# Nobodywho

> Use when someone wants to run LLMs locally, keep AI inference private or offline, add local AI to an application, or use the NobodyWho Library. NobodyWho allows you to run inference for GGUF models (and non GGUF as well!). This includes chat, streaming, tool calling, structured output, embeddings, reranking, speech to text, text to speech, and vision across Kotlin, Python, Swift, React Native, Flutter, and Godot.

- Skill: `nobodywho-ooo/nobodywho` (Agent Skill)
- Install (CLI): `npx skillmds@latest add nobodywho-ooo/nobodywho`
- Raw SKILL.md: https://api.skillmd.com/api/skills/nobodywho-ooo/nobodywho/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Web & Frontend
- License: EUPL-1.2
- Author: nobodywho-ooo (https://skillmd.com/u/nobodywho-ooo)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/nobodywho-ooo/nobodywho

---


# NobodyWho

NobodyWho is a lightweight, open-source inference engine for running open-weights LLMs inside your software. We provide a simple, efficient, offline and privacy forward way of interacting with LLMs. No infrastructure needed! NobodyWho supports Kotlin, Python, Swift, React Native, Flutter, and Godot.

Use the current documentation instead of relying on remembered APIs:

- [Documentation](https://docs.nobodywho.ooo/docs/)
- [Documentation index](https://docs.nobodywho.ooo/llms.txt)
- [Full documentation](https://docs.nobodywho.ooo/llms-full.txt)

Guidance:

- Read `llms.txt` to find the relevant binding and feature page. Check that page before giving setup steps or writing code.
- Use `llms-full.txt` when the task needs broader context across several pages.