Elamur: **Mova** · [Parse](https://mova.elamur.ai/free/en/parse/) · [Dictionary](https://md.dictionary.elamur.ai/free/en/) · [Translate](https://md.translate.elamur.ai/free/en/) · [Research](https://md.research.elamur.ai/free/en/) · [MCP](https://mcp.elamur.ai/) · [Groupants](https://md.groupants.elamur.ai/free/en/)

[Mova](https://md.mova.elamur.ai/free/en/) · [this page in HTML](https://mova.elamur.ai/free/en/docs/repo-docs/)

[home](https://md.mova.elamur.ai/free/en/) / [docs](https://md.mova.elamur.ai/free/en/docs/) / Documentation

- [mysticism](https://md.mova.elamur.ai/free/en/docs/repo-docs/mysticism/) — Mysticism · 40
- [seeds](https://md.mova.elamur.ai/free/en/docs/repo-docs/seeds/) — Seeds, explained · 7
- [animals.md](https://md.mova.elamur.ai/free/en/docs/repo-docs/animals/) — Animals and workers
- [architecture.md](https://md.mova.elamur.ai/free/en/docs/repo-docs/architecture/) — Architecture
- [assets.md](https://md.mova.elamur.ai/free/en/docs/repo-docs/assets/) — Mova mascot artwork
- [context.md](https://md.mova.elamur.ai/free/en/docs/repo-docs/context/) — Context, layers and memory
- [correspondences.md](https://md.mova.elamur.ai/free/en/docs/repo-docs/correspondences/) — Correspondences
- [data.md](https://md.mova.elamur.ai/free/en/docs/repo-docs/data/) — Data, libraries and licences
- [dialect.md](https://md.mova.elamur.ai/free/en/docs/repo-docs/dialect/) — The Mova dialect: a UD metadialect, treebanks and converters
- [economics.md](https://md.mova.elamur.ai/free/en/docs/repo-docs/economics/) — The economics of Mova
- [english.md](https://md.mova.elamur.ai/free/en/docs/repo-docs/english/) — The English layer
- [gpu-exec.md](https://md.mova.elamur.ai/free/en/docs/repo-docs/gpu-exec/) — Execution modes: CPU only and GPU enhanced
- [groupants.md](https://md.mova.elamur.ai/free/en/docs/repo-docs/groupants/) — Groupants
- [hybrid-system.md](https://md.mova.elamur.ai/free/en/docs/repo-docs/hybrid-system/) — Mova as a hybrid system
- [knowledge.md](https://md.mova.elamur.ai/free/en/docs/repo-docs/knowledge/) — Worlds and knowledge
- [mathematical-modeling.md](https://md.mova.elamur.ai/free/en/docs/repo-docs/mathematical-modeling/) — Mathematical modeling of code
- [modules.md](https://md.mova.elamur.ai/free/en/docs/repo-docs/modules/) — Add-on modules
- [parsers.md](https://md.mova.elamur.ai/free/en/docs/repo-docs/parsers/) — Open parsers: witnesses and tests
- [pragmatics.md](https://md.mova.elamur.ai/free/en/docs/repo-docs/pragmatics/) — Pragmatics: frames — who did what to whom, why, and what came next
- [school.md](https://md.mova.elamur.ai/free/en/docs/repo-docs/school/) — The school
- [training.md](https://md.mova.elamur.ai/free/en/docs/repo-docs/training/) — Training Mova
- [all 68 pages in this folder and below →](https://md.mova.elamur.ai/free/en/docs/repo-docs/all/)

# Documentation

Mova is a Hybrid Combinatorial–Operational System with a Combinatorial Small Language Model (SLM) at its core. These pages describe how it is built and how it works. Start with [the hybrid system](https://md.mova.elamur.ai/free/en/docs/repo-docs/hybrid-system/), then [the architecture](https://md.mova.elamur.ai/free/en/docs/repo-docs/architecture/). Each crate has a README next to its code with the full command reference.

## Overview

- [Mova as a hybrid system](https://md.mova.elamur.ai/free/en/docs/repo-docs/hybrid-system/) — what Mova is: the three layers (language, combinatorial, operational), what is implemented and what is direction; the octopus mascot.
- [The economics of Mova](https://md.mova.elamur.ai/free/en/docs/repo-docs/economics/) — why Mova changes where intelligence is spent: a persistent orchestrator, the SLM at the margin, large models as consultants, and what to measure.
- [Architecture](https://md.mova.elamur.ai/free/en/docs/repo-docs/architecture/) — the pipeline from text to answer, the three levels of logic, the teacher loop, the students, the crates and where things live.
- [Context, layers and memory](https://md.mova.elamur.ai/free/en/docs/repo-docs/context/) — context, layers and memory: the tale world, the SLM subsystems and what is inferred from context, with the gaps named.

## The language layer

- [The English layer](https://md.mova.elamur.ai/free/en/docs/repo-docs/english/) — the English parser and compressor step by step, the grammar expert system, trees by derivation, and the round trip through the layers.
- [Open parsers: witnesses and tests](https://md.mova.elamur.ai/free/en/docs/repo-docs/parsers/) — the open parsers Mova uses as witnesses and tests, their licences and roles.
- [The Mova dialect: a UD metadialect, treebanks and converters](https://md.mova.elamur.ai/free/en/docs/repo-docs/dialect/) — the Mova UD dialect, treebanks and converters between conventions.
- [Pragmatics: frames — who did what to whom, why, and what came next](https://md.mova.elamur.ai/free/en/docs/repo-docs/pragmatics/) — frames (who did what to whom, why, and what came next), speech acts, implicature, expressions read by their meaning, the external pragmatics tools.
- [seeds/](https://md.mova.elamur.ai/free/en/docs/repo-docs/seeds/) — the grammar seeds explained, one page per folder.

## Worlds, knowledge and the school

- [Worlds and knowledge](https://md.mova.elamur.ai/free/en/docs/repo-docs/knowledge/) — the knowledge contract (skeleton, important graph, global graph), the absurdity matrix, the nerve graph, RAG.
- [The school](https://md.mova.elamur.ai/free/en/docs/repo-docs/school/) — the primary school: how courses are made, their format, how the pupil reads and answers, controls, diagnosis, tools, retention in a fresh process, Mova-driven improvement, and the school results.
- [Training Mova](https://md.mova.elamur.ai/free/en/docs/repo-docs/training/) — how Mova is trained: the teacher transport, the training pipeline, measuring and gates, self-directed learning (induce, self-play), the annotation and storage contract, reviewed promotion, re-annotation.

## Workers

- [Animals and workers](https://md.mova.elamur.ai/free/en/docs/repo-docs/animals/) — the Octopus (an LLM that develops Mova, not part of its runtime) and Mova's Rust animals: Crab, Eel, Fish, Whales, Nautilus, Turtle, Sea Spider (and MovaBot), terminals, the Dolphin consultants; their protocols, evidence boundaries and custom modules.

## Groupants and mathematical modeling

- [Groupants](https://md.mova.elamur.ai/free/en/docs/repo-docs/groupants/) — the groupant: the combinator node of a piece of code, its components, sidecars, tree, registry, coverage, the external reference library and the publication scope.
- [Mathematical modeling of code](https://md.mova.elamur.ai/free/en/docs/repo-docs/mathematical-modeling/) — the models every file and group needs: vidtvorants, typed obernants, reverse reconstruction, the mathematical combiner, executable Rust approximants.
- [Correspondences](https://md.mova.elamur.ai/free/en/docs/repo-docs/correspondences/) — typed mathematical correspondences between algorithm groupants and Mova sources, and algorithm transfers through explicit adapters.

## Execution, data and releases

- [Execution modes: CPU only and GPU enhanced](https://md.mova.elamur.ai/free/en/docs/repo-docs/gpu-exec/) — the two execution modes, CPU only and GPU enhanced: stages, checks and reference switches.
- [Data, libraries and licences](https://md.mova.elamur.ai/free/en/docs/repo-docs/data/) — where data lives, licences, the maths and science libraries, Wiktionary, paper cards, competitions.
- [Add-on modules](https://md.mova.elamur.ai/free/en/docs/repo-docs/modules/) — add-on modules (for example dictionaries under their own licences): install from a URL or a torrent, verify, and load into Mova.
- [Changelog](https://md.mova.elamur.ai/free/en/docs/CHANGELOG/) — what changed in each release; release notes: [0.6](https://md.mova.elamur.ai/free/en/docs/releases/0.6/) (draft), [0.5](https://md.mova.elamur.ai/free/en/docs/releases/0.5/), [0.4](https://md.mova.elamur.ai/free/en/docs/releases/0.4/), [0.3](https://md.mova.elamur.ai/free/en/docs/releases/0.3/), all in `releases/`.
- [Elamur Cosmic License](https://md.mova.elamur.ai/free/en/docs/LICENSE/) and [Data and model licences](https://md.mova.elamur.ai/free/en/docs/licence/DATA/) — the Elamur Cosmic License and the licences of data and models.

## Elsewhere in the repository

- [Tests](https://md.mova.elamur.ai/free/en/docs/tests/) — unit tests and benchmark commands.
- [`corpus/open`](https://md.mova.elamur.ai/free/en/docs/corpus/open/) — the open corpus. [Papers Mova uses](https://mova.elamur.ai/free/en/docs/papers/) lists the works Mova uses, each linked to its card on Elamur Research; [usage.tsv](https://md.mova.elamur.ai/free/en/docs/repo-docs/) logs where each is applied.
- [`train`](https://md.mova.elamur.ai/free/en/docs/train/) — how to retrain Mova for your own domain.
- [eval/](https://md.mova.elamur.ai/free/en/docs/repo-docs/) — evaluation lists. Ablation reports of [tools/value](https://md.mova.elamur.ai/free/en/docs/tools/value/) are run records, not pages.
- [assets/](https://md.mova.elamur.ai/free/en/docs/repo-docs/assets/) — the octopus artwork. [mysticism/](https://md.mova.elamur.ai/free/en/docs/repo-docs/mysticism/) — background texts and [Gali](https://md.mova.elamur.ai/free/en/docs/repo-docs/mysticism/02-gali/), the working mode for AI instances that build Mova: Mova's own working philosophy, not tooling; nothing in the build or the checks depends on it.

## Writing docs

New documentation extends one of the pages above. A new page needs a new subsystem; per-feature, per-experiment and per-review notes do not become pages. Docs describe how things are and work; the only measurements kept are school results and comparisons with earlier releases. Every relative link must resolve: `cargo test -p mova-modelcheck --test doc_links` checks files and heading anchors in all public Markdown.