kubectl for local LLMs

Ollama, llama.cpp, LM Studio, MLX — pick two and you already have a fragmented stack. inferctl is the one place that knows what's actually running.

A local inference control plane. Inspect, route across, and coordinate local backends — Ollama, llama.cpp, OpenAI-compatible, LM Studio, MLX — from one command. It explains your stack; it doesn't run inference.

Try inferctl doctor.

Docs →

Source release: go install github.com/inferctl/inferctl/cmd/inferctl@latest