genmount

Genmount OS client — run Genmount models locally, with an authenticated cloud fallback.

PyPI Python License: AGPL-3.0 Last Commit Stars

genmount is the user-side thin client for Genmount OS. It runs models locally on your machine via Ollama and routes hard cases to an authenticated cloud — shipping no model weights and running no server kernel on your device.

pip install genmount

🚀 Quickstart

pip install genmount
genmount doctor                 # check Python, Ollama, config

# Get a model (gated, free) from Hugging Face, then load it into Ollama:
#   https://huggingface.co/doorm-ai/Llama-3.2-3B-genmount-tcm-GGUF
ollama create genmount-tcm -f Modelfile   # FROM ./<file>.gguf; PARAMETER repeat_penalty 1.15

genmount chat "What does the classical literature say about ..."   # runs 100% locally

No account needed for local use — chat runs entirely on your machine via Ollama. Registration is only for cloud features (model sync / cloud fallback — rolling out):

genmount init --register        # optional: collects name / org / email / intended use

Your device keypair is generated locally and never leaves your machine.

🧰 Commands

Command Status What it does
genmount doctor ✅ Health check: Python, Ollama, config, device key — works offline
genmount init ✅ Generate a local device keypair + write config; --register activates against the cloud
genmount chat "…" ✅ local One-shot prompt to your local Ollama model
genmount upgrade [--check] ✅ Compare the installed version against the latest on PyPI
genmount chat --cloud ⏳ Route hard cases to authenticated cloud inference
genmount sync ⏳ Download + install the models your account can access into Ollama (sha256-verified)

🔐 Auth — zero shared secrets

  • A per-device ED25519 keypair is generated on your machine; the private key never leaves it.
  • An activation code exchanges your public key for a short-lived JWT plus per-request signatures.
  • By design, the client cannot disable or bypass server-side audit, redaction, or rate limiting.

🔭 Where this client sits

Tier Scope This repo?
L3 Production Production weights, clinical adapters, partner data 🔒 Closed
L2 Finetune-Workbench Training pipeline + quality gates Sibling repo (pending)
L1 Platform Gateway · state space · audit · redactor · runtime Sibling repo (pending)
Client Local runner + authenticated cloud glue ← You are here

The client is base-model agnostic — it talks to Genmount OS over a stable, authenticated API and is not tied to any one model or release schedule.

📦 Models

Genmount's traditional-medicine education models are distributed (gated, free registration) on Hugging Face — Built with Llama:

Run with repeat_penalty 1.15 (the genmount client sets this for you).

⚖️ Scope & safety

Outputs are educational / reference material over classical texts — not a diagnosis, prescription, dosing, or treatment recommendation, and not a medical device (non-SaMD). Always consult a qualified practitioner.

📡 Stay updated

  • ⭐ Star to follow releases · 👁 Watch → Custom → Releases for drop notifications
  • 💬 Discussions · 📬 Issues

📚 Companion artifacts

💼 Commercial / non-AGPL licensing

For commercial use outside AGPL-3.0-or-later terms, or partner integrations:

📧 service@doorm.ai

DOORM AI PTE. LTD. (UEN 202441729W) · Singapore

Project links

Key dates

PyPI data
Data sourced directly from PyPI's database.
  • Released:
Newer release available (0.1.2)

1 maintainer

PyPI data
Data sourced directly from PyPI's database.
Avatar for kelvintong88 from gravatar.com kelvintong88

Credits

Author: DOORM AI PTE. LTD.

License expression

AGPL-3.0-or-later
View SPDX License List

Requires

Python >=3.10

Provides Extra

dev

Tags

ai cli doorm genmount ollama tcm

Classifiers

Report project as malware

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

genmount-0.1.1.tar.gz (76.6 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

genmount-0.1.1-py3-none-any.whl (17.9 kB view details)

Uploaded Python 3

File details

Details for the file genmount-0.1.1.tar.gz.

File metadata

  • Download URL: genmount-0.1.1.tar.gz
  • Upload date:
  • Size: 76.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for genmount-0.1.1.tar.gz
Algorithm Hash digest
SHA256 02a85a1d7776aa82fcfd303bb17a1822734ef08dc75b34d810bed8e8c792db28
MD5 9a9f3f442ae0cbe325366eff1da87660
BLAKE2b-256 df97043ecf092fea5ea349ef12da42707796353a795c73168417df9db2e36833

See more details on using hashes here.

Provenance

The following attestation bundles were made for genmount-0.1.1.tar.gz:

Publisher: publish.yml on doorm-ai/genmount

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file genmount-0.1.1-py3-none-any.whl.

File metadata

  • Download URL: genmount-0.1.1-py3-none-any.whl
  • Upload date:
  • Size: 17.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for genmount-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 f786ee376f00ed1790f8004cf99e69efe5c87462195c6b4e1fd30de995ebc9e5
MD5 ffd876697efaf2a877608493b675eed1
BLAKE2b-256 fbff6ec25d4d5501d9298b28c68a1994fed128a09a29ee81ffb5158b4f80d9ab

See more details on using hashes here.

Provenance

The following attestation bundles were made for genmount-0.1.1-py3-none-any.whl:

Publisher: publish.yml on doorm-ai/genmount

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page