MLX

experimentalai

Apple Silicon native text generation via a local mlx_lm server

pip install chp-adapter-mlx

Auto-discovered through the chp.adapters entry point — no host config needed.

Capabilities

What this adapter exposes.

chatv1.0.0

chp.adapters.mlx.chat

generatev1.0.0

chp.adapters.mlx.generate

list_modelsv1.0.0

List models served by the local mlx_lm server (OpenAI /v1/models), via chp.adapters.http.

chp.adapters.mlx.list_models

start_serverv1.0.0

chp.adapters.mlx.start_server

statusv1.0.0

chp.adapters.mlx.status

stop_serverv1.0.0

Stop the local mlx_lm server running on a port (SIGTERM the tracked pid).

chp.adapters.mlx.stop_server