Metadata-Version: 2.4
Name: vaayu
Version: 1.0.1
Summary: Vaayu: 245M & 492M Small Language Machine Model (SLMM) with Native MCP & Tool Calling
Author: Meet Mendapara
License: MIT
Keywords: slmm,machine-model,mcp,tool-calling,agent,pytorch,transformers
Requires-Python: >=3.10
Description-Content-Type: text/markdown
Requires-Dist: torch>=2.1.0
Requires-Dist: transformers>=4.40.0
Requires-Dist: tokenizers>=0.19.0
Requires-Dist: huggingface_hub>=0.23.0
Requires-Dist: pydantic>=2.0.0
Requires-Dist: numpy>=1.24.0
Dynamic: requires-python

# Vaayu: Small Language Machine Model (SLMM)

[![PyPI version](https://img.shields.io/pypi/v/vaayu.svg)](https://pypi.org/project/vaayu/)
[![Python](https://img.shields.io/pypi/pyversions/vaayu.svg)](https://pypi.org/project/vaayu/)
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
[![Hugging Face](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Vaayu--Base-blue)](https://huggingface.co/meetmendapara/Vaayu-Base)

**Vaayu** is an ultra-lightweight, embeddable **Small Language Machine Model (SLMM)** family designed specifically for local machine execution, application integration, and native **Model Context Protocol (MCP)** tool calling.

---

## Key Features

- **Embedded & Local**: Runs entirely locally on consumer hardware and CPUs/GPUs with low memory footprint (~245M to 492M parameters).
- **Native MCP Support**: Direct, first-class connection to Model Context Protocol servers over `stdio` and `SSE`.
- **Structured Tool Calling**: Emits precise tool calls in structured JSON formats with built-in schema compliance.
- **Fast KV-Cache Inference**: Optimized autoregressive generation with Grouped Query Attention (GQA).
- **Zero Heavy Dependencies**: Clean Python API designed to be embedded directly into existing applications, IDE extensions, or agentic frameworks.

---

## Installation

```bash
pip install vaayu
```

---

## Quickstart

### 1. Load Pretrained Model from Hugging Face

You can load official weights directly from the Hugging Face Hub:

```python
from vaayu import Vaayu

# Load official Vaayu-Base directly from Hugging Face Hub
ai = Vaayu.from_pretrained("meetmendapara/Vaayu-Base")

# Generate response
response = ai.chat("Explain the purpose of Model Context Protocol (MCP) in one paragraph.")
print(response)
```

### 2. Connect to Local MCP Tools

Vaayu natively discovers and invokes tools provided by MCP servers:

```python
from vaayu import Vaayu

ai = Vaayu.from_pretrained("meetmendapara/Vaayu-Base")

# Connect to any local MCP server (e.g. filesystem or custom service)
ai.attach_mcp_server(
    command="npx",
    args=["-y", "@modelcontextprotocol/server-filesystem", "./workspace"]
)

# Run an agentic prompt with tool execution
result = ai.agent_step("Read the file config.json and list all defined settings.")
print(result)
```

### 3. Load Local Checkpoints

If you have trained or downloaded local weights:

```python
from vaayu import Vaayu

ai = Vaayu.load_local("checkpoints/vaayu_base/vaayu_final.pt")
print(ai.chat("Hello, Vaayu!"))
```

---

## Command Line Interface (CLI)

Vaayu comes with an interactive CLI for chatting, testing tools, and inspecting weights:

```bash
# Start an interactive chat session with Hugging Face weights
vaayu chat --repo meetmendapara/Vaayu-Base

# Or chat with a local checkpoint
vaayu chat --weights checkpoints/vaayu_base/vaayu_final.pt
```

---

## Architecture Variants

| Model Variant | Parameters | Context Window | Target Use Case |
| :--- | :--- | :--- | :--- |
| **Vaayu-Base** | **245M** | 2048 | In-process local embedding, single-turn tool calling, edge runtimes |
| **Vaayu-Large** | **492M** | 2048 | Multi-step agentic workflows, complex tool schemas, code generation |

---

## License

MIT License. Free for research and commercial applications.
