Hacker News Reader

Confirmed Linux user with the good ol 2000 web style. Great job!

dat999zxon Show HN: Chronocity – Watch your Git repo's history grow into a 3D city

Thanks!

dat999zxon Show HN: The Thousand – 1k founders, 1 question, one book

Nope, stop with the outbid.lol slop.

Go advertise somewhere else, HN is not the place for you.

dat999zxon Show HN: Knowl – agent memory with write-time supersession, 0.90 on MAB

2 sessions meaning 2 processes, the knowl.db file uses WAL + 10s busy_timeout. Along with 'BEGIN IMMEDIATE' to avoid read transactions upgrading mid-write. Writes are queued so transactions don't collide with each other.

About the sync about 2 different sessions or even agents/subagents, Knowl notify to the query card what changed since the last query. Eg: 'KNOWL CHANGED: 3 items since you last looked' so they know to re-read and decide.

dat999zxon Show HN: Knowl – agent memory with write-time supersession, 0.90 on MAB

Hey HN.

Open-source version at: https://github.com/dat999zx/knowl

The number is FactConsolidation single-hop at 262K context on MemoryAgentBench. On multi-hop Knowl scored 0.07 against an all-time ceiling of 0.14.

Write-up of the approaches that failed first: https://blog.knowl.cloud/the-story-of-knowl

dat999zxon My agent.md to improve LLM-assisted code quality

I think it's a bit too detailed, especially with the linting.

To me when I code by hand, I never use {} after an if statement if it's one-line, it's just faster, look cleaner to me.

dat999zxon Show HN: terminal-code – VS Code inside the terminal

Haha cool idea dude. But why?

dat999zxon Show HN: Knowl – CLAUDE.md hit 1000 lines, so I built memory that prunes itself

Install takes 30 seconds:

npm install -g @dat999zx/knowl

knowl init

That's it, fully working now.

Also all your atoms are stored inside of knowl.db file which is at root of your project after initializing. You can use knowl view command to watch the atoms and how they interact with each other.

dat999zxon There's no reason for software to be slow anymore

Most of the time, it's the network related stuff, requests that are slow. But with AI, devs nowadays are chasing the aesthetic vibe, cool animations, forward-backward video on the background relative to the scrolls... Which worsen the performance drastically just for a cool landing page. I mean that could be cool for landing page only but some people put all those animations in the product itself too, which is a pain to use.