ARAIL — EXPERIMENTS & EDUCATION

A rail for AI experimentation
& education.

ARAIL ships as a blueprint. Take an agent and an IDE and tailor / set up yourself. A Python runtime, AeroLLM, a starter model, and supportive agents — including Buddy. Everything you need to start a session offline, on a single box.

If you have a smaller machine, choose Minimalist mode. Else set up Maximum mode to build out all the functionality: a Rust router, AeroLLM, an agent swarm, AutoResearch, frontier teacher models.

Open the lab →View the explainer →Read the source ↗

QuKaiZen · ARAIL · v0.4 · airgapped

02 — ORIGIN

Why I built this.

First there was Buddy. Then a place for him to live.

I wanted to learn AI — properly. I was curious how the models were built. I didn't know where to begin, so I started with a companion: Buddy. Then I built an environment for him. That environment became ARAIL.

Then I found agentic AI, then autoresearch — and couldn't get enough. The lab needed to be pluggable, and I had to be able to see what was happening inside it.

03 — THE RAIL

AutoResearch AI Lab.

The name is the goal. A rail — straight, fast, repeatable — that you mount things onto. The rail is the scaffolding. What rides on it can change month to month — the operating surface stays the same.

same dashboard for every experiment
same activity stream for every agent
same knowledge base behind every loop
same airgapped → hybrid switch for every call

agentsautoresearchdual-modelknowledge

THE LAB — MINIMALIST CORE · MAXIMOST REACH

IN THE LAB · MISSION CONTROL

Not a mockup — the real operating surface. Every experiment, agent, and knowledge loop on one screen, server-rendered and airgapped.

Mission control — quick actions, live services, and your current mission

Autoresearch — every experiment is a git branch; the loop runs your program.md

The knowledge base — one tree feeding the wiki, notebooks, and agents

Lab docs — the AI dictionary and runbooks, in-product

Agent Control Center — forge an agent from a prompt, deploy without a restart

05 — DEFINITION

Three keystrokes to a local AI lab.

A clone-and-run research bench. Dashboard, chat, autoresearch loop, knowledge base, agents — server-rendered, no SPA, no telemetry. Default mode is airgapped. Zero network calls until you flip LAB_MODE=hybrid.

$ git clone cdarnell/arail
  cloned to ~/arail
$ ./arail setup
  ✓ venv created  ✓ deps pinned  ✓ portal ready
$ ./arail start
  ▶ serving on 127.0.0.1:8080
  ⬤ airgapped  ⬤ buddy · sre · researcher
$ open http://127.0.0.1:8080

04 — COST POSTURE

Pay for frontier models. Just not by accident.

Simulate before you spend.

LOCAL MODE — AIRGAPPED

Iterate freely. Run a thousand experiments overnight. Zero network calls until you say so.

HYBRID MODE — METERED

Every cloud call is logged with provider, model, and tokens. Same surface. Same agents. Real receipts.

06 — TIERS

Two tiers, one surface.

TIER · STARTER · MINIMALIST

The lab

Dashboard
Chat — local + cloud
Autoresearch loop
Knowledge Base
Agents — Buddy · SRE · Researcher
Airgapped by default

TIER · OPERATOR · MAXIMUM

The operator's console

everything in Minimalist +
Admin · Docs · Notebooks
405B local inference via AeroLLM
Cloud SDKs · provider routing
Still airgapped unless you flip LAB_MODE=hybrid

BUDDY TUNNEL

Hybrid only — gateway required

The dashed branch in the diagram. Telegram, Slack, Discord, Signal cleanly; iMessage and WhatsApp through bridges. Needs internet and a gateway. Airgapped mode blocks the tunnel by design — see docs/BUDDY.md.

07 — PLUGGABILITY

What plugs into the rail.

Four mounting points. Swap any one. Same protocol, same activity stream, same token accounting.

08 — COMPARE

Same prompt. Two minds. One screen.

Local vs cloud. Small vs large. Base vs fine-tuned. Real comparison, not benchmarks.

parse_goal> explain the bias-variance tradeoff like I write firmware

QWEN-3-8B

local · MLX

Bias is your model's stuck-at fault — it always answers a little wrong. Variance is marginal noise — different inputs ring differently. You tune capacity to balance them, same as a low-pass filter…

184 tok·3.1s·$0.000

CLAUDE-OPUS-4.1

cloud · anthropic

Think of bias as systematic miscalibration baked into your model class, and variance as jitter from the specific training samples you happened to draw. They trade off through model capacity…

212 tok·1.8s·$0.024

09 — OBSERVABILITY

If you can't see it, you can't trust it.

Every agent action — timestamped, attributed, token-counted, streamed live.

Activity stream

tail -f · live

14:02:08 buddy parsed goal → p95_latency < 400ms 412 tok

14:02:11 researcher spawned experiment exp_0014 qwen-3-8b · MLX · 88 tok

14:02:24 researcher baseline measured · p95 = 612ms 1.2k tok

14:03:01 sre ⚠ vram pressure 88% · throttling to bs=4 —

14:03:48 researcher applied kv-cache patch · p95 = 387ms ✓ target hit · 3.4k tok

14:03:50 buddy notes written → knowledge_base/exp_0014.md 204 tok

10 — MEMORY

Knowledge base — the gem.

The lab gets smarter the longer you use it. Drop data in. Agents drop data in. Relevant pieces get RAG'd back into context — for you and for them.

KNOWLEDGE_BASE/

RAG · retrieve · augment · generate

YOU

papers · notes · code

BUDDY

distilled summaries

RESEARCHER

experiment notes

SRE

crash transcripts

11 — CONSTRAINT

The hardware wall.

Even a $5,000 GPU still settles.

The compromise: < 100B parameters · small context · loud fans · hot rack. That wall is real. You can buy your way closer to it. You can't buy your way through it.

So I stopped trying to buy through it. I built around it.

WHAT YOU ACTUALLY WANT TO RUN

405B

WHAT FITS — AT SMALL CONTEXT

~70B

12 — INFERENCE

AeroLLM — built around the wall.

Layered inference for MLX and CUDA. Same idea AirLLM proved — stream weights in, compute, evict — rebuilt for unified memory and quiet enclosures.

# INSPIRATION

▸ AirLLM

+ proved the idea
− unstable on long runs
− no MLX support
− CUDA-only · 3090 sounded like a leaf blower

# THE ANSWER

▸ AeroLLM — same idea, made for laptops

✓ MLX + CUDA
✓ stable on hour-long runs
✓ ships with ARAIL Maximum

Thanks to the AirLLM team for charting the path.

13 — HARDWARE

We meet you where you are.

No pretending. Minimalist runs almost anywhere. Maximum needs the rig.

MINIMALIST

cpu	any modern x86_64 / Apple silicon
ram	16 GB
gpu	optional
disk	20 GB
os	macOS · Linux · WSL2
net	none required

MAXIMUM

cpu	M-series MacBook Pro · serious gaming rig
ram	64 GB unified / 64 GB sys + 24 GB VRAM
gpu	RTX 3090 / 4090 · M3 Max / M4 Pro+
disk	500 GB NVMe
os	macOS 14+ · Linux
net	required only for hybrid mode

14 — NEXT FRONTIER

Project Nucleus — a model that learns from your knowledge base.

Nucleus reads the world's published research on distillation and efficient fine-tuning, then applies it to a base model + your KB. You get a smaller, sharper, you-shaped model.

01 · INGEST

knowledge_base/

papers · notes · experiments

02 · SURVEY

techniques

distillation · LoRA · DPO

03 · TRAIN

recipe

picked, not guessed

04 · SHIP

you-shaped model

smaller · sharper · local

⬤ IN DEVELOPMENT · EXPECTED v0.6 — EARLY LAB ACCESS VIA DISCORD

15 — AVAILABLE

A QuKaiZen product. Built the kaizen way.

Available by request.

MINIMALIST

⬤ AVAILABLE

Dashboard · Chat · Autoresearch · Knowledge Base · Agents. Airgapped by default · hybrid opt-in. Runs on any modern laptop.

MAXIMUM

⬤ AVAILABLE

Everything in Minimalist + Admin · Docs · Notebooks. AeroLLM · 405B local inference. Cloud SDKs · provider routing. Serious rig or M-series MacBook Pro.

NUCLEUS — ADD-ON

⬤ PREVIEW

Fine-tuning pipeline. A smaller, sharper, you-shaped model distilled from your knowledge base. See /nucleus.

ACCESS

By request · qukaizen.com

Not open source · Pull requests not accepted · Source available under select arrangements

Request access →

A rail for AI experimentation& education.