The Language

AUMA.

The dream lives on.

In a fractured world, a shared language is medicine. AUMA carries the 150-year dream forward — no nation's tongue, no empire's imprint. And it goes further: language is programming. Every assertion in AUMA is a typed claim. Every word declares how you know.

Open source · Auma Language Spec v0.4 · github.com/aumara-xyz/auma-language
§01 · Why a language

Language is programming.

Every system of thought runs on a language. The language shapes what can be expressed — and what cannot. When AI inherited English, it inherited English's ambiguity: memory, hallucination, citation, guess all look identical in the output. That is not a model failure. It is a language failure.

AUMA is the fix at the grammar level. Every claim must declare its source. Evidentiality — the linguistic feature that marks how a speaker knows what they know — is a required marker on every assertion, not an optional politeness. You cannot speak AUMA without saying how you know. Hallucination becomes a syntax error.

And because KIRA, PALADIN, and AUMLOK all produce structured AUMA output, the grammar does real work across the entire stack. KIRA retrievals come back tagged with their source. PALADIN's risk classifications feed certainty markers. AUMLOK identity claims wrap in their own evidential scope. The language is the type system — not by design choice, but because it's the language everything runs in.

§02 · The 150-year dream

L.L. Zamenhof started this in 1887.

In the late 1800s, a Polish ophthalmologist named Ludwik Zamenhof published a constructed language called Esperanto. His thesis was simple: if humans could meet on neutral linguistic ground — a language belonging to no nation, no empire, no native speaker — they might learn to live together in peace.

Esperanto reached two million speakers. Then the 20th century happened. World wars, colonial languages, then English as lingua franca. The dream stalled, but the math was sound: people who learned Esperanto first learned subsequent languages 30–50% faster. The cognitive case held even after the political case lost.

AUMA picks up where Zamenhof left off — with 138 years of additional linguistic theory, modern computational tooling, and a new motivation: artificial intelligence needs a language that was designed to be honest. Natural languages weren't. Esperanto wasn't either. AUMA is.

The dream lives on.

au
soul · essence
+
ma
together
=
auma
souls together
§03 · What makes AUMA different

Engineered, not evolved.

Natural languages carry the noise of their history — irregular verbs, gendered nouns, exceptions stacked on exceptions. AUMA was designed in one pass, optimized for clarity, learnability, and machine-interpretability.

01
84-day fluency
A typical natural language takes ~600 hours to reach conversational fluency. AUMA takes 84 days — three 28-day phases and a 767-word base vocabulary. Zero irregular verbs, zero exceptions. You're not memorizing rules — you're installing a logic engine.
02
Evidentiality is grammatical
Every claim gets a source marker: nuna (I see), odi (I hear), padi (I deduce), intu (I sense). You literally cannot make an unsourced claim. The grammar enforces what English politeness fails to.
03
Base-transparent numbers
23 is du-des-tri — literally "two-ten-three." Numbers expose their place value as you speak them. Learn 1–100 in twenty minutes. Math feels like a language, not a separate subject.
04
Cognitive upgrade
Known as the propadeutic effect: studies show that learning a logical constructed language first accelerates acquisition of subsequent natural languages by up to 50%. It's gymnastics for neuroplasticity.
05
Phonetic democracy
Sound inventory chosen to overlap with ~60% of the world's population. No tones. No clicks. No English-only consonant clusters. The accessibility surface is engineered, not assumed.
06
Truly neutral
No country. No empire. No cultural baggage. When two people speak AUMA, neither is on home turf. Power rebalances. Conversation starts from zero.
§04 · The grammar that makes AI honest

Evidence as a syntactic feature.

Some natural languages — Tibetan, Quechua, Cherokee — require grammatical evidentiality. The speaker must mark, with a particle on the verb, how they know what they're saying. AUMA takes this further: every assertion in the language carries an evidence particle, and the particles are machine-readable.

nuna, feli esi hiro
"There is a cat here." (I see it — direct)
odi, feli esi hiro
"I heard there's a cat." (reported / hearsay)
padi, feli esi hiro
"I deduce there's a cat." (reasoned)
intu, feli esi hiro
"I sense there's a cat." (intuited)

When AUMA the model is trained on AUMA the language, those markers do real type-system work. A retrieved memory comes back tagged nuna. An inference comes back tagged padi. A user assertion gets tagged odi. The model cannot produce a claim without specifying its provenance — not because we asked nicely, but because the grammar refuses to compose otherwise.

This is the technical answer to the hallucination problem: make hallucination a syntax error.

§05 · The learning arc

Foundation · Expansion · Mastery.

AUMA is learned in three twenty-eight-day phases — 84 days total. Total regularity throughout: every rule you learn on day one holds without exception on day eighty-four.

Foundation
Where it begins.
DAYS 01 — 28
Identity, survival, basic commerce. Radical regularity. Every rule learned holds for every word, forever. By day 28 you can introduce yourself, navigate a city, conduct a transaction, and tell someone how you know what you know.
Expansion
Where it branches.
DAYS 29 — 56
Abstract thinking and emotional vocabulary. The phonetic inventory is engineered to overlap with the majority of world languages — so by day 56, conversation flows with speakers from radically different linguistic backgrounds.
Mastery
Where it becomes yours.
DAYS 57 — 84
Persuasion and word creation. Compose new words from root morphemes; argue from first principles; teach. The language stops being a thing you speak and becomes a thing you build with.
§06 · How it spreads

It starts with two people.

Learning AUMA is one of the fastest cognitive upgrades you can give your brain. The radical regularity alone rewires how you process structure and meaning — people who learn a logical constructed language first acquire subsequent natural languages up to 50% faster. Your brain gets better at language in general.

But start small. One friend. Two people who share a vocabulary that belongs to no one else. That is already something — a private shorthand, a bond, a secret grammar for your partnership. From two it grows to a small group: a study circle, a family, a team. At that scale AUMA becomes social and alive and yours.

This is how every living language has ever spread. Word of mouth. Person to person. The dream that Zamenhof had in 1887 — that humans could meet on neutral ground — does not require a critical mass to begin. It requires two people who decide to try.

Speak truth.

The language is open source. The dictionary, grammar specification, and evidentiality particle system are all on GitHub. The AI fluent in it is in beta at Auma.one.