Ask HN: What are you working on? (August 2026)

This month marks 1 year since I first started self-research and building my own coding agent VT Code [0]. I've been learning and experiment with a lot of things to first adapt myself and to learn about AI native/harness engineering. Thankfully, last month VT Code receives highest amount of contributions from the open-source community.

This month I will be focusing and enhance more long-running horizontal for VT Code such as plan mode, better strengthen tools policy structure and improve its harness as new and existing model grows exponentially. And If you are curious and want to fork it feel free, and welcome, let's build!

[0] https://github.com/vinhnx/VTCode

I am currently working on Clippy Vision, which is a fully local screen watcher that watches your screen continuously and builds context over time so you don't have to re-explain context like you do have to in case of Claude or ChatGPT.

Currently, its reactive, i.e a simple ReAct loop which calls function to retrieve data from memory and answers question when asked. Everything runs locally (Ollama + a local vision model, SQLite for storage), nothing leaves the machine.

Right now,I am planning to add a skill layer on top of the base watcher. So instead of it just being reactive, it acts proactively, for eg: spotting some mistakes in my code that I may have missed, or when you see X do Y types, and so on.

I am actively building this project. Version 1 is out already. source code: https://github.com/protocorn/clippy-vision

Hunting for jobs and it seems like a project of its own, given the current state of software job markets.

Currently working on Rusaka Technologies and building and planning to launch sharekeyx - our AI based market prediction platform for retail clients.

Please check it out and share your crtique - https://sharekeyx.com/

KM looks interesting. I just had this idea that some day people will be using some type of unified front end, which has input connections that change depending on what plugged into it prompting for input.

https://news.ycombinator.com/item?id=49151189

With regards to KM, I wonder if you could collect information in realtime upon entry into those sites rather than taking archives of prior activity. I suppose it'd add too much complexity without any promise of meaningful return... yet.

At some point it could allow input into new alternative services instead of the standard ones - it could look something like https://pico.sh/.