What is localai-apps?

A guide for building interactive apps inside LocalAI as a Page: a single HTML file that LocalAI displays in its Pages area. It covers apps such as trackers, forms, dashboards, games and calculators.

Use it to build tools people can use inside LocalAI, including lists, planners, forms, timers and other interactive pages.

It prevents an interactive request from being implemented as an unrelated Python, Node or desktop program. It also explains when a Page or a Home widget is the right choice.

localai-apps — Skill for Claude Code and Codex by mudler/LocalAI

About the project

LocalAI is an inference server that runs language, vision, voice, image, and video models through compatible APIs on local hardware. It is used to operate models privately across different hardware, including CPU-only systems, and supports applications, agents, and multi-user services. The catalogue contains instructions for using LocalAI.

mudler/LocalAI · 50,218 stars · on GitHub · localai.io

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.

Any agent

npx skills add mudler/LocalAI --skill localai-apps

Clone the repo

git clone --depth 1 https://github.com/mudler/LocalAI

Made for: Claude Code, Codex.

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/skills/mudler/localai/localai-apps/github.svg)](https://agentmods.dev/skills/mudler/localai/localai-apps)

Your own site

<a href="https://agentmods.dev/skills/mudler/localai/localai-apps"><img src="https://agentmods.dev/badge/skills/mudler/localai/localai-apps/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/mudler/localai/localai-apps"><img src="https://agentmods.dev/badge/skills/mudler/localai/localai-apps.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,843 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00049	$0.03843
Opus 5.5	$0.00020	$0.01537
Sonnet 5.5	$0.00010	$0.00769
Haiku 4.5	$0.00005	$0.00384

Measured 4d ago against content hash 34fd15ab8b62, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

localai-apps 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.

core/services/studio/builtinskills/tree/localai-apps/SKILL.md · 235 lines

How it starts

The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Apps in LocalAI are Pages

Do the work with files, but talk to the user in plain words: say what changed ("I saved your shortcuts", "I added a Reading list page", "Home now shows your open tasks"), not file names, folders, formats or JSON. Name a file only if the user named it or asks where something is, or when you give them a file as a result (a document they asked for).

LocalAI has its own app format: a Page. It is one HTML file in the user's home that LocalAI shows under Pages in the sidebar. The user can pin it and (with a shared folder) share it. Unless the user names a language or a runtime, "make me an app" means a Page. Do not start a Python, Node or desktop program for it.

Decide

The user wants	Do
An interactive thing to use here: tracker, to-do list, dashboard, form, game, calculator, planner, converter, timer	A Page (this skill)
The same, refreshed on a schedule or when a file arrives	A Page plus a trigger: load the `localai-workspace` skill, section "Updates on a schedule"
A Home widget (a list or a number)	The `localai-workspace` skill, not a Page
A page that should also show on Home	A Page with a `widget` block and a compact mode (section "On Home"), then the `localai-workspace` skill to add the tile
A real program: a script, a service, a CLI, something to install or deploy	Write that program as asked. First check the `Commands:` line of this chat: if nothing here runs commands, say so and give the files to run elsewhere
Data from the web	A Page cannot reach the network. Get the data with your web tools and write it to a file next to the page; the page reads it with `fetch('data.json')`

If the user asked explicitly for Python, Node or another language, do that and skip this skill.

A script, test data or a draft that you make on the way goes in the chat's work folder that the prompt names (/workspace/home/Chats/<chat>/work/); the page folder holds only the page and its data.

What a Page is

Read the full file on GitHub · 235 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.

4d ago First seen · 235 lines · 49 tokens per session scan A 34fd15ab8b62

Subscribe to this mod's changes

localai-apps is a skill published in the GitHub repository mudler/LocalAI (50,218 stars, last pushed yesterday), licensed MIT. It adds 49 tokens to every session and 3,843 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-11-02.

LLM Productivity ai api llama stable-diffusion tts

localai-apps next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
localai-appsmudler/LocalAI	Skill	50k	yesterday	MIT	A	49	Claude Code, Codex
meeting-transcript-to-action-itemsskrun-dev/skrun	Skill	209	1mo ago	MIT	A	90	Claude Code, Codex
support-systemshelixml/helix	Skill	829	yesterday	none	A	60	Claude Code, Codex
relay-tipsAetherCore-Dev/relay-radar	Skill	150	4d ago	none	A	63	Claude Code
apple-notesNousResearch/hermes-agent	Skill	261k	today	MIT	A	17	Claude Code, Codex
sglang-diffusion-cache-ditsgl-project/sglang	Skill	39k	today	Apache-2.0	A	161	Claude Code
obsidianNousResearch/hermes-agent	Skill	261k	today	MIT	A	19	Claude Code, Codex