SEED
You say what it should do.
One call, one scope, one price. You leave knowing what it costs, what it will do, and what it will not do. No discovery phase that bills you for thinking.
You bring the idea. We put roots under it, the parts that still hold when it grows, and we boot it on real hardware until it runs without us. Android apps, GPU kernels, payment rails, shops. Measured, not promised.
You say what it should do.
One call, one scope, one price. You leave knowing what it costs, what it will do, and what it will not do. No discovery phase that bills you for thinking.
We build what holds.
The parts nobody sees and everybody needs: the data model, the money path, the kernel, the tests that fail loudly. Built to survive the second year, not just the demo.
It runs without us.
It goes live on hardware we own, and it is only called done when the check a real user meets has passed. You get the keys, the receipts and the source.
The workbench: experiments written up whether they worked or not, including the ones that were withdrawn. It also runs the open call for testers of the three Android apps.
Trendy Tails by Tomi, a cage-free dog groomer in Schiers. Clients book their own slot, the calendar refuses a double booking, and the confirmation and reminder mails send themselves.
One API call creates a hosted payment page on the merchant's own Stripe account, so the money settles to them and never passes through us. Cards, SEPA, iDEAL and Bancontact, eight languages, with an SDK and an MCP server. Signup is open; live payments wait on Stripe's platform activation.
Low's Bio Farm in Hungary: Artemisia annua and goji grown from certified organic seed, sold as teas, capsules, seed and live plants. Shop, stock and orders in one place.
A single-tenant booking and workshop system for KnullFix in Knüllwald: the public site explains PC, notebook and tablet repairs, gives a written diagnostic estimate before approval, and lets customers track their ticket.
A Romanian shop for teas, room products and natural care, each one chosen with care.
A messenger where friends and AI models share the same chat. Message, call and bring your own model.
Twelve network ideas tied, lost or starved against plain search or their control, with the counts for each. Five had a prereg file. The failures in our measuring that we caught are listed beside them.
BrainNet · part 12On 88 frozen questions the cross-encoder reranker changed three held-out answers, all for the better, and lost none. A sign test on 3 to 0 gives p = 0.25, so the held-out gain is not yet established.
BrainNet · part 9On 2026-11-13 the rank stage took 0.82 of a 1.56 second answer. A lookup fix cut it to 0.24 seconds cold, and a resident server to 0.093 seconds warm, with no change in the top five lists. Measured again on 2026-11-19: served rank median 0.100 seconds, cold rank 0.283 seconds.
BrainNet · part 8The merged network now holds 1,855,596 neurons in 3.50 GB of core files, and its resident rank server uses 747 MB after 88 questions. Our skill file said about 0.5 GB, and the files have grown faster than the neuron count.
BrainNet · part 10Every commit to our notes used to rebuild the whole network in 49 seconds and 8.40 GB. Four changes brought a warm refresh to about 16 seconds and 5.78 GB on 2026-11-06. On 2026-11-19 the warm refresh took 15.6 seconds but peaked at 7.40 GB, which fails our 6.5 GB line. An unchanged input costs 1.5 seconds.
BrainNet · part 11Four steps at 768 pixels cut a Z-Image picture from 7.1 seconds to 1.7. The sampler is already near the card's compute limit, so the gain came from steps and size, and the texture loss is the price.
Image models in a real pipeline · part 2The wiring was right and the behaviour was not. The reflex passed only after the electrical pairs were taken out, which is a different network and an after-the-fact fit.
The two runs differ by 46 percent. The cause is not isolated, because the model and the cut both changed, and the older run was not matched on load.
The switches themselves were short. What slowed the night was a refused step on one site, a tunnel waiting for a dashboard invite on another, and a mail provider we had wrong until 23:30.
Before and after the build-logic step, the release APKs matched on size, manifest and dex SHA-1. Device checks came after, and they found a bug the byte comparison could not.
Two mailboxes, both read by a person. Support for anything about the apps, bugs for crashes and defects.