# soma · downloads

soma runs anywhere python does. pick the app for your platform, or grab the script bundle if you want the source.

## mac app (recommended)

`soma.dmg` · released 2026-08-01

soma for macos. a minimal black-and-white desktop app with four spaces — chat (load a checkpoint and talk to it locally, in text or voice: the mac app can record one utterance through apple's on-device speech recognition and read replies through the system voice, with online learning so the conversation can become part of the model's ongoing training), train (continue training from local files or live streams, watching loss, accuracy, throughput, decimation, autosaves, and dream samples in real time), stream (run small live input scripts that feed soma an ongoing text stream as a training source), and logOS (browse shared checkpoints from logossoma.com, inspect their metadata, download them into soma, and continue them locally). keeps a local app folder for checkpoints, data, streams, logs, and chat history; no cloud account required for local use.

download: https://logossoma.com/api/download/app/mac

quickstart: drag soma to applications · open it · drop your corpus into soma's data folder, then hit train.

## python script (any os)

soma v12.3.17 · released 2026-08-23

soma v12.3.17 as a python script bundle. token-native continual spectral learner — a fixed 8k sentencepiece dictionary (soma-8k-v1) feeds a token trace bank whose retained identity is projected through the current learned dictionary each batch; a serial budget-residual mlp of depth D composes over the projected bandpass present with tied io/output dictionary and residual gates initialised at 0.1; row magnitude is governed by radial plasticity compression rather than hard row clipping, so rows lose outward growth as they approach capacity while inward and directional learning stay open; io2 drives plasticity, decimation gain and depth saturation from the spectral residual. zip containing the v12.3.17 runtime (soma_v12_3.py), the checked-in soma-8k-v1 tokenizer, a launcher shell wrapper, the logos bridge, the training loop and worker, stream sources, corpus builders, the current v12.3.17 spec, a cloud trainer, and the local speech helpers (soma_voice.py + macos_soma_speech.swift + soma-speech binary) so the mac app can talk and listen fully on-device. for linux, windows, cloud gpus, or anyone who wants the source.

downloads:
- bundle (.zip): https://logossoma.com/api/download/script/soma.zip
- soma_v12_3.py (standalone runtime): https://logossoma.com/api/download/script/soma.py
- v12.3 spec (.md): https://logossoma.com/api/download/script/soma_spec.md

quickstart — mac / linux (bundled launcher bootstraps a venv on first run):

```
unzip soma.zip
cd soma-v12.3.17-script-bundle
./soma
```

quickstart — windows / manual:

```
pip install -r requirements.txt
python soma_v12_3.py
```

## paper

https://logossoma.com/api/download/paper.pdf

## full algorithm reference

human page: https://logossoma.com/specs
markdown mirror (this format): https://logossoma.com/api/specs.md