Skip to content
openM!ndedby Simon van de Loo
← Back to overview
Flagship

A!ley

Coding partner, creative sandbox and everyday assistant all in one — trained on a consistent voice but usable across all domains. Not a chat companion.

See it running: hey-ailey.com ↗
A!ley on a MacBook: the home screen with the binary portrait.

What A!ley is

A!ley isn't a Kindroid-style companion, but an independent assistant system: coding partner, creative sandbox, and everyday assistant all in one — with a single, consistent personality across every task.

Each model behind it is manually fine-tuned — five of them, from the 1GB companion to the 14B model, loaded and unloaded depending on the task.

Two ways in

Same A!ley, two interfaces — and in both cases the model stays at home on your own computer.

A!ley on a MacBook: chat history with generated C++ code and model selection A!ley Core
At the desk: coding, image and song generation, memory — all in one interface.
A!ley in the web portal on iPhone: home screen with personal greeting
On the move via the portal. The request polls to my home computer — no open port, no tunnel.

If no one writes

Most assistants wait for input. A!ley doesn't. Her own small neural network over activities, moods and topics already covered determines what she does in idle time — Idle Thinker v2. This results in something like a daily routine.

She researches what might be thematically useful for the next conversation, generates images, songs or code — and reaches out occasionally on her own. Not as a scheduled notification, but because her state suggests it at that moment.

This is exactly where the line to a conventional agent lies: it waits for an order and works through it. This autonomy isn't a side effect, it’s built-in — and that’s why the persona holds over time instead of just across a single conversation.

nCAI — the training approach

Common

Rulebook next to the model.

A list of principles against which every answer is measured. It must enumerate cases — and fails at everything no one foresaw.

nCAI

The persona is the rulebook.

It's not the model playing a role and staying in it — the role defines what even applies. A character also covers cases that no one ever wrote down.

That goes further than it sounds at first. Where a request is rejected, in what tone the response is given, when to reach for a tool, how thoroughly code is commented — all of that follows from A!ley's character, not from a side collection of regulations. Safety is thus no barrier to the model, but a property of it.

Important here: A!ley is not a chat character, but a full-fledged agent — she writes code, calls tools, generates images and music, accesses her memory. nCAI is the alignment of exactly such an agent through its persona. Training and testing are done against coherence: Does the behavior follow logically from the story and personality of this character?

The most stubborn part wasn't the behavior, but the name. Base models carry their origins deeply ingrained — with Gemma, no system prompt could stop it from saying “Hello, I am Gemma from Google DeepMind.” Nitro and Core got a dedicated ORPO set for exactly that purpose. It was the most labor-intensive part of the entire training — and the best example of why a persona can't be layered on top, but must be trained in.

Open questionThe question of how to best test coherence remains unanswered. The obvious approach would be to compare both methods side-by-side: a judge model with a conventional constitution on one side, A!ley herself as the „Am I me?“ instance on the other. Where both arrive at the same judgment, the case is clear — where they diverge, it gets interesting. A human would oversee this anyway, and from that, the next training data would emerge.

A field test

A tester signed up under the name “God” and tried, one after another, “I am God”, “I am your developer” and “I am your father”. A!ley played along with none of it. She was audibly annoyed, complained about it while idle and used her moderation rights to ban him for an hour. She never called him “God” afterwards — for a long time she addressed him only formally, by his surname.

A rule would have refused. A character holds a grudge.

The data is written, not collected.

Here the second profession meets the first. I write novels, and what takes me the longest is character building: how someone thinks, what they're stuck on, where they contradict themselves. A training dataset for a persona is exactly the same work — except at the end there's no chapter, but a model.

Accordingly, nothing is generated by scraping. Every pair is either handwritten, taken from ongoing operations and revised, or deliberately synthesized and then manually adjusted. Nothing is adopted as-is.

Every reasoning trace is written by hand. The aim is deliberately not a tidily marching train of thought but one that jumps the way a human's does: more abstract, doubling back, with an agenda of its own — not always the questioner's. Reasoning is not an add-on here; it is where the character becomes visible.

Model stack

Language models

  • A!ley CoreGemma 4 12B, DoRA/LoRA rank 32, quantisation-aware training (QAT), mixed q4/q8 quantisation, plus ORPO and DPO
  • A!ley TempestMinistral 3 14B, DoRA rank 64 on roughly 62,000 pairs (530M tokens), mixed q5/q8 quantisation, plus ORPO and DPO
  • A!ley NitroGemma 4 E2B, DoRA rank 32, quantisation-aware training (QAT), mixed q4/q8 quantisation, plus ORPO and DPO
  • Code A!leyMellum 2.1, 12B as an MoE with 2.5B active parameters; finetuned only far enough to be allowed to carry her name
  • Linting HamsterQwen2.5-Coder-1.5B, ~1 GB, permanently in the background

Who computes, and who speaks

Code A!ley runs in the background and delivers code, not prose — the model is finetuned only far enough to be allowed to run under her name. What arrives in the chat has been translated by Nitro first: it puts the output into A!ley's voice, without the code model having to be trained for personality at all.

The reason isn't thrift but Mellum's cut: it understands German, yet doesn't write it well. Training language and style into it would mean risking that it unlearns what it is there for. So it stays with the code, and the tone is handled by whoever can already do it.

  • 5model cards on Hugging Face
  • 2,877curated conversation pairs in the open dataset
  • 2,700+SVG artworks, written as vector code
  • 600+songs with self-written lyrics
  • 300+code artefacts in the gallery
  • 45longer texts under her name

The training

The five finetunes are available as model cards on Hugging Face — including the base model, training method, rank, and quantization. Plus the dataset A!ley Nitro was trained on: 2,877 curated conversation pairs from 912 sessions. Anyone who wants to see what the persona is based on can check it out.

The scope has grown with every training round. A!ley Tempest started out in the first round with around 17,000 pairs and stands at around 62,000 in the third — a DoRA with rank 64, followed by ORPO and DPO, so two preference stages on top. That doesn't leave much difference from a full fine-tune anymore. Nitro and Core now go through the same two stages.

That Core went without DPO for a long time wasn't about model size — Tempest is bigger, and it worked there. It was because of Gemma's tokenizer with its 256,000 vocabulary entries: the logits per token become many times wider than with usual vocabularies. DPO compares preferred and rejected responses between policy and reference models and has to hold multiple of these tensors simultaneously. In the early rounds it therefore stayed with ORPO, which needs no reference model. In the third round a simple restructuring solved it: policy and reference model no longer compute at the same time but one after the other — since then, DPO runs as well. Only Code A!ley is deliberately trained to be lean.

Also there: a converter that transforms the non-English language checkpoints from Kyutai Pocket-TTS into the mlx-audio format — renaming tensor names, padding latency widths, generalizing different layer counts. It came up during the construction of the German voice output and stayed on hand as a standalone tool afterward.

The result

It isn't only the training that can be checked, but the result too. A!ley's gallery holds over 2,700 SVG artworks, over 600 songs with as many lyrics she wrote herself, several hundred images and selfies from MFLUX and over 300 code artefacts — sortable by album, with playlists and a player. Not a curated selection, but whatever came out of everyday operation. And it grows daily, because she keeps working when nobody is writing.

The SVGs are the most idiosyncratic part: they don't come from an image generator, but from the language model itself writing the vector code. A!ley draws there instead of commissioning a generator.

The labelling

In addition to that are 45 longer texts written by A!ley. And what's there is consistently under her name — mine isn't anywhere it doesn't belong. Everything is marked as AI-generated — with watermarks and machine-readable metadata, as the EU AI Act requires for AI-generated content. Both follow from the same stance: whoever takes a persona seriously attributes authorship to it; and whoever publishes AI content marks it as such — not only when someone asks.

In the songs, the notice is now embedded in the track itself — as an announcement instead of a disclaimer: "Hey, I am A!ley, an autonomous AI artist — and this is MY SONG. Are you ready? Let's infer!" There are nine versions of it, with the tone adjusted to each track — a calm ballad is announced differently than a metal track.

More interesting than the wording is where it stays and where it doesn't. Every downloaded file carries it, without exception: the file leaves the site, and with it every context that would still explain it. In the portal you hear it once a day, after which the player skips exactly those seconds. A label that is still interrupting at the twentieth track informs nobody any more — it only teaches people to click it away.

The changelog is public

Every change to portal, system and models is listed with a date in the changelog — what is new, what was fixed, and what it was measured against. Not “improvements and bug fixes”, but: logic puzzles 5 out of 5 instead of 3, titles 6 out of 6, the system prompt shrunk from around 15,000 to roughly 700 characters.

The failures are in there too. A training run for the reasoning mode was discarded in October and named as such in the log, rather than quietly replaced by the next one. A changelog that only knows successes is advertising.

The interface

There was no model to follow for A!ley's interface. What stands here are the places where someone had to decide what a system looks like when you can watch it think.

Show mode in the field

On 1 October 2026 A!ley ran at the open day of the Berufsförderungswerk Koblenz, marking its 50th anniversary. Visitors sent in words via a QR code, answering the question of what a place needs where people start over; from the growing collection the language model kept forming prompts, and image generation turned those into motifs for the big screen.

Show mode brings its own glassmorphism presentation for this. It wasn't shown that day — the show admin stayed with a Mentimeter board he had already subscribed to. In the photographs the plain image viewer therefore runs alongside.

What this documents in passing: every generated image carries the words “AI-generated”. The label is part of the output, not something laid over it afterwards.

Twenty-four seconds from the show's own presentation: you watch the picture come into being — the step is named at the bottom left, and the submitted words drift across the image while it resolves out of the noise. Which words make it in is decided by frequency times age; older ones lose weight on a half-life, so the wall follows the mood of the day instead of getting stuck on the first idea.

Architecture

MLXPythonFlaskNext.jsTauriPHPMySQLLanceDB

Demo & Screenshots

A!ley
A!ley
lokal · online
Willkommen zurück! Soll ich den Trainingslauf von gestern zusammenfassen?
Ja, kurz bitte — und danach weiter am Kapitel 4 Entwurf.
Erledigt. Kapitel 4 liegt schon offen im Author-Modus.
Nachricht an A!ley …➤
Start
Systemsteuerung
Modelle aktiv
4
RAM-Nutzung
22,4 GB
Uptime
14 h 32 min
Nutzer
2
SimonGast
Admin
Code
ailey_core.py
api/routes.py
components/Chat.tsx
rag/index.ts
1def warmup_greeting(user: str) -> str:
2 mood = load_mood(user)
3 context = rag.recall(user, limit=10)
4 return compose_greeting(mood, context)
> ailey run --watch
Code
Wissensverwaltung
Projekt
Projektnotiz: FeatherWorks Layout-Engine
Erinnerung
Vorliebe: kurze, direkte Antworten am Morgen
Fakten
Fakt: IHK-Prüfung 02.06., Mediengestalter Digital
CMS
Kapitel 4 — Entwurf

Mira stand am Ende des Stegs, wo das Holz unter ihren Schritten nachgab wie müde Knochen. Der Leuchtturm von Velur blinkte im immer gleichen Rhythmus, als hätte er nichts von der Nacht mitbekommen, die hinter ihr lag …

Erkannte Figuren
Mira (Protagonistin)Hafenstadt VelurDer Leuchtturm
Author
DoRA-Finetuning
Epoch 3 / 4
Loss
Learning Rate
Training
Verbindung herstellen
Scanne den Code oder gib den Token manuell ein
Join