Hacker News Reader

dh1011on Show HN: Zot – Yet another coding agent harness

I have the same concern. Looks like they do include a disclaimer in the GitHub README, but not on zot.sh.

My problem with Warp is that I have to create an account to use my local llm

dh1011on Website streamed live directly from a model

Very cool idea. Wish it could render faster.

dh1011on I run multiple $10K MRR companies on a $20/month tech stack

> If you have a graphics card sitting somewhere in your house, you already have unlimited AI credits.

I tried running a local LLM, and it’s actually cheaper to use AI credits when you factor in electricity costs. Only use a local LLM if data privacy is your priority.

dh1011on AniSora: Open-source anime video generation model

https://huggingface.co/IndexTeam/Index-anisora

dh1011on Ask HN: What are you working on? (April 2025)

https://github.com/dh1011/c2p

https://marketplace.visualstudio.com/items?itemName=H337.c2p

I’m developing a VS Code and Cursor extension that helps developers quickly copy all code in a workspace to the clipboard for use with LLMs.

It also displays the token count for each file, as well as the total token count across the workspace.

By default, it ignores files listed in .gitignore, but this behavior can be customized in the extension settings, along with many other options.

dh1011on .localhost Domains

Thanks for sharing!

This is cool, but it only seems to work on the host that has the /etc/hosts loopback redirect to *.localhost. I run my app on a home server and access it from multiple PCs on the LAN. I have several apps, each associated with a different port number. Right now, I rely on a start page (https://github.com/dh1011/start-ichi) to keep track of all those ports. I’m wondering if there’s an easy way to resolve custom domains to each of those apps?

dh1011on Ask HN: What are you working on? (March 2025)

I'm working on a VSCode extension that lets me quickly copy code from a workspace into a structured format for LLMs. This makes it easy to provide context so the LLM can continue developing the codebase.

There are other similar tools out there—mostly web apps or CLI-based—but I found a VSCode extension to be the fastest and most convenient option for VSCode users.

Here’s the extension link: https://marketplace.visualstudio.com/items?itemName=H337.c2p

I'd love to get any feedback.

dh1011on Ask HN: Is anyone doing anything cool with tiny language models?

I copied all the text from this post and used an LLM to generate a list of all the ideas. I do the same for other similar HN post .

dh1011on The best browser bookmarking system is files

I completely agree that bookmarks should prioritize content over metadata. This is actually what led me to develop the "semantic-bookmark-manager" [1]. It uses LLM to summarize the content of bookmarked pages and generate relevant tags. Additionally, it utilizes RAG to facilitate semantic searching within your bookmarks.

[1] https://github.com/dh1011/semantic-bookmark-manager

dh1011on Ask HN: What are you working on (September 2024)?

I am working on "Subscription Manager," a simple single-page web application that allows users to manage their recurring payments. It provides a summary of your expenses, including weekly, monthly, and yearly totals for all your current subscriptions. Additionally, it features notifications through NTFY to notify when a subscription is dued for payment.

Here is the Github repo of this project: https://github.com/dh1011/subscription-manager

This is a self-hosted open-source project, licensed under the MIT license.

dh1011on Show HN: LLM-Term – Simple Rust-based CLI assist tool

Thank you. I was using VHS for the demo. Here is the link: https://github.com/charmbracelet/vhs