631–640 of 913 posts
I'm building a source code analyzer with AI. It's a TUI that you poin at a local codebase and it generates Mermaid diagrams. While I was doing it I needed to render those diagrams as ASCII and I was surprised there's no Python library for Mermaid to ASCII. So I wrote one: https://github.com/fasouto/termaid ( https://termaid.com/ )
Built the tool to kind of builds the tools. Just publicly made available yesterday actually. https://github.com/fabritorio/fabritorio I am still extensively dogfooding but I think I'm mostly there for my use case, probably adding some other channel support like Telegram or Discord so that it can reach out your current self host. But yeah not a prio since at least for me most of my use cases are just within my own PC…
After asking agents to make the same types of changes over and over again, I decided to make a tool that would just tell the agent that its code needs improving. I figured that if I could get the agent to self-review and improve the code it writes, that it would save me time when I finally come around to reviewing it.
Tool: https://github.com/thempatel/mdlr Blog: https://www.thempatel.com/2026/06/06/slop.html
2. An app that receives forwarded text messages from my iPhone and then outputs the text message onto a dedicated television connected via a raspberry Pi to display a cold-war era style GUI teletype sort of interface. It actually looks really stinkin cool
Made a multi-player Battlefield game for my scout group: up to 6 players set up ships like in the classic Battefield game. But you can try to hit any of the other up to 5 enemies and each team can see who hit them. And instead of turn-based, you have to hike to/visit a physical location, fill in a code you found there to get bombs for the game. Or do a quiz and get the answers right. Great fun so far!
I had OpenCode with DeepSeek V4 Flash create a quiz about the HN FAQ, so use that to earn bombs :-)
You will need to place some ships (or have them auto-placed) before the game can start.
Built the tool to kind of builds the tools. Just publicly made available yesterday actually. https://github.com/fabritorio/fabritorio I am still extensively dogfooding but I think I'm mostly there for my use case, probably adding some other channel support like Telegram or Discord so that it can reach out your current self host. But yeah not a prio since at least for me most of my use cases are just within my own PC…
This seems really cool actually. Just read thru the README and watched the demo gif. Any examples of what you've built with it so far? Might have to play around with it tonight. I've been getting pretty heavy into local LLMs since getting my 5090. Amazing what Qwen can do given how small it is (running 35B at Q4 quant).
Cool thing is I built the tools with the [Tool Builder](https://github.com/fabritorio/fabritorio/blob/main/docs/node...) as well, pretty small CLI helpers. https://imgur.com/a/XeYYbzC
Most of it has been to maximize productivity with AI 1) Use chatgpt pro from codex cli, opencode, claude etc as you can't get it via API. This has been the biggest boost in productivity for me as I don't have to copy and paste. https://github.com/agentify-sh/desktop 2) A small gate to make sure any agent cannot run destructive rm -rf or git reset --hard commands, it has saved me many many times https://github.com/age…
Collection of JSX scripts for After Effects which automate repetitive production tasks since I often work with hundreds of comps in my projects - https://github.com/nuclearsugar/AfterEffectsScripts/
Built the tool to kind of builds the tools. Just publicly made available yesterday actually. https://github.com/fabritorio/fabritorio I am still extensively dogfooding but I think I'm mostly there for my use case, probably adding some other channel support like Telegram or Discord so that it can reach out your current self host. But yeah not a prio since at least for me most of my use cases are just within my own PC…
This seems really cool actually. Just read thru the README and watched the demo gif. Any examples of what you've built with it so far? Might have to play around with it tonight. I've been getting pretty heavy into local LLMs since getting my 5090. Amazing what Qwen can do given how small it is (running 35B at Q4 quant).
It enables something similar to unified memory. Ive got a 5060 (16GB) card and 96 GB ddr5.
I can run qwen3.5-122b int4 at 25tok/sec.And now even does image ingestion!
Ive been bulk transliterating and translating foreign language books into english. And all completely local.