941–950 of 1001 posts
It's a deterministic judgement engine for disagreeing inputs. The input interface is shaped for LLMs now, but there's no particular reason it has to stay limited that way & it has a normal API.
I pulled in a lot of research on conflict logics to build it out.
The next big push technically will be an ingest pipeline and a more sophisticated logic engine.
https://shopspec.io/ ShopSpec is a deterministic parametric furniture generator (bookshelves, cabinets, shop carts, leg-and-rail frames, multi-carcass composites) that encodes real woodworking intelligence and outputs shop-ready artifacts. Most recently, introduced the concept of value engineering by sweeping across dimensions to batch evaluate candidates that ranks based on sheet purchases. Also have in beta an MCP…
This is amazing, I may use it for a built-in pantry i'm planning to build. In my use case, I end up with one side at an angle, is there a way to support that?
I've been vibe coding a way to stream my music files collection. Right now I have a server in my NAS which serves a website that streams my music, like an Internet radio but on my local network. I've been very happy to rediscover my collection, especially when I wake up and let it put something random. Maybe it could be something that I could use beyond my local network? (for personal use, of course), what I have now…
I'm building https://uscodex.org . In a nutshell, the goal is to collect all US federal law in version control, and cross-link any references between different sections. Currently I have the US Code, CFR, ~30 years of public laws and congressional bills and 25 years of executive orders. Actually using raw git repos as the main data store which has worked out great since the US Code changes very little between new rel…
project is cool, but what you will do with it? Do you have audience, marketing strategy, monetization plans, etc?..
Audience is primarily lawyers and legal researchers in fields that rely heavily on statutory law (tax, bankrupty, immigration, etc). I'm blessed to have a plethora of lawyers in my family/friends, so planning on using them as ~guinea pigs~ beta testers. If you (or anyone else reading this) think this is something you might use, I would love to talk more! seb@uscodex.org
In terms of monetization, I'm not really sure yet. My hosting costs are very cheap at the moment, so I'm not in any rush there, but I'm imagining I'll build in some more premium features like an API (for other legal-techs), change monitoring (for anyone relying on specific statutes in their work) or team research features (shared bookmarks, notes, collections etc). Open to suggestions here too! One very cool thing about my data pipeline is I've essentially built a connected graph of federal law with tens of millions of edges across millions across hundreds of thousands of sections, and I think there will be a lot of powerful applications of that dataset
I mainly built it to explore which areas have model consensus and which have diversity of opinion.
Lately it supports running agents in Podman containers. It's also possible to independently update Agent harness versions without updating the CLI tool.
One of the next items on the roadmap is tidying up the architecture to clearly define what's in the core of that framework and what's plugged into the framework on top of it - kind of a plugin system.
Plugins may bundle settings such as what commands need to be run when building the container images, startup commands that need to run when starting the containers or the definition of information that should be forwarded from the host into agents' containers (environment variables, networking settings, etc.).
So far, I am hoping for (more) external contributions as well as someone who is willing to share ideas or talk about the concepts around that framework. :-)