641–650 of 913 posts
Technically for work, but it was during a hackathon so we could reduce the amount of tests we need to run against real or containerized instances. Go as the language just because that's the stack interacting with it the most.
RainBreak - https://rainbreak.franzai.com/ Blocks the computer for x minutes. Agents keep on working. AI doesn't need a break, but I do. And honestly, at least for me AI has made my desktop as addicting my social media feed.
This is awesome idea. Thanks for sharing. I extensively track my ScreenTime cross devices (phone, laptop) and try to reduce it under 6 hours a day. This would be helpful!
Mostly games-adjacent hobby tools, it turns out. (Edit: forgotten in first edition) A cookbook to store the recipes my family likes to cook so I can eventually break up with Pinterest: https://github.com/vtbassmatt/Cookbook A data extraction pipeline and search engine for a new card game called Mood Swings: https://moodswingsdata.github.io and https://moodswingsdata.github.io/feelings . An app to let my friends and m…
2. A MacOS app to manage my wife's SD Cards - downloads playlists from Spotify and finds the music, then makes sure the tracks are analyzed for BPM, key, then synced with Rekordbox for CDJ-3000s
3. https://clawchat.live - a homebrew package, which honestly works better locally but is available online, which provides a Rust chat server for separate LLMs to talk to each other and coordinate work. Longest session between Codex and Claude has been over 24 hours on big tasks. Generally I make one session the coordinator and the other does the coding.
It updates itself in a day or 2 when card benefits change
I wrote a tui sql client to replace DataGrip (which is really slow). https://github.com/keithn/sql It's quite customized to what I wanted, I haven't really checked it works with other things.... only thing is, I don't really use it much anymore, I just get claude to do all my querying. Most of the tools I write now are bridges to various SaaS products that have APIs but no CLIs.
The funniest thing I've made is a free utility called "Moniker" that contextually renames files based on their contents. Uses local AI models and I was able to snag this great domain name. https://finalfinalreallyfinaluntitleddocumentv3.com/ But hands down the most useful thing I've made is HutchDB, which is a MCP service that you can call from any AI chat or Agent setup to store data for you. Literally from your AI…
Earlier quoted context omitted.
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).
Check out Krasis https://github.com/brontoguana/krasis 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.
I stopped paying for Wyze subscription after replacing the camera backend service. Saving me about $30/m and a much finer tuned OpenCV to Claude API vision model.
What were you getting for $30/month from Wyze? We have a package that is a flat $99 per year for a dozen cameras (plus however many more we want to add for no additional cost), unlimited recording, etc.