00 · A LIFESTYLE CHANGE
Your intelligence.
Forever owned.
Always improving.
ARAIL gathers the understanding. DaC is the press that compiles it into sourced truth. Nucleus mints the printed book — a model you own. AeroLLM runs it on your hardware. PaperAgents puts it to work.
Learn to use AI responsibly and securely, then own a specialized model that runs on your hardware. Humans learn. AI does.
Cloud-optional. No subscription. Local, private, cryptographically yours.
SCROLL
Built to educate.
Learn to use AI in the modern world — responsibly and securely — and master any domain with it. QuKaiZen is the harness we're building around AI itself — five parts, one stack. All of it runs on your own hardware — no cloud, no subscription, no data leaving the room.
The Harness
ARAIL the lab — research with Buddy, experiments with a goalAeroLLM the inference engine — run models far bigger than your GPUDaC the press — compiles data and docs as code into sourced truthNucleus the build pipeline — prints the book, a model you ownPaperAgents agentic automation wrappers — every action leaves a paper trailServed by retrieval — RAG — while a topic is fresh. Baked into the model's weights once it settles. Same subject, kept current.
Built today: the provenance-gated knowledge base, its open API, off-disk inference · Roadmap: the Nucleus bake hand-off, the Fact Steward (automated fact verification)
How it started: on the field's shared R&D — the papers, the techniques, and the engineers who made them understandable. People like Karpathy, whose vision of compiled knowledge set the stage. The thesis traces that lineage.
One press, pointed at any subject.
Each World is a subject under development — an open, fast API over a fully sourced corpus that research agents keep current. The same press that compiles the stack's own knowledge, pointed anywhere.
AI / ML
World I · the AI / ML Dictionary
The original. The whole discipline, from attention and transformers to RAG and agent memory.
Enter the World →
Astronomy
World II · immersive
Sourced terms from parsec to the cosmic microwave background. Crank the lever and the stars come out.
Enter the World →
Mathematics
World III · immersive
The famous formulas and the most beautiful results, Euler's identity to Gödel. The blackboard never stops writing.
Enter the World →
Quantum
World IV · new
The physics of the very small, told honestly. Superposition, entanglement, qubits, and the pop-science myths stripped out.
Enter the World →
Biology
World V · new
The science of life, from the double helix and the cell to evolution and the immune system, with the myths corrected.
Enter the World →
Ecology
World VI · new
Trophic cascades, regime shifts, and metapopulations — ecosystem-level ecology told honestly, with the pop-myths corrected.
Enter the World →
A declared manifest gates the worlds as they build.
Where it began.
ARAIL is the research lab: autoresearch agents curate arXiv daily, and Buddy — your lab partner — tracks your goals and flags what's worth your attention. Local, zero telemetry, Apple Silicon or Linux from 8GB unified. It's the seed everything else grew from.
Buddy
ARAIL LAB AGENT
Experiment #47 completed — convergence at 95.2%
You set a goal: "Match the 70B teacher on Linux memory management."
The swarm found 3 new edge cases in NUMA topology since last run. Does that align with where you wanted to take this?
./arail setup one command, two tiers — README on GitHub
Buddy Tunnel reaches him on iMessage, Signal, Slack & more — docs on GitHub ↗
Declare the team. The agents reconcile.
Small specialist agents for sales, support, ops, and books — declared in TOML, watched continuously, and pulled back to the state you declared when reality drifts. Same stack as the lab; one agent per function the business already does.
[team.sales] watch = "continuous" [team.support] reconcile = "desired-state" [team.ops] [team.books] # one agent per function
400B parameters. 8 GB of VRAM.
Once the book is printed, AeroLLM reads it — streaming the model off your SSD one layer at a time — load, compute, discard, prefetch — so the full weight set is never resident. Speculative decoding stacks on top: a small draft model proposes, the full model verifies in a single pass, provably lossless.
With full credit to AirLLM for the layer-streaming idea — rebuilt in Rust for stability and Apple Silicon (MLX) support.
7×
Faster Throughput
up to 7× — speculative decoding on 70B+ teachers
400B+
Max Model Scale
on 8GB VRAM, layer-by-layer off SSD
~83%
Less Power Overhead
unified memory vs discrete-GPU copies
85%
Cost Savings / Watt
projected — $0.30/W vs $2/W industry standard
Mine deep. Craft precise. Forge permanent.
Parallel agents mine a frontier teacher across 7 knowledge layers; an adversarial swarm then runs until it exhausts every failure mode — graduation happens when the swarm gives up, not when epochs complete. The printed book is the result: a compact 1–7B Super Skill that knows its domain, owned by you, running local.
Today the pipeline runs deliberately, not on its own — automatic bake from a settled World is the aim.
3B from 500B
Distilled to a model you own
graduates when the swarm gives up, not when epochs complete
3-Gate
Post-graduation certification
general regression · domain mastery · hallucination audit
Ed25519
Nucleus Seal provenance
corpus + teacher + config + training, signed once
<2%
Hallucination rate, hard target
zero fabricated entities · refusal calibration >90%
Nucleus Seal — verify it, don't trust it.
corpus | teacher | config | training → sha256 → Ed25519 ✓ · checked offline — change one byte and it stops verifying
Revocation today is operational, not cryptographic — full scope on /nucleus
Understand all of it.
Learn is the front door for everyone finding their footing — the same press, turned on its own craft. Every concept behind the stack explained plainly, starting with the AI / ML Dictionary and a /what API your tools can call.
08 · The Principle
This is not RAG.
This is not prompt engineering.
The Super Skill knows.
Intelligence crystallized into a 1–7B model — sealed, local, near-zero marginal cost per query. It doesn't look the knowledge up. It knows it.
Core Metric
Wisdom per Watt
certified, owned capability ÷ lifetime energy to mint & run it
the point where owning beats renting — and it only moves in your favor