A command that searches your Mac for running language-model inference engines, which are programs that generate text from models, and reports their addresses and versions.

Use it to discover supported engines, check which models are running, scan a particular address, or find engines using non-standard ports.

It finds engines automatically instead of making you remember which programs are running or which ports they use.

detect.de — Command for coding agents by druide67: A command that searches your Mac for running language-model…

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add commands/druide67/asiai/detect.de

Clone the repo

git clone --depth 1 https://github.com/druide67/asiai

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/commands/druide67/asiai/detect.de.svg)](https://agentmods.dev/commands/druide67/asiai/detect.de)

Your own site

<a href="https://agentmods.dev/commands/druide67/asiai/detect.de"><img src="https://agentmods.dev/badge/commands/druide67/asiai/detect.de.svg" alt="Measured on agentmods" height="20"></a>

Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 634 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00036	$0.00634
Opus 5	$0.00018	$0.00317
Sonnet 5	$0.00007	$0.00127
Haiku 4.5	$0.00004	$0.00063

Measured 3d ago against content hash 5ca46097cc1c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

detect.de scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

docs/commands/detect.de.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

asiai detect

Automatische Erkennung von Inferenz-Engines über eine 3-Schichten-Kaskade.

Verwendung

asiai detect                      # Auto-Erkennung (3-Schichten-Kaskade)
asiai detect --url http://host:port  # Nur bestimmte URL(s) scannen

Ausgabe

Detected engines:

  ● ollama 0.17.4
    URL: http://localhost:11434

  ● lmstudio 0.4.5
    URL: http://localhost:1234
    Running: 1 model(s)
      - qwen3.5-35b-a3b  MLX

  ● omlx 0.9.2
    URL: http://localhost:8800

Funktionsweise: 3-Schichten-Erkennung

asiai verwendet eine Kaskade von drei Erkennungsschichten, von der schnellsten zur gründlichsten:

Schicht 1: Konfiguration (schnellste, ~100ms)

Liest ~/.config/asiai/engines.json — bei vorherigen Durchläufen entdeckte Engines. Dies findet Engines auf nicht standardmäßigen Ports (z.B. oMLX auf 8800) ohne erneutes Scannen.

Schicht 2: Port-Scan (~200ms)

Scannt Standardports plus einen erweiterten Bereich:

Port	Engine
11434	Ollama
1234	LM Studio
8080	mlx-lm oder llama.cpp
8000-8009	oMLX oder vllm-mlx
52415	Exo

Schicht 3: Prozesserkennung (Fallback)

Verwendet ps und lsof, um Engine-Prozesse auf beliebigen Ports zu finden. Findet Engines auf völlig unerwarteten Ports.

Automatische Persistierung

Jede in Schicht 2 oder 3 entdeckte Engine wird automatisch in der Konfigurationsdatei (Schicht 1) für schnellere Erkennung beim nächsten Mal gespeichert. Auto-entdeckte Einträge werden nach 7 Tagen Inaktivität bereinigt.

Wenn mehrere Engines einen Port teilen (z.B. mlx-lm und llama.cpp auf 8080), verwendet asiai API-Endpoint-Probing, um die richtige Engine zu identifizieren.

Explizite URLs

Bei --url werden nur die angegebenen URLs gescannt. Es wird keine Konfiguration gelesen oder geschrieben — nützlich für einmalige Prüfungen.

asiai detect --url http://192.0.2.10:11434,http://localhost:8800

Siehe auch

config — Persistente Engine-Konfiguration verwalten

Read the full file on GitHub · 74 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

3d ago First seen · 74 lines · 36 tokens per session scan A 5ca46097cc1c

Subscribe to this mod's changes

detect.de is a command published in the GitHub repository druide67/asiai (11 stars, last pushed 4d ago), licensed Apache-2.0. It adds 36 tokens to every session and 634 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Apple Silicon Data and AI LLM benchmark cli inference lm-studio

detect.de