Skip to content
Agentmart
Submit a tool

local-llm-chat

Chat with the on-device local LLM running on a Zettlab NAS via the zettos-ai engine (fully private/offline).

Skill by Xianleewu

IndexedMIT★ 3
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/xianleewu-local-llm-chat

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Chat with the on-device local LLM running on a Zettlab NAS via the zettos-ai engine (fully private/offline). Use when the user wants to query their device's local LLM, run an offline chat or summary, or test the local AI engine's text generation. Triggers on "local LLM", "device chat", "offline model", "本地大模型", "离线对话", "设备上的模型".

Use cases: testing, ml

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/local-llm-chat

What's inside

Skill name
local-llm-chat
Description
Chat with the on-device local LLM running on a Zettlab NAS via the zettos-ai engine (fully private/offline). Use when the user wants to query their device's local LLM, run an offline chat or summary, or test the local AI engine's text generation. Triggers on "local LLM", "device chat", "offline model", "本地大模型", "离线对话", "设备上的模型".
License
MIT
Instructions
21 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (2)

  • SKILL.md
  • run.py

SKILL.md (first lines)

# local-llm-chat

用设备上的本地 LLM 对话(经 zettos-ai 引擎,数据不出设备)。

## 前提
- `pip install -e <helper-repo>/sdk`
- `export ZETTOS_AI_BASE_URL=http://<DEVICE_IP>:5000`(默认 `127.0.0.1:5000`)
- 设备上已加载一个 LLM 实例(不确定就先用 `local-engine-admin` 查 status / 加载)

## 用法

运行本 skill 目录下的 `run.py`:

```bash
python run.py <LLM_INSTANCE_ID> "你的问题"            # 同步,一次返回
python run.py --stream <LLM_INSTANCE_ID> "你的问题"   # 流式,逐 token
```

若用户没给 instance_id,先用 `local-engine-admin` 的 `status` 找出 model_type 为 `llm` 的实例 id。

From Xianleewu/zettos-ai-engine-helper, MIT.

More from Xianleewu/zettos-ai-engine-helper

Signals

Stars
3
Forks
0
Open issues
0
Last commit (this folder)
Jun 11, 2026 (4 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Repository
github.com/Xianleewu/zettos-ai-engine-helper
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from Xianleewu

Cite this page

local-llm-chat skill. Agent Mart. https://agentmart.dev/skills/xianleewu-local-llm-chat (last updated 2026-10-24)