actop — Apple Silicon performance monitor

Whole-chip telemetry, no sudo

actop reads Apple Silicon power, frequency, and residency metrics directly from IOReport via Python ctypes — the same library powermetrics uses, minus the sudo, subprocesses, and temp files.

▮CPU · GPU · ANE

Per-cluster and per-core utilization, DVFS P-state frequency, and power for the P-CPU, E-CPU, GPU, and Neural Engine.

▮Memory bandwidth

Live GB/s against the SoC's peak, with a bandwidth-saturation alert and a MEM-BOUND indicator.

▮Thermals & throttling

CPU/GPU die temperatures from the Apple SMC and the macOS thermal state, with a THROTTLING indicator.

▮Per-process power

A watt-attributed PWR column — per-process power and energy attribution, unique among the sudoless *top tools.

▮Programmable API

Monitor / Profiler with to_pandas() — instrument your own LLM / MLX / CoreML runs from Python.

▮SoC-aware scaling

16 built-in M1–M4 profiles with reference wattage and bandwidth for stable, cross-session chart scaling.

Install in one line

Then run actop.

Homebrew recommended

brew tap binlecode/actop
brew install binlecode/actop/actop

uv non-Homebrew

uv tool install \
  git+https://github.com/binlecode/actop.git

pip

pip install \
  git+https://github.com/binlecode/actop.git

Profile your own workloads

Wrap any workload to get a pandas frame of power, frequency, residency, and cumulative session energy — no TUI needed.

from actop import Profiler

with Profiler() as p:
    run_my_inference()          # your workload

df = p.to_pandas()  # rows = samples; cols = power/freq/residency/energy

actop.