Skip to main content
Dromos, Lernex's inference engine for the Metis models, run on your own machine.

pip install dromos
dromos run praxis chat in the terminal
dromos serve logos the OpenAI API on this machine

The engine picks its backend when it starts: CUDA on an NVIDIA GPU (Linux x86_64 and Windows x64; the CUDA runtime
comes from NVIDIA's own wheels, which this package installs), Metal on Apple silicon (macOS 14 or later), and the CPU
otherwise.

Metadata

Release files for dromos 0.1.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Built distributions (wheels)

Table of built distributions (wheels) for dromos 0.1.0
File Actions
dromos-0.1.0-py3-none-win_amd64.whl Python 3 none Windows x86-64 Details for dromos-0.1.0-py3-none-win_amd64.whl
dromos-0.1.0-py3-none-manylinux_2_28_x86_64.whl Python 3 none Linux glibc 2.28+ x86-64 Details for dromos-0.1.0-py3-none-manylinux_2_28_x86_64.whl
dromos-0.1.0-py3-none-manylinux_2_28_aarch64.whl Python 3 none Linux glibc 2.28+ ARM64 Details for dromos-0.1.0-py3-none-manylinux_2_28_aarch64.whl
dromos-0.1.0-py3-none-macosx_14_0_arm64.whl Python 3 none macOS 14.0+ ARM64 Details for dromos-0.1.0-py3-none-macosx_14_0_arm64.whl

Total release size: 133.9 MB

Release files / dromos-0.1.0-py3-none-win_amd64.whl

Download URL dromos-0.1.0-py3-none-win_amd64.whl
Size 63.8 MB
Tags Python 3 Windows x86-64
SHA-256 checksum
How to use checksums
fc0b2b7ecbea9b6351df32b6fec357a257124658af8085e51a58f33fcbdcecc1
BLAKE2b-256 checksum
How to use checksums
6c24d0371751fa66469f7e9d83d2d40344ae4028dbffb8c7b25be113c9fae9ca
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 1, 2026.

Transparency log

Release files / dromos-0.1.0-py3-none-manylinux_2_28_x86_64.whl

Download URL dromos-0.1.0-py3-none-manylinux_2_28_x86_64.whl
Size 65.7 MB
Tags Linux glibc 2.28+ x86-64 Python 3
SHA-256 checksum
How to use checksums
b30258c5067c382daf444f1e6cfa00d03d40ccfec485aa7cd5404c494d5f082e
BLAKE2b-256 checksum
How to use checksums
e07c899f09efb91c12a267230fce4ad6ff5782ad3c87574a57ac4e8bd509a3e8
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 1, 2026.

Transparency log

Release files / dromos-0.1.0-py3-none-manylinux_2_28_aarch64.whl

Download URL dromos-0.1.0-py3-none-manylinux_2_28_aarch64.whl
Size 3.1 MB
Tags Linux glibc 2.28+ ARM64 Python 3
SHA-256 checksum
How to use checksums
f44df2c6e4c25616e98cd413410825bb09830590d9d40432a1d8f426e7a575ea
BLAKE2b-256 checksum
How to use checksums
da599d26337610fb2cd07f4b2e4710039a18184101bceb66becabb7a6d6952de
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 1, 2026.

Transparency log

Release files / dromos-0.1.0-py3-none-macosx_14_0_arm64.whl

Download URL dromos-0.1.0-py3-none-macosx_14_0_arm64.whl
Size 1.3 MB
Tags Python 3 macOS 14.0+ ARM64
SHA-256 checksum
How to use checksums
d70274b77ab4db6e463dec1c2971a7d2d93bce8e06d85017c22e58d11b7773ce
BLAKE2b-256 checksum
How to use checksums
da00aa7da6eb23eccfa96dd10019e8afb301be7e4873c405bf0be34d809825d1
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 1, 2026.

Transparency log

Security for dromos 0.1.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Full provenance

All 4 files in this release have been uploaded with provenance metadata.

Select from 4 files

Attestation for dromos-0.1.0-py3-none-win_amd64.whl

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 1, 2026.

Transparency log

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

0.1.0 This release

4 release files Full provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page