# ProgramAsWeights (PAW)

**Compile natural language specifications into neural programs that run locally.**

ProgramAsWeights lets you define functions in English and compile them into tiny neural programs (.paw files) that run on your machine. Once compiled, they work as regular Python functions -- no internet connection, no external service, no per-call fees.

## Quick Start

```bash
pip install programasweights --extra-index-url https://pypi.programasweights.com/simple/
```

```python
import programasweights as paw

# Load an official program by name
fn = paw.function("email-triage")

result = fn("Thesis defense committee needs your signature by EOD")
print(result)  # "immediate"

result = fn("Department newsletter: spring picnic next Friday")
print(result)  # "wait"
```

## Compile Your Own

```python
import programasweights as paw

# Describe what you want in English
program = paw.compile(
    "Fix malformed JSON: repair missing quotes and trailing commas"
)

# Use the compiled program
fn = paw.function(program.id)
fn("{name: 'Alice', age: 30,}")  # '{"name":"Alice","age":30}'
```

## What Can You Build?

PAW is for functions that are easy to describe but hard to code as rules:

- **Fuzzy search** -- typo-tolerant matching, semantic search, near-duplicate detection
- **Format repair** -- fix broken JSON, normalize dates, repair malformed API inputs
- **Log triage** -- extract errors from verbose output, detect anomalies
- **Custom classification** -- define "important" or "urgent" in your own words
- **Smart notifications** -- classify emails/messages by your own urgency rules
- **Agent preprocessing** -- parse tool calls, route tasks, validate outputs

## How It Works

Each compiled program has two parts:

1. **Discrete pseudo-program** -- text instructions generated by the neural compiler
2. **Continuous neural adapter** -- LoRA weights (~23 MB) that tune the interpreter model

At runtime, the SDK loads a quantized base model (Q6_K ~594 MB for Qwen3, Q8_0 ~134 MB for GPT-2, downloaded once) and applies the LoRA adapter. Inference runs entirely locally via llama.cpp.

## Browser Inference

Programs compiled with the compact interpreter (GPT-2 124M) also run directly in the browser via WebAssembly -- no custom server needed for inference:

```html
<script type="module">
  import paw from '@programasweights/web';
  const fn = await paw.function('email-triage-browser');
  const result = await fn('Urgent: server is down!');
</script>
```

See the [Browser Inference guide](guide/browser-inference.md) for details.

## Next Steps

- [Installation](getting-started/installation.md) -- detailed setup guide
- [Your First Program](getting-started/first-program.md) -- step-by-step tutorial
- [Writing Good Specs](guide/writing-good-specs.md) -- tips for effective specifications
- [Python SDK Reference](api-reference/python-sdk.md) -- full API documentation
- [Browser SDK](guide/browser-inference.md) -- run programs in the browser
- [Browse the Hub](hub/browsing-programs.md) -- discover community programs