xybrid-ai / xybrid

English · 简体中文 Xybrid Run LLMs, ASR, and TTS natively in apps and games. Rust core · iOS · Android · Flutter · Unity Private, offline, no cloud required. Documentation · SDKs · Models · Join Discord · Issues [![Website][website-shield]][website-url] [![Discord][discord-shield]][discord-url] [![Twitter][twitter-shield]][twitter-url] [![License][license-shield]][license-url] [![Build][build-shield]][build-url] [![Stars][stars-shield]][stars-url] [![Release][release-shield]][release-url] [![Release Date][release-date-shield]][release-url] [![pub.dev][pubdev-shield]][pubdev-url] [![Maven Central][maven-shield]][maven-url] [website-shield]: https://img.shields.io/badge/xybrid.ai-4285F4?style=flat [website-url]: https://www.xybrid.ai/ [discord-shield]: https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fdiscord.com%2Fapi%2Finvites%2FYhFHHkhbad%3Fwith_counts%3Dtrue&query=%24.approximate_member_count&logo=discord&logoColor=white&label=Discord&color=5865F2&suffix=%20members [discord-url]: https://discord.gg/YhFHHkhbad [twitter-shield]: https://img.shields.io/twitter/follow/xybrid_ai [twitter-url]: https://x.com/xybrid_ai [license-shield]: https://img.shields.io/badge/License-Apache_2.0-blue.svg?style=flat [license-url]: https://opensource.org/licenses/Apache-2.0 [build-shield]: https://img.shields.io/github/actions/workflow/status/xybrid-ai/xybrid/ci.yml?branch=master&style=flat [build-url]: https://github.com/xybrid-ai/xybrid/actions [stars-shield]: https://img.shields.io/github/stars/xybrid-ai/xybrid?style=flat [stars-url]: https://github.com/xybrid-ai/xybrid/stargazers [release-shield]: https://img.shields.io/github/v/release/xybrid-ai/xybrid?style=flat&sort=semver [release-url]: https://github.com/xybrid-ai/xybrid/releases [release-date-shield]: https://img.shields.io/github/release-date/xybrid-ai/xybrid?style=flat [pubdev-shield]: https://img.shields.io/pub/v/xybrid_flutter?style=flat&label=pub.dev [pubdev-url]: https://pub.dev/packages/xybrid_flutter [maven-shield]: https://img.shields.io/maven-central/v/ai.xybrid/xybrid-kotlin?style=flat&label=Maven%20Central [maven-url]: https://central.sonatype.com/artifact/ai.xybrid/xybrid-kotlin      Start Here | Goal | Path | |------|------| | Fastest demo (2 min) | Download CLI → | | Build a mobile or desktop app | Flutter SDK → | | Add AI NPCs to your game | Unity SDK → and try the 3D tavern demo | | Android native | Kotlin SDK → | | Rust / embedded | Core crate → | --- SDKs Xybrid is a **Rust-powered runtime** with native bindings for every major platform. | SDK | Platforms | Install | Status | Sample | |-----|-----------|---------|--------|--------| | **Flutter** | iOS, Android, macOS, Linux, Windows | pub.dev | Available | README | | **Unity** | macOS, Windows, Linux, iOS, Android | See below | Available | Unity 3D AI tavern | | **Swift** | iOS, macOS | Swift Package Manager | Coming Soon | README | | **Kotlin** | Android | Maven Central | Available | README | | **CLI** | macOS, Linux, Windows | Download binary | Available | — | | **Rust** | All | / | Available | — | Every SDK wraps the same Rust core — identical model support and behavior across all platforms. Install **Unity** — Package Manager → Add from git URL: > The branch contains pre-built native libraries for all platforms. > To pin a specific version: **Flutter** — add to your : **Kotlin (Android)** — add to your : --- Quick Start See each SDK's README for platform-specific setup: Flutter · Unity · Swift · Kotlin · Rust Single Model Run a model in one line from the CLI, or three lines from any SDK: **CLI:** **Flutter:** **Kotlin:** **Swift:** **Unity (C#):** **Rust:** Pipelines Chain models together — build a voice assistant in 3 lines of YAML: **CLI:** **Flutter:** **Kotlin:** **Swift:** **Unity (C#):** **Rust:** --- Supported Models All models run entirely on-device. No cloud, no API keys required. Browse the full registry with . Start with these | Model | Type | Params | Why start here | |-------|------|--------|----------------| | **SmolLM2 360M** | LLM | 360M | Best quality-to-size ratio for any device | | **Kokoro 82M** | TTS | 82M | High-quality speech, 24 voices, fast | | **Whisper Tiny** | ASR | 39M | Accurate multilingual transcription | Speech-to-Text | Model | Params | Format | Description | |-------|--------|--------|-------------| | Whisper Tiny | 39M | SafeTensors | Multilingual transcription (Candle runtime) | | Wav2Vec2 Base | 95M | ONNX | English ASR with CTC decoding | Text-to-Speech | Model | Params | Format | Description | |-------|--------|--------|-------------| | Kokoro 82M | 82M | ONNX | High-quality, 24 natural voices | | KittenTTS Nano | 15M | ONNX | Ultra-lightweight, 8 voices | Language Models | Model | Params | Format | Description | |-------|--------|--------|-------------| | Gemma 3 1B | 1B | GGUF Q4_K_M | Google's mobile-optimized LLM | | Llama 3.2 1B | 1B | GGUF Q4_K_M | Meta's general purpose, 128K context | | Qwen 2.5 0.5B | 500M | GGUF Q4_K_M | Compact on-device chat | | Qwen 3.5 0.8B | 800M | GGUF Q4_K_M | Latest Qwen with reasoning (thinking mode) | | Qwen 3.5 2B | 2B | GGUF Q4_K_M | Larger Qwen 3.5 with extended reasoning | | SmolLM2 360M | 360M | GGUF Q4_K_M | Best tiny LLM, excellent quality/size ratio | Coming Soon | Model | Type | Params | Priority | Status | |-------|------|--------|----------|--------| | Phi-4 Mini | LLM | 3.8B | P2 | Spec Ready (first multi-quant: Q4, Q8, FP16) | | Qwen3 0.6B | LLM | 600M | P2 | Planned | | Trinity Nano | LLM (MoE) | 6B (1B active) | P2 | Planned | | LFM2 700M | LLM | 700M | P2 | Planned | | Nomic Embed Text v1.5 | Embeddings | 137M | P1 | Blocked (needs Tokenize/MeanPool steps) | | LFM2-VL 450M | Vision | 450M | P2 | Planned | | Whisper Tiny CoreML | ASR | 39M | P2 | Planned | | Qwen3-TTS 0.6B | TTS | 600M | P2 | Blocked (needs custom SafeTensors runtime) | | Chatterbox Turbo | TTS | 350M | P3 | Blocked (needs ModelGra…