# Xybrid

> Xybrid runs LLMs, speech-to-text (ASR), and text-to-speech (TTS) natively
> on-device across Flutter, Swift, Kotlin, Unity, and Rust — private, offline,
> no cloud required. Models load from a registry by id and download on first use.

## Agent setup

- [Agent setup prompt](https://www.xybrid.ai/agent-setup/prompt.md): Paste this URL into a coding agent (Claude Code, Codex, Cursor, ...) to install the CLI, skills, and an SDK and self-configure a project.

## Docs

- [Documentation](https://docs.xybrid.dev): Full documentation.
- [Quickstart](https://docs.xybrid.dev/docs/quickstart): Install an SDK and run your first model.
- [Model registry](https://www.xybrid.ai/models): Browse available ASR, TTS, and LLM models by id.
- [Sitemap](https://www.xybrid.ai/sitemap.xml): XML sitemap for full page discovery.

## Source

- [GitHub](https://github.com/xybrid-ai/xybrid): Core runtime, CLI, and SDK bindings.
- [Discord](https://discord.gg/YhFHHkhbad): Community and support.