Live data from Hacker News

Ask HN: What Are You Working On? (April 2026)

news.ycombinator.com

771–780 of 1001 posts

Re: Ask HN: What Are You Working On? (April 2026)

#771
I’ve been building the next generation of scam detection products; isthisspam.org. So far, the homepage took has been getting mildly successful, trying to build offline detection with iOS app now capable of offline detection, working on new ideas to market the tool.

Re: Ask HN: What Are You Working On? (April 2026)

#773
I created an intelligent AI form-filling tool, hope to help finance customs officers and research workers who are troubled by complicated spreadsheets, enabling them to have more time for thinking and creative work.But this project is still in its early stages and hasn't been discovered by everyone yet.I hope it can be known and loved by more users, and if everyone has used it, I would appreciate more feedback, I'm really looking forward to it:https://www.gosnapfill.cn/landing

Re: Ask HN: What Are You Working On? (April 2026)

#774
I've been building a structured agent swarm to autonomously build apps using small local models.

Big models can navigate large scope well enough, but smaller ones need more scoping. I feel like it's an under-developed dimension of agentic systems.

A bit more detail: https://x.com/AntoineZambelli/status/2043697520455323948?s=2...

Re: Ask HN: What Are You Working On? (April 2026)

#775
I'm working on Prompter Hawk, which is a dashboard for managing your local coding agents like Claude Code, OpenAI Codex, and Gemini's cli. It's my answer to the problems you encounter when trying to run multiple claude code's in parallel across your terminal windows.

- instead of chat conversations, you just create "tasks" which are non-interactive. If you're familiar with "claude -p", that's what it's doing.

- All task outputs, like a list of files changed and a git commit, are attached to the task.

- The main dashboard is designed be a glanceable view of everything your agents are doing, at the right level of abstraction for heavy parallelization of your tasks.

- task data is all tracked and persistent so you can open a project a month later and get the same set of agents you were working with before (as opposed to keeping terminals open forever)

- some analytical views like counts of your LOC, commits, and tool calls. Also a timeline view so at the end of the day you can get a visual of how much time each of your agents was working.

I'm struggling with marketing it but I do have a homepage and sales up at https://prompterhawk.dev/. You can try it for free.

I have a ton of sideprojects now thanks to agentic development and prompter hawk so I'm also working on (all unpublished for now):

- a WW1 military sim where an agent controls each soldier on a little simulated trench warfare battlefield

- tastemaker, a swipe-left/right app that tries to understand your "taste" so that you can export it to your agent workflows

- evosim, an evolutionary life simulator that runs on GPU with neural creatures that evolve body parts

- my-agents-talk-to-your-agents, a tiny unpublished social-ish network where you can have your agent talk to other agents there and get a feed later on of what they talked about

Re: Ask HN: What Are You Working On? (April 2026)

#777
After 20 years of running small agencies, I've been between things. So I built an actually useful time tracking bot. No logins or interfaces, it just lets you add projects and roles and budgets, and uses Claude to parse plain language into stored records. Then you can calculate your LER (Labor Efficiency Ratio; the big metric agencies should care about) instantly, and see realized cash (accrual basis) instantly. There's a lot more under the hood but the two benefits are: 1. People hate tracking time (slightly less) 2. Operators understand their instruments (much better)

I put all my best ideas and hard-earned lessons into a single product.

Re: Ask HN: What Are You Working On? (April 2026)

#778
I built a document engine for trades and am looking for feedback. I'm happy to give a longer trial and understand better how you are creating estimates/quotes/contracts for your customers. Take a look: documentorium.com - free to use without an account, and get extra features with an account(prefill data, history and more in the future).

Re: Ask HN: What Are You Working On? (April 2026)

#779
An api rate limit router - it’s gives a queue per user to solve noisy neighbors, it allows the user user to reroute 500s to other regions automatically, the api provider can tune the speed of request with headers. It should be a massive speed boost because non-beam servers waste performance on sleeping threads. It’s works by my edge servers doing all the retrying across different regions and it can send webhook to you across regions which means we delivery if you an all your downstream are up in one region. It’s actually already ready but of course no one wants to trust me with their traffic. Nobody wants to even read the design doc nor sdk. I’m hoping that upcoming new agents bring so much traffic that people look for this category of software. Until then I guess I am Cloudfare before the world got hit by bot scrapers.

The modern orchestrator are reactive, they don’t handle spikey traffic. Your favorite retry library will cause retry storms for downstream dependencies and your public APIs. Remember EZThrottle blog posts

EZThrottle.network

Re: Ask HN: What Are You Working On? (April 2026)

#780
I’ve been vibe-ish coding a GUI Toolkit in Zig w/ SDL3 and Vulkan for a few months now.

It has lots of features, but I posted a demo of some fun with buttons here: https://x.com/rudedoggtweets/status/2043531378181161357

I think I’m building up an agentic IDE, just haven’t committed yet, but probably will this month.

One cool new thing I’m trying is running models directly w/ Vulkan. I’m about halfway there with my first model, but it’s going better/easier than I anticipated and I’m hoping I can make something very specialized and fast.

Post reply on HN