diff --git a/README.md b/README.md
index 7b76557..86ba161 100644
--- a/README.md
+++ b/README.md
@@ -1,33 +1,84 @@
 # PUMA
 
-**PUMA** aims to be a lightweight, high-performance inference engine for local AI. *Play for fun.*
+A lightweight, high-performance inference engine for local AI. *Play for fun.*
 
 ## Features
 
-- 🚀 **Model Management** - Download and manage AI models from multiple providers
+- **Model Management** - Download and manage AI models from model providers like Hugging Face
+- **System Detection** - Automatic GPU detection and system information reporting
+- **Local Caching** - Efficient model storage with custom cache directories
+- **Multiple Providers** - Support for Hugging Face with ModelScope coming soon
 
-## Quick Start
+## Installation
 
-### Install from source
+### From Source
 
 ```bash
 make build
 ```
 
+The binary will be available as `./puma`.
+
+## Quick Start
+
+### 1. Download a Model
+
+```bash
+# From Hugging Face (default)
+puma pull InftyAI/tiny-random-gpt2
+```
+
+### 2. List Downloaded Models
+
+```bash
+puma ls
+```
+
+### 3. Check System Information
+
+```bash
+puma info
+```
+
+Example output:
+```
+System Information:
+  Operating System:   Darwin
+  Architecture:       arm64
+  CPU Cores:          14
+  Total Memory:       36.00 GiB
+  GPU:                Apple M4 Max (Metal) - 32 GPU cores
+
+PUMA Information:
+  PUMA Version:       0.0.1
+  Cache Directory:    ~/.puma/cache
+  Cache Size:         799.88 MiB
+  Models:             1
+  Running Models:     0
+```
+
 ## Commands
 
-| Command | Description |
-|---------|-------------|
-| `pull` | Download a model from a provider |
-| `ls` | List local models |
-| `ps` | List running models |
-| `run` | Create and run a model |
-| `stop` | Stop a running model |
-| `rm` | Remove a model |
-| `info` | Display system-wide information |
-| `inspect` | Return detailed information about a model |
-| `version` | Show PUMA version |
-| `help` | Show help information |
+| Command | Status | Description | Example |
+|---------|--------|-------------|---------|
+| `pull` | ✅ | Download a model from a provider | `puma pull InftyAI/tiny-random-gpt2` |
+| `ls` | ✅ | List local models | `puma ls` |
+| `ps` | 🚧 | List running models | `puma ps` |
+| `run` | 🚧 | Create and run a model | `puma run InftyAI/tiny-random-gpt2` |
+| `stop` | 🚧 | Stop a running model | `puma stop <model-id>` |
+| `rm` | ✅ | Remove a model | `puma rm InftyAI/tiny-random-gpt2` |
+| `info` | ✅ | Display system-wide information | `puma info` |
+| `inspect` | 🚧 | Return detailed information about a model or service | `puma inspect InftyAI/tiny-random-gpt2` |
+| `version` | ✅ | Show PUMA version | `puma version` |
+| `help` | ✅ | Show help information | `puma help` |
+
+## Configuration
+
+PUMA stores models in `~/.puma/cache` by default. This location is used for all downloaded models and metadata.
+
+## Supported Providers
+
+- **Hugging Face** - Full support with custom cache directories
 
 ## Development
 
@@ -43,7 +94,24 @@ make build
 make test
 ```
 
-### Supported Providers
+### Project Structure
+
+```
+puma/
+├── src/
+│   ├── cli/         # Command-line interface
+│   ├── downloader/  # Model download logic
+│   ├── registry/    # Model registry management
+│   ├── system/      # System detection (CPU, GPU, memory)
+│   └── utils/       # Utility functions
+├── Cargo.toml       # Rust dependencies
+└── Makefile         # Build commands
+```
+
+## License
+
+Apache-2.0
+
+## Contributing
 
-- ✅ **Hugging Face** - Full support with custom cache directories
-- 🚧 **ModelScope** - Coming soon
+[![Star History Chart](https://api.star-history.com/svg?repos=inftyai/puma&type=Date)](https://www.star-history.com/#inftyai/puma&Date)