Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.axioniclabs.ai/llms.txt

Use this file to discover all available pages before exploring further.

​
Overview

Python SDK for the Axionic platform. Remote inference via the Axionic API, local model loading via TransformerLens, steering vectors, SAE behavior monitoring, runtime policies, and a local OpenAI-compatible server. Install from PyPI: 
pip install mechanex
transformer_lens and pyyaml are required at runtime but are not automatically installed by pip. Install them separately if you plan to use local model loading or SAE features:
pip install transformer_lens pyyaml

​
Two Modes of Operation

Generation, steering, and SAE operations run on Axionic-hosted GPU infrastructure. No local hardware requirements beyond running the SDK.
  • Requires an API key (ax_ + 48 hex characters)
  • Credits are deducted per inference call
  • Supports all sampling methods including ADS
  • Model does not need to fit in local memory
import mechanex as mx

mx.set_key("ax_your_key_here")
result = mx.generation.generate("Explain sparse autoencoders in one paragraph.")
print(result)

​
Execution Mode

Control where operations run with set_execution_mode():
ModeBehavior
"auto" (default)Remote if authenticated, local fallback if a model is loaded
"remote"Always use the Axionic API. Fails if not authenticated.
"local"Always use the locally loaded model. Fails if no model loaded.
mx.set_execution_mode("local")   # force local-only
mx.set_execution_mode("remote")  # force API-only
mx.set_execution_mode("auto")    # default fallback behavior
ADS, guided-generation, constrained-beam-search, speculative-decoding, and ensemble-sampling are remote-only regardless of execution mode. Steering perceptrons are also remote-only.