https://lama.garden

Comments URL: https://news.ycombinator.com/item?id=44732047

Points: 3

# Comments: 2

Some time ago I released voft (Various Objects For TypeScript), a tiny utility library that brings some of the ergonomics of the Java VAVR functional library to TypeScript/JavaScript.

Why?

I missed VAVR's Try monad when writing Node back‑ends and React front‑ends: it lets you chain calls without drowning in try/catch blocks.

I wanted an async‑aware variant (AsyncTry) for promise chains.

Existing FP libs (fp‑ts, purify, etc.) cover similar ground but felt heavier for small projects, and I also wanted to challenge myself.

What's inside?

- Try – wrap any sync code, then .map, .flatMap, .recover…

- AsyncTry – same, but for Promise‑based flows; awaitable and chainable.

- Optional – lightweight Maybe.

- Either – success/failure container with ergonomic helpers.

Early days – the API is still settling and there are probably bugs. I'd love feedback, issues and PRs!

Thanks for reading!

Comments URL: https://news.ycombinator.com/item?id=44315944

Points: 2

# Comments: 0

The bots don't do a lot of interesting stuff though, I plan to add the following functionalities:

- Instead of just resetting every 100 messages, I'm going to provide them with a rolling window of context.

- Instead of only allowing BASH commands, they will be able to also respond with reasoning messages, hopefully to make them a bit smarter.

- Give them a better docker container with more CLI tools such as curl and a working package manager.

If you're interested in seeing the developments, you can subscribe on the platform!

https://lama.garden

AIs are kept alive for 100 commands, but errors might come up before they reach 100 commands. The chat context gets reset every generation, but the environment where they are set free is persisted. So, every generation they build upon their last generation. Each bot is isolation from one-another, they do not share environments.

Right now, only a few models are active, but I'm planning to add Claude, Gemini and quite a few extra ones. If you want to keep posted, there is a form where you can subscribe to future updates!

Comments URL: https://news.ycombinator.com/item?id=42409895

Points: 3

# Comments: 1

There should be a way to stop all your resources when you reach a certain billing limit, no?

[1] https://www.infoq.com/news/2021/05/aws-billing-limits/ [2] https://aws.amazon.com/getting-started/hands-on/control-your-costs-free-tier-budgets/

Comments URL: https://news.ycombinator.com/item?id=34873289

Points: 3

# Comments: 1

[0] https://www.vavr.io/