A Mac command that finds locally running large-language-model inference engines, which are programs that run AI models.

It detects engines through saved configuration, port scans, or process checks, and can scan specific URLs.

It saves you from checking configuration files, network ports, and running processes manually to find available engines.

detect.ko — Command for coding agents by druide67: A Mac command that finds locally running large-language-model inference…

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.ko

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.ko.svg)](https://agentmods.dev/commands/druide67/asiai/detect.ko)

Your own site

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

Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 669 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin 100% copy Near-identical to another mod 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	$0.00040	$0.00669
Opus 5	$0.00020	$0.00334
Sonnet 5	$0.00008	$0.00134
Haiku 4.5	$0.00004	$0.00067

Measured 4d ago against content hash 42ec7e518570, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

detect.ko 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 4d 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.

Origin

This is a copy

100% identical to detect.ja — 50 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

docs/commands/detect.ko.md · 74 lines

What it actually says

asiai detect

3계층 캐스케이드를 사용하여 실행 중인 추론 엔진을 자동 감지합니다.

사용법

asiai detect                      # 자동 감지 (3계층 캐스케이드)
asiai detect --url http://host:port  # 지정 URL만 스캔

출력

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

작동 방식: 3계층 감지

asiai는 가장 빠른 것에서 가장 철저한 것까지 3개 감지 레이어의 캐스케이드를 사용합니다:

레이어 1: 설정 (가장 빠름, ~100ms)

~/.config/asiai/engines.json 읽기 — 이전 실행에서 감지된 엔진. 비표준 포트(예: oMLX의 8800)의 엔진을 재스캔 없이 감지.

레이어 2: 포트 스캔 (~200ms)

기본 포트와 확장 범위를 스캔:

포트	엔진
11434	Ollama
1234	LM Studio
8080	mlx-lm 또는 llama.cpp
8000-8009	oMLX 또는 vllm-mlx
52415	Exo

레이어 3: 프로세스 감지 (폴백)

ps와 lsof를 사용하여 임의의 포트에서 수신 대기 중인 엔진 프로세스를 찾습니다. 완전히 예상치 못한 포트에서 실행되는 엔진도 감지합니다.

자동 저장

레이어 2 또는 3에서 감지된 엔진은 다음 감지를 빠르게 하기 위해 설정 파일(레이어 1)에 자동 저장됩니다. 자동 감지 항목은 7일 비활성 후 정리됩니다.

여러 엔진이 포트를 공유하는 경우(예: mlx-lm과 llama.cpp의 8080), asiai는 API 엔드포인트 프로빙으로 올바른 엔진을 식별합니다.

명시적 URL

--url 사용 시 지정된 URL만 스캔됩니다. 설정 읽기/쓰기가 수행되지 않습니다 — 일회성 확인에 유용합니다.

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

참고

config — 영구적인 엔진 설정 관리

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.

4d ago First seen · 74 lines · 40 tokens per session scan A 42ec7e518570

Subscribe to this mod's changes

detect.ko is a command published in the GitHub repository druide67/asiai (11 stars, last pushed 5d ago), licensed Apache-2.0. It adds 40 tokens to every session and 669 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to detect.ja, differing in 50 lines, and is treated as a copy.

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

detect.ko

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

This is a copy

What it actually says

asiai detect

사용법

출력

작동 방식: 3계층 감지

레이어 1: 설정 (가장 빠름, ~100ms)

레이어 2: 포트 스캔 (~200ms)

레이어 3: 프로세스 감지 (폴백)

자동 저장

명시적 URL

참고

What this file has done since we first saw it

Other commands, from other repositories

perfup

integrate-pipeline

netllm-connect

netllm-setup

netllm-swarm

/opsx-explore