diff --git a/yuy-chat-README.md b/yuy-chat-README.md
new file mode 100644
index 0000000..2a5f3a5
--- /dev/null
+++ b/yuy-chat-README.md
@@ -0,0 +1,1244 @@
+
+
+
+
+
+
+
+
+# Beautiful TUI Chat for Local AI Models
+
+**Talk to Yuuki models in your terminal.**
+**Streaming responses. Conversation history. Zero cloud required.**
+
+
+
+
+
+
+
+
+
+
+
+
+
+[](LICENSE)
+
+[](https://www.rust-lang.org/)
+
+[](https://github.com/ratatui-org/ratatui)
+
+[](https://tokio.rs/)
+
+[](#platform-support)
+
+[](#platform-support)
+
+[](#platform-support)
+
+[](#platform-support)
+
+
+
+---
+
+
+
+
+
+|
+
+```
++--------------------------------------------------+
+| yuy-chat v0.1.0 Yuuki-best | Balanced |
++--------------------------------------------------+
+| |
+| You: Explain async/await in Rust |
+| |
+| Yuuki: async/await in Rust allows you to write |
+| asynchronous code that looks synchronous. The |
+| async keyword marks a function as returning a |
+| Future, and await suspends execution until the |
+| Future resolves... |
+| |
++--------------------------------------------------+
+| Message: _ |
++--------------------------------------------------+
+| Enter: Send | Ctrl+C: Menu | Ctrl+S: Save |
++--------------------------------------------------+
+```
+
+ |
+
+
+**A full chat experience in your terminal.**
+
+
+
+Select models interactively.
+Stream responses word by word.
+Save and reload conversations.
+Switch presets on the fly.
+
+All running locally on your machine.
+All powered by ratatui + Rust.
+
+ |
+
+
+
+
+
+
+
+
+
+## What is yuy-chat?
+
+
+
+
+
+**yuy-chat** is a terminal user interface (TUI) application for chatting with local AI models. Built with Rust and powered by [ratatui](https://github.com/ratatui-org/ratatui), it provides a polished, keyboard-driven interface for real-time conversations with Yuuki models -- without ever leaving the terminal.
+
+It connects to proven inference backends (**llama.cpp** and **llamafile**) and optionally to the **HuggingFace Inference API** for cloud-based generation. Model discovery, conversation management, preset switching, and streaming are all handled out of the box.
+
+yuy-chat is the companion tool to [yuy](https://github.com/YuuKi-OS/yuy) (the CLI for downloading and managing models). Together they form the complete local inference toolkit for the Yuuki project.
+
+
+
+---
+
+
+
+
+
+## Features
+
+
+
+
+
+
+
+
+
+Interactive Chat
+
+Real-time streaming responses displayed word by word. Multi-line input with Shift+Enter. Scrollable message history with keyboard navigation.
+
+
+
+Model Selector
+
+Auto-discovers `.gguf` and `.llamafile` models from your local directory. Navigate with arrow keys, select with Enter. Refresh without restarting.
+
+
+
+Conversation History
+
+Save conversations as JSON files. Load previous chats from a built-in conversation browser. Delete old sessions you no longer need.
+
+
+
+HuggingFace Cloud
+
+Optional API integration for cloud-based inference. Configure your HF token in the settings screen. Local and cloud models appear side by side in the selector.
+
+ |
+
+
+Generation Presets
+
+Three built-in modes -- Creative (0.8 temp), Balanced (0.6 temp), and Precise (0.3 temp). Cycle between them with a single keypress. Custom presets planned for v0.2.
+
+
+
+Settings Screen
+
+Configure models directory, HuggingFace token, default preset, history saving, and UI theme -- all from within the TUI.
+
+
+
+Cross-Platform
+
+Runs on Termux (Android), Linux, macOS, and Windows. Same binary, same interface, same experience. Mobile-first defaults for constrained hardware.
+
+
+
+Lightweight
+
+~8 MB binary. ~20 MB idle RAM. ~50 ms startup. Built with Rust for zero-overhead performance and memory safety.
+
+ |
+
+
+
+
+
+---
+
+
+
+
+
+## Installation
+
+
+
+
+
+### Prerequisites
+
+- [Rust](https://www.rust-lang.org/tools/install) 1.70 or later (1.75+ recommended)
+- An inference runtime: [llama.cpp](https://github.com/ggerganov/llama.cpp) or a `.llamafile` model
+- AI models in GGUF or Llamafile format (use [yuy](https://github.com/YuuKi-OS/yuy) to download them)
+
+
+
+### From Source
+
+```bash
+git clone https://github.com/YuuKi-OS/yuy-chat
+cd yuy-chat
+cargo build --release
+cargo install --path .
+```
+
+
+
+### Termux (Android)
+
+```bash
+pkg install rust git
+git clone https://github.com/YuuKi-OS/yuy-chat
+cd yuy-chat
+cargo build --release -j 1
+cargo install --path .
+```
+
+> **Note:** First compilation takes longer on ARM due to CPU constraints. Use `-j 1` to avoid thermal throttling. Incremental builds are fast (~10 sec).
+
+
+
+### Verify
+
+```bash
+yuy-chat --version
+```
+
+
+
+---
+
+
+
+
+
+## Quick Start
+
+
+
+
+
+```bash
+# 1. Get a model (using yuy CLI)
+yuy download Yuuki-best
+
+# 2. Install a runtime
+pkg install llama-cpp # Termux
+brew install llama.cpp # macOS
+
+# 3. Launch the chat
+yuy-chat
+```
+
+The interface opens in the model selector. Pick a model with arrow keys and press Enter. Start typing and hit Enter to send messages. That's it.
+
+
+
+---
+
+
+
+
+
+## Keyboard Reference
+
+
+
+
+
+### Model Selector
+
+| Key | Action |
+|:----|:-------|
+| `Up` / `k` | Previous model |
+| `Down` / `j` | Next model |
+| `Enter` | Select model |
+| `R` | Refresh model list |
+| `Q` | Quit |
+
+
+
+### Chat
+
+| Key | Action |
+|:----|:-------|
+| `Enter` | Send message |
+| `Shift+Enter` | New line |
+| `Ctrl+Enter` | Force send |
+| `Up` / `Down` | Scroll history (when input is empty) |
+| `Ctrl+C` | Open menu |
+| `Ctrl+L` | Clear chat |
+| `Ctrl+S` | Save conversation |
+| `Backspace` | Delete character |
+
+
+
+### Menu
+
+| Key | Action |
+|:----|:-------|
+| `1` | Change model |
+| `2` | Cycle preset |
+| `3` | Save conversation |
+| `4` | Load conversation |
+| `5` | Clear chat |
+| `6` | Settings |
+| `Q` / `Esc` | Back to chat |
+
+
+
+### Settings
+
+| Key | Action |
+|:----|:-------|
+| `Up` / `Down` | Navigate settings |
+| `Enter` | Edit setting |
+| `Esc` | Back to menu |
+
+
+
+---
+
+
+
+
+
+## Generation Presets
+
+
+
+
+
+| Preset | Temperature | Top P | Best For |
+|:-------|:------------|:------|:---------|
+| **Creative** | 0.8 | 0.9 | Stories, brainstorming, creative writing |
+| **Balanced** | 0.6 | 0.7 | General chat, explanations **(default)** |
+| **Precise** | 0.3 | 0.5 | Code, math, factual answers |
+
+Cycle presets during a chat session via `Ctrl+C` then `2`, or set a default in the configuration file.
+
+
+
+---
+
+
+
+
+
+## Supported Formats and Runtimes
+
+
+
+
+
+
+
+
+
+Model Formats
+
+| Format | Extension | Notes |
+|:-------|:----------|:------|
+| GGUF | `.gguf` | Recommended. Requires llama.cpp |
+| Llamafile | `.llamafile` | Self-executing. Zero dependencies |
+
+ |
+
+
+Inference Runtimes
+
+| Runtime | Type | Notes |
+|:--------|:-----|:------|
+| llama.cpp | Local subprocess | Default. Fast, CPU-optimized |
+| llamafile | Local executable | Bundled runtime + model |
+| HuggingFace API | Cloud HTTP | Optional. Requires token |
+
+ |
+
+
+
+
+
+yuy-chat auto-detects the appropriate runtime based on the selected model's format. For GGUF models, it searches for `llama-cli`, `llama`, or `main` binaries in PATH.
+
+
+
+---
+
+
+
+
+
+## HuggingFace Integration
+
+
+
+
+
+Cloud-based inference is optional. To enable it:
+
+1. Get a token from [huggingface.co/settings/tokens](https://huggingface.co/settings/tokens)
+2. Open Settings in yuy-chat (`Ctrl+C` then `6`)
+3. Navigate to "HuggingFace Token" and paste it
+
+Cloud models then appear in the selector alongside local models:
+
+```
+> Yuuki-best-q5.gguf 2.3 GB [Local]
+ Yuuki-3.7-q4.gguf 1.8 GB [Local]
+ Yuuki-best (via API) Cloud [HuggingFace]
+```
+
+| | Local | Cloud |
+|:--|:------|:------|
+| Speed | Faster (no network) | Depends on connection |
+| Privacy | 100% offline | Data sent to HF API |
+| Storage | Requires disk space | None |
+| Availability | Always | Requires internet |
+
+
+
+---
+
+
+
+
+
+## Configuration
+
+
+
+
+
+### Config File
+
+Location: `~/.config/yuy-chat/config.toml`
+
+```toml
+models_dir = "/home/user/.yuuki/models"
+default_preset = "Balanced"
+save_history = true
+theme = "Dark"
+
+# Optional
+# hf_token = "hf_xxxxxxxxxxxxx"
+```
+
+### Priority Order
+
+1. **TUI settings** -- changes made in the settings screen
+2. **Config file** -- `~/.config/yuy-chat/config.toml`
+3. **Defaults** -- sensible defaults based on platform detection
+
+
+
+### Directory Layout
+
+```
+~/.config/yuy-chat/
+ config.toml # configuration
+ conversations/ # saved chats
+ conversation-20260206-143022.json
+ conversation-20260206-150133.json
+
+~/.yuuki/models/ # models (shared with yuy CLI)
+ Yuuki-best/
+ yuuki-best-q4_0.gguf
+ Yuuki-3.7/
+ yuuki-3.7-q5_k_m.gguf
+```
+
+
+Platform-specific paths
+
+
+| Platform | Config path |
+|:---------|:------------|
+| Linux | `~/.config/yuy-chat/config.toml` |
+| macOS | `~/.config/yuy-chat/config.toml` |
+| Windows | `C:\Users\{user}\AppData\Roaming\yuy-chat\config.toml` |
+| Termux | `/data/data/com.termux/files/home/.config/yuy-chat/config.toml` |
+
+
+
+
+
+---
+
+
+
+
+
+## Architecture
+
+
+
+
+
+```
+ User
+ |
+ v
+ +-------------------------------------------------------------+
+ | yuy-chat (Rust) |
+ | |
+ | main.rs Entry point + event loop |
+ | | crossterm polling (100ms) |
+ | v |
+ | app.rs State machine |
+ | | ModelSelector | Chat | Menu | |
+ | | Settings | ConversationList |
+ | v |
+ | ui/ Rendering layer (ratatui) |
+ | | selector.rs, chat.rs, menu.rs, |
+ | | settings.rs, conversations.rs |
+ | v |
+ | models/ Business logic |
+ | scanner.rs, runtime.rs, hf_api.rs |
+ +-------+----------------------------+-----------------------+
+ | |
+ v v
+ +------------------+ +-------------------+
+ | External APIs | | Local Storage |
+ | HuggingFace | | ~/.config/ |
+ | Inference API | | ~/.yuuki/models/ |
+ +--------+---------+ +-------------------+
+ |
+ v
+ +--------------------------------+
+ | Inference Runtimes |
+ | llama.cpp | llamafile |
+ +--------------------------------+
+```
+
+
+
+### Source Layout
+
+```
+yuy-chat/
+ Cargo.toml # manifest and dependencies
+ README.md
+ TECHNICAL.md # full technical specification
+ src/
+ main.rs # entry point, event loop, terminal setup
+ app.rs # application state, message handling
+ config.rs # config load/save, presets, themes
+ conversation.rs # message storage, JSON persistence
+ models/
+ mod.rs # module declarations
+ scanner.rs # auto-discovery of local + HF models
+ runtime.rs # subprocess management, streaming
+ hf_api.rs # HuggingFace Inference API client
+ ui/
+ mod.rs # module declarations
+ selector.rs # model selection screen
+ chat.rs # main chat interface
+ menu.rs # options menu
+ settings.rs # configuration screen
+ conversations.rs # saved conversations browser
+```
+
+
+
+### Data Flow
+
+```
+User Input --> Event Loop --> App State --> Business Logic --> UI Render
+ ^ |
+ +-----------------------------+
+ (state mutation loop)
+```
+
+
+
+### Design Patterns
+
+| Pattern | Implementation |
+|:--------|:---------------|
+| State machine | `AppState` enum drives which screen is active and how events are routed |
+| Async streaming | Tokio channels (`mpsc`) pipe inference output chunk-by-chunk to the UI |
+| Subprocess isolation | llama.cpp runs in a spawned `Child` process with piped stdout |
+| Double buffering | ratatui handles minimal redraws automatically |
+| Lazy loading | Models and conversations are loaded on-demand, not at startup |
+
+
+
+---
+
+
+
+
+
+## Technical Specifications
+
+
+
+
+
+### Project Metrics
+
+```
+Language: Rust 2021 Edition
+Lines of code: ~1,453
+Rust source files: 15
+Modules: 5
+Public functions: ~45
+Data structures: 12
+Enums: 8
+Direct dependencies: 16
+Binary size (release): ~8 MB
+```
+
+
+
+### Performance
+
+| Operation | Time |
+|:----------|:-----|
+| Startup (no models) | ~50 ms |
+| Startup (10 models) | ~200 ms |
+| Model scan (10 models) | ~100 ms |
+| Render frame | ~1-2 ms |
+| Send message (pre-inference) | ~5 ms |
+| Save conversation | ~10 ms |
+
+
+
+### Memory Usage
+
+| State | RAM |
+|:------|:----|
+| Idle (no model) | ~20 MB |
+| Model loaded | ~50 MB |
+| Active inference | ~100-500 MB |
+| Peak (large models) | ~1 GB |
+
+
+
+### System Requirements
+
+| Requirement | Minimum | Recommended |
+|:------------|:--------|:------------|
+| Rust | 1.70+ | 1.75+ |
+| RAM | 512 MB | 2 GB |
+| Disk | 50 MB (binary) | 100 MB |
+| CPU | ARM/x86 (32/64-bit) | x86_64 or ARM64 |
+| Terminal | Unicode support | Modern terminal emulator |
+
+
+
+### Dependencies
+
+| Crate | Purpose |
+|:------|:--------|
+| `ratatui` | Terminal UI framework |
+| `crossterm` | Cross-platform terminal control |
+| `tokio` | Async runtime |
+| `reqwest` | HTTP client (HuggingFace API) |
+| `serde` + `serde_json` + `toml` | Serialization |
+| `chrono` | Timestamps for conversations |
+| `walkdir` | Recursive model directory scanning |
+| `dirs` | Cross-platform home directory |
+| `anyhow` + `thiserror` | Error handling |
+| `colored` | Terminal colors |
+| `tracing` | Logging |
+| `which` | Binary detection in PATH |
+
+
+
+---
+
+
+
+
+
+## Platform Support
+
+
+
+
+
+| Platform | Status | Notes |
+|:---------|:-------|:------|
+| **Termux (Android)** | Full support | Primary target. ARM64 tested |
+| **Linux x86_64** | Full support | Ubuntu 22.04+ tested |
+| **Linux ARM64** | Full support | Raspberry Pi 4 tested |
+| **macOS Intel** | Full support | Catalina+ tested |
+| **macOS Apple Silicon** | Full support | M1/M2 tested |
+| **Windows 10/11** | Full support | Windows 11 tested |
+| **FreeBSD** | Untested | Should work |
+
+
+
+
+Termux (Android) -- Primary Target
+
+
+Optimizations applied automatically when Termux is detected:
+
+- Single-threaded compilation (`-j 1`) to prevent thermal throttling
+- Conservative I/O patterns for mobile storage
+- Simplified progress indicators for narrow terminal widths
+
+Detection method:
+
+```rust
+std::env::var("PREFIX")
+ .map(|p| p.contains("com.termux"))
+ .unwrap_or(false)
+```
+
+
+
+
+macOS
+
+
+- Metal GPU acceleration available through llama.cpp
+- Homebrew for runtime installation (`brew install llama.cpp`)
+- Full keyboard support in Terminal.app and iTerm2
+
+
+
+
+Windows
+
+
+- Windows Terminal recommended for best rendering
+- Backslash path handling automatic
+- CUDA acceleration via llama.cpp for NVIDIA GPUs
+
+
+
+
+
+---
+
+
+
+
+
+## Conversation Format
+
+
+
+
+
+Conversations are saved as JSON files in `~/.config/yuy-chat/conversations/`.
+
+**Filename convention:** `conversation-{YYYYMMDD}-{HHMMSS}.json`
+
+```json
+{
+ "messages": [
+ {
+ "role": "user",
+ "content": "Explain async/await in Rust",
+ "timestamp": "2026-02-06T14:30:22.123Z"
+ },
+ {
+ "role": "assistant",
+ "content": "async/await in Rust allows you to write...",
+ "timestamp": "2026-02-06T14:30:25.456Z"
+ }
+ ],
+ "created_at": "2026-02-06T14:30:22.123Z",
+ "updated_at": "2026-02-06T14:35:10.789Z"
+}
+```
+
+
+
+---
+
+
+
+
+
+## Security
+
+
+
+
+
+### Current
+
+- **HTTPS only** -- all HuggingFace API calls use TLS (rustls, no OpenSSL)
+- **No shell injection** -- subprocesses use `Command::arg()`, never string interpolation
+- **Scoped file access** -- all reads/writes within `~/.config/yuy-chat/` and `~/.yuuki/`
+- **Process isolation** -- llama.cpp runs as a separate subprocess with piped I/O
+
+### Known Limitations
+
+- HuggingFace tokens are stored in plaintext in `config.toml`
+- File permissions are not enforced on config files
+
+### Planned (v0.2+)
+
+- System keyring integration for token storage
+- File permission enforcement (`0o600` for sensitive files)
+- Encrypted token storage on Termux via libsodium
+- Input size limits and sanitization
+
+
+
+---
+
+
+
+
+
+## Troubleshooting
+
+
+
+
+
+
+No models found
+
+
+```bash
+# Check if models exist
+ls ~/.yuuki/models/
+
+# Download a model using yuy CLI
+yuy download Yuuki-best
+
+# Or place a .gguf file manually
+cp your-model.gguf ~/.yuuki/models/
+```
+
+
+
+
+llama.cpp not found
+
+
+```bash
+# Termux
+pkg install llama-cpp
+
+# macOS
+brew install llama.cpp
+
+# Verify
+which llama-cli
+```
+
+
+
+
+Permission denied on llamafile
+
+
+```bash
+chmod +x ~/.yuuki/models/*.llamafile
+```
+
+
+
+
+Slow responses
+
+
+- Use a smaller quantization (`q4_0` instead of `q8_0`)
+- Check available RAM (`free -h` or `top`)
+- Switch to the **Precise** preset (shorter outputs)
+- Ensure no other heavy processes are running
+
+
+
+
+UI rendering issues
+
+
+- Use a terminal with Unicode support
+- On Windows, use Windows Terminal (not CMD)
+- On Termux, ensure terminal encoding is UTF-8
+- Try resizing the terminal window
+
+
+
+
+
+---
+
+
+
+
+
+## Roadmap
+
+
+
+
+
+### v0.2 -- Enhanced UX
+
+- [ ] Syntax highlighting for code blocks
+- [ ] Copy/paste support
+- [ ] Export conversations to Markdown
+- [ ] Custom system prompts
+- [ ] Vim keybindings mode
+- [ ] Custom user-defined presets
+
+### v0.3 -- Power Features
+
+- [ ] Multiple chat tabs
+- [ ] Search in conversation history
+- [ ] Token usage statistics
+- [ ] Model comparison mode
+- [ ] Template system for prompts
+
+### v1.0 -- Ecosystem
+
+- [ ] Plugin system
+- [ ] Custom themes (user-defined color schemes)
+- [ ] Conversation branching
+- [ ] Multi-modal support (images)
+- [ ] REST API server mode
+
+
+
+---
+
+
+
+
+
+## Contributing
+
+
+
+
+
+### Development Setup
+
+```bash
+git clone https://github.com/YuuKi-OS/yuy-chat
+cd yuy-chat
+
+# install Rust if needed
+curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
+
+# build and verify
+cargo build
+cargo test
+cargo fmt -- --check
+cargo clippy
+```
+
+### Commit Convention
+
+```
+():
+```
+
+Types: `feat` | `fix` | `docs` | `style` | `refactor` | `test` | `chore`
+
+```
+feat(chat): add multi-line input support
+
+- Detect Shift+Enter for newlines
+- Update input rendering for wrapped text
+- Add cursor position tracking
+
+Closes #12
+```
+
+### Pull Request Checklist
+
+- [ ] Tests pass (`cargo test`)
+- [ ] Code is formatted (`cargo fmt`)
+- [ ] No clippy warnings (`cargo clippy`)
+- [ ] Documentation updated if needed
+- [ ] Commits follow the convention above
+
+### Coding Standards
+
+- `snake_case` for functions, `CamelCase` for types
+- Document all public functions with `///` comments
+- Use `Result` and the `?` operator for error handling
+- Prefer `async/await` over callbacks
+- Justify any new dependency in the PR description
+
+
+
+---
+
+
+
+
+
+## Design Decisions
+
+
+
+
+
+
+Why a TUI instead of a GUI or web UI?
+
+
+The primary target is Termux on Android. A TUI requires no display server, no browser, and minimal resources. It also works over SSH, inside tmux, and in any terminal emulator on any platform. A GUI may be added as an optional feature later.
+
+
+
+
+Why ratatui?
+
+
+ratatui is the most actively maintained TUI framework in the Rust ecosystem. It provides immediate-mode rendering, a rich widget library, and cross-platform terminal support through crossterm. The API is well-documented and the community is responsive.
+
+
+
+
+Why subprocess spawning instead of library linking?
+
+
+Linking llama.cpp as a C library adds significant build complexity, especially for cross-compilation and Termux. Spawning a subprocess is simpler, isolates crashes, and allows the user to update llama.cpp independently. Library integration is planned for v1.0.
+
+
+
+
+Why Tokio for a TUI?
+
+
+Inference is slow. Without async, the UI would freeze during response generation. Tokio enables non-blocking subprocess reads, smooth streaming display, and sets the foundation for future parallel features like multi-tab chat.
+
+
+
+
+Why JSON for conversations instead of SQLite?
+
+
+JSON files are human-readable, trivially portable, and require no additional dependency. Each conversation is self-contained. SQLite may be introduced in v1.0 if search and indexing become necessary.
+
+
+
+
+
+---
+
+
+
+
+
+## Build Configuration
+
+
+
+
+
+### Release Profile
+
+```toml
+[profile.release]
+opt-level = "z" # optimize for binary size
+lto = true # link-time optimization
+codegen-units = 1 # single codegen unit for better optimization
+strip = true # strip debug symbols
+```
+
+### Environment Variables
+
+```bash
+RUST_LOG=debug yuy-chat # enable debug logging
+RUST_LOG=info yuy-chat # info-level logging
+YUY_MODELS_DIR=/path yuy-chat # custom models directory
+XDG_CONFIG_HOME=/custom yuy-chat # custom config directory
+```
+
+### Cross-Compilation
+
+```bash
+# ARM64 (Raspberry Pi, Termux native)
+rustup target add aarch64-unknown-linux-gnu
+cargo build --release --target aarch64-unknown-linux-gnu
+
+# Windows (from Linux)
+rustup target add x86_64-pc-windows-gnu
+cargo build --release --target x86_64-pc-windows-gnu
+
+# macOS Apple Silicon (from Linux)
+rustup target add aarch64-apple-darwin
+cargo build --release --target aarch64-apple-darwin
+```
+
+
+
+---
+
+
+
+
+
+## About the Yuuki Project
+
+
+
+
+
+yuy-chat exists to serve the [Yuuki project](https://huggingface.co/OpceanAI/Yuuki-best) -- a code-generation LLM being trained entirely on a smartphone with zero cloud budget.
+
+
+
+|
+
+**Training Details**
+
+| | |
+|:--|:--|
+| Base model | GPT-2 (124M parameters) |
+| Training type | Continued pre-training |
+| Hardware | Snapdragon 685, CPU only |
+| Training time | 50+ hours |
+| Progress | 2,000 / 37,500 steps (5.3%) |
+| Cost | $0.00 |
+
+ |
+
+
+**Quality Scores (Checkpoint 2000)**
+
+| Language | Score |
+|:---------|:------|
+| Agda | 55 / 100 |
+| C | 20 / 100 |
+| Assembly | 15 / 100 |
+| Python | 8 / 100 |
+
+ |
+
+
+
+A fully native model (trained from scratch, not fine-tuned) is planned for v1.0. A research paper documenting the mobile training methodology is in preparation.
+
+
+
+---
+
+
+
+
+
+## Related Projects
+
+
+
+
+
+| Project | Description |
+|:--------|:------------|
+| [yuy](https://github.com/YuuKi-OS/yuy) | CLI for downloading, managing, and running Yuuki models |
+| [Yuuki-best](https://huggingface.co/OpceanAI/Yuuki-best) | Best checkpoint model weights |
+| [Yuuki Space](https://huggingface.co/spaces/OpceanAI/Yuuki) | Web-based interactive demo |
+| [yuuki-training](https://github.com/YuuKi-OS/yuuki-training) | Training code and scripts |
+
+
+
+---
+
+
+
+
+
+## Links
+
+
+
+
+
+
+
+[](https://huggingface.co/OpceanAI/Yuuki-best)
+
+[](https://huggingface.co/spaces/OpceanAI/Yuuki)
+
+[](https://github.com/YuuKi-OS/yuy)
+
+
+
+[](https://github.com/YuuKi-OS/yuuki-training)
+
+[](https://github.com/YuuKi-OS/yuy-chat/issues)
+
+
+
+
+
+---
+
+
+
+
+
+## License
+
+
+
+
+
+```
+Copyright 2026 Yuuki Project
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+ http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+```
+
+
+
+---
+
+
+
+
+
+**Built with patience, a phone, and zero budget.**
+
+
+
+[](https://huggingface.co/OpceanAI)
+
+
+
+