nobodywho

name	nobodywho
description	Use when working with NobodyWho local LLM inference docs, APIs, model selection, GGUF model loading, chat, streaming, tool calling, structured output, embeddings/RAG, or NobodyWho integrations for Python, Kotlin, Swift, React Native, Flutter, or Godot.

NobodyWho

NobodyWho is a local-first inference engine for running GGUF/open-weight LLMs inside apps.

Always browse the current docs

Do not rely on remembered or hardcoded API details. Before giving implementation guidance or writing code, read the relevant current documentation:

• Docs index: https://docs.nobodywho.ooo/llms.txt
• Full docs: https://docs.nobodywho.ooo/llms-full.txt
• Overview: https://docs.nobodywho.ooo/docs/
• Model selection: https://docs.nobodywho.ooo/docs/model-selection

Platform docs:

• Python: https://docs.nobodywho.ooo/python/
• Kotlin: https://docs.nobodywho.ooo/kotlin/
• Swift: https://docs.nobodywho.ooo/swift/
• React Native: https://docs.nobodywho.ooo/react-native/
• Flutter: https://docs.nobodywho.ooo/flutter/
• Godot: https://docs.nobodywho.ooo/godot/install

Repos and examples:

• Main repo: https://github.com/nobodywho-ooo/nobodywho
• GitHub org: https://github.com/nobodywho-ooo
• Swift starter: https://github.com/nobodywho-ooo/swift-starter-example
• React Native starter: https://github.com/nobodywho-ooo/react-native-starter-example
• Flutter starter: https://github.com/nobodywho-ooo/flutter-starter-example
• Electron starter: https://github.com/nobodywho-ooo/electron-starter-example
• Vision Pro example: https://github.com/nobodywho-ooo/NobodyWho-Vision-Pro
• Watch example: https://github.com/nobodywho-ooo/NobodyWho-Watch

Workflow

1. Identify the target platform and task.
2. Read the relevant current docs page(s), using llms.txt to discover pages.
3. If writing code, verify API names and installation steps from the docs or installed package/types.
4. Prefer links to source docs over copying volatile details into the answer.

Stable reminders

• NobodyWho runs local GGUF models; it is not a hosted LLM API.
• Chat, embeddings, reranking/cross-encoding, multimodal, tool calling, and structured output may need different model capabilities.
• Remote model loading and cache behavior can vary by platform; check the platform docs.
• For private/gated Hugging Face models, check the docs for the current authentication pattern.