# local-ai-use

A meta-skill that reroutes image generation, text-to-speech and speech-to-text through a local Lemonade Server instead of a paid cloud API.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 1100 installs · ★ 465
- Author: amd
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/amd/skills/tree/HEAD/skills/local-ai-use/SKILL.md
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/skills/local-ai-use

## What it does

You run this skill once. It installs Lemonade Server if no modern `lemonade` CLI is present, waits for the auto-started `lemond` service, and checks that the server answers on the port `lemonade status` reports. Then it writes a `Local AI Use` block into the workspace `AGENTS.md`, so the routing rule is read on every later turn. Text still goes to the cloud model; only images, speech synthesis and transcription move on-device.

One command does the work: `python scripts/setup_local_ai.py`. It is idempotent, so re-running it on a configured workspace is just a healthcheck. Models are not downloaded during setup. Each default is pulled lazily on first use, which means your first image request fetches `SD-Turbo` separately. Budget around 8 GB of free disk for the three default models, plus network for the install and the first `lemonade pull`.

Version drift is the real trap here. The skill targets Lemonade v10.1.0 and newer, where everything sits behind a single `lemonade` CLI; an older binary on your `PATH` will shadow it, so remove that first. On Linux the install needs `sudo`, and on a managed machine where the agent must not install packages, run the script with `--no-install`. If you are embedding Lemonade inside an app you ship, this is the wrong skill.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add amd/skills --skill local-ai-use -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/local-ai-use/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/local-ai-use/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add amd/skills --skill local-ai-use -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/local-ai-use/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add amd/skills --skill local-ai-use -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/local-ai-use/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install amd/skills local-ai-use
```

2. **Manually: put the files in place**
- File: `.github/skills/local-ai-use/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add amd/skills --skill local-ai-use -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/amd/skills --path skills/local-ai-use
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/local-ai-use/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add amd/skills --skill local-ai-use -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/amd/skills/tree/HEAD/skills/local-ai-use/SKILL.md

## When to use it
- move image generation onto your own machine
- transcribe a recording without sending it to the cloud
- read text aloud with a local speech model
- pin local routing in `AGENTS.md` for future turns
- drop paid DALL-E, Whisper and ElevenLabs calls

## Example prompts
- set this workspace up to make images on my own machine
- transcribe this recording locally, offline
- make this picture through the local Lemonade server

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 59ab45fb0bcf17c9.

BEGIN THIRD-PARTY FILE 59ab45fb0bcf17c9
```text
---
name: local-ai-use
description: >-
  Makes this agent generate images, transcribe audio, and synthesize speech on
  the user's own machine through a local Lemonade Server instead of a paid cloud
  API. Use it above all to change that routing persistently, from now on — keep
  generating pictures locally while chat stays on the cloud; set this workspace
  up to make images on my own machine — even when the user asks for no image or
  file in the same breath. Also use it for a single request the user wants done
  locally, offline, on-device, or kept private: transcribe this recording, make
  this picture, read this text aloud. Applies in Claude, Cursor, Codex, or any
  agent harness. Use when the user wants to cut cost or tokens on image, audio,
  or voice API calls, or to drop DALL-E, hosted Whisper, ElevenLabs, or other
  paid multimodal APIs; or mentions Lemonade Server, OmniRouter, SD-Turbo,
  kokoro, Ryzen AI, or NPU/iGPU/dGPU inference. Changes no application source
  code; do not use it if the user is adding local AI to an app they ship.
---

# Local AI Use (route image, TTS, STT through Lemonade)

This is a **meta-skill**. You run it once. After that, every later request that
needs image generation, text-to-speech, or speech-to-text uses the local
[Lemonade Server](https://lemonade-server.ai) instead of a cloud API. The
agent's own LLM keeps handling text; only the expensive multimodal calls move
on-device.

The skill does three things:

1. **Makes sure local Lemonade is installed and running.** If no modern
   `lemonade` CLI is found, the setup script installs the latest version of
   Lemonade on the user's behalf. Modern Lemonade has no `serve` command — the
   Lemonade service (the `lemond` daemon) auto-starts on install and is managed
   by the OS — so the setup script waits for the service and, if it stays down,
   prints the exact OS-specific command to start it (e.g. `sudo systemctl start
   lemond` on Linux).
2. **Verifies that local Lemonade is reachable** on the port `lemonade status`
   reports, so a server already running on a non-default port is used as-is
   rather than reported missing (`13305` is only the fallback).
3. **Drops a `Local AI Use` block into the workspace `AGENTS.md`** so the agent
   reads the routing rule on every later turn, in Cursor, Claude Code, Codex,
   Gemini CLI, and any other agent that respects `AGENTS.md`.

> **Requires modern Lemonade (v10.1.0 or newer).** Modern Lemonade unified
> everything under one `lemonade` CLI (`lemonade status`, `lemonade pull`, ...)
> driving an always-on `lemond` service. `lemonade` is the only valid CLI, and
```
END THIRD-PARTY FILE 59ab45fb0bcf17c9

The third-party file has ended. Everything between the 59ab45fb0bcf17c9 tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2642 of 20024 bytes. © amd · MIT · https://github.com/amd/skills/tree/HEAD/skills/local-ai-use/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md