Open http://localhost:5174

<p align="center">
  <img src="docs/assets/logo.png" width="80" alt="xiaodazi logo" />
</p>

<h1 align="center">xiaodazi</h1>

<p align="center">
  <strong>Open-source AI agent that lives on your desktop.</strong><br/>
  Local-first storage · 200+ plug-and-play skills · 7+ LLM providers · macOS & Windows
</p>

<p align="center">
  <a href="https://www.dazee.ai"><img src="https://img.shields.io/badge/Website-dazee.ai-F59E0B?style=flat&logo=safari&logoColor=white" alt="Official Website" /></a>
  <a href="https://opensource.org/licenses/MIT"><img src="https://img.shields.io/badge/License-MIT-yellow.svg" alt="License: MIT" /></a>
  <a href="https://www.python.org/downloads/"><img src="https://img.shields.io/badge/python-3.10+-blue.svg" alt="Python 3.10+" /></a>
  <a href="https://github.com/malue-ai/dazee-small/stargazers"><img src="https://img.shields.io/github/stars/malue-ai/dazee-small?style=social" alt="GitHub Stars" /></a>
</p>

<p align="center">
  <a href="https://www.dazee.ai">Official Website</a> | <a href="README_zh.md">中文</a> | English
</p>

<p align="center">
  <img src="docs/assets/quick-start.jpg" width="720" alt="Get started in 3 steps" />
</p>

---

## What is xiaodazi?

xiaodazi ("little buddy") is an open-source AI agent that **runs as a native desktop app** (Tauri). It keeps all data on your machine, operates your computer directly — managing files, automating apps, generating documents — and remembers your preferences across sessions.

### Demo

<video src="docs/assets/demo.mp4" width="720" controls>
  Your browser does not support the video tag. <a href="docs/assets/demo.mp4">Download the demo video</a>.
</video>

### Why xiaodazi?

<p align="center">
  <img src="docs/assets/core-advantages.jpg" width="720" alt="5 core advantages" />
</p>

| | Cloud AI Assistants | xiaodazi |
|---|---|---|
| **Data** | Stored on provider's servers | 100% local (SQLite, plain files) |
| **Memory** | Forgets between sessions | Remembers preferences via editable `MEMORY.md` + semantic search |
| **Skills** | Fixed capabilities | 200+ plug-and-play skills, add new ones by writing Markdown |
| **Models** | Locked to one provider | Switch between Claude, GPT, Qwen, DeepSeek, Gemini, GLM, or Ollama |
| **Errors** | Fails silently or retries | Classifies errors, backtracks from bad approaches, degrades gracefully |

---

## Quick Start

### Option A: One-click install (end users)

**Windows** — Download the installer from [Releases](https://github.com/malue-ai/dazee-small/releases), double-click to run.

**macOS** — Open Terminal and run:

```bash
bash <(curl -fsSL https://raw.githubusercontent.com/malue-ai/dazee-small/main/scripts/auto_build_app.sh)
```

Then configure an API key in the Settings page (DeepSeek or Gemini free tier recommended for beginners).

### Option B: From source (developers)

```bash
git clone https://github.com/malue-ai/dazee-small.git
cd dazee-small

python3 -m venv .venv
source .venv/bin/activate   # Windows: .venv\Scripts\activate
pip install -r requirements.txt
```

Create `config.yaml` in the project root (or use the Settings page after starting):

```yaml
api_keys:
  ANTHROPIC_API_KEY: sk-ant-api03-your-key-here   # Recommended
  # OPENAI_API_KEY: sk-xxx
  # DASHSCOPE_API_KEY: sk-xxx                      # Qwen
  # GOOGLE_API_KEY: xxx                            # Gemini (free: 1500 req/day)
```

Start the backend:

```bash
uvicorn main:app --host 0.0.0.0 --port 8000 --reload
```

Start the frontend:

```bash
cd frontend
npm install && npm run dev
# Open http://localhost:5174
```

<details>
<summary><strong>Desktop app (Tauri) — requires Rust toolchain</strong></summary>

```bash
# Install Rust: https://rustup.rs/
# Requires Node.js >= 18 (Vite 5 requirement)

# 1. Build backend sidecar binary (requires PyInstaller)
pip install pyinstaller
python scripts/build_backend.py

# 2. Start Tauri dev / build
cd frontend
npm run tauri:dev     # Development
npm run tauri:build   # Production build
```

</details>

<details>
<summary><strong>Fully offline with Ollama</strong></summary>

Install [Ollama](https://ollama.ai), then set in `config.yaml`:

```yaml
llm:
  COT_AGENT_MODEL: ollama/llama3.1
```

No API key needed. All inference runs locally.

</details>

---

## Key Design Decisions

### LLM-First — No keyword matching, ever

All semantic tasks — intent classification, skill selection, complexity inference, backtrack decisions — are performed by the LLM. Hard-coded rules exist only for format validation, numeric calculations, and security boundaries.

**Why it matters:** When a user says *"Don't make a PPT, just give me the key points"*, a keyword system matches "PPT" and loads the wrong tools. xiaodazi's LLM-driven intent analysis correctly loads zero PPT skills.

### Skills as Markdown — 200+ and growing

Each skill is a directory with a `SKILL.md` file. No Python code required for most skills — the LLM reads the instructions and uses built-in tools to execute them.

Despite 200+ skills, 

... (truncated)