> ## Documentation Index
> Fetch the complete documentation index at: https://docs.agnitra.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Getting Started

> Install the Agnitra SDK, run the CLI, and generate optimization telemetry.

# Getting Started

Agnitra delivers an end-to-end optimization platform that pairs model tuning, telemetry, and usage-based billing in a single developer flow. Use the SDK or CLI to profile workloads, generate optimized TorchScript artifacts, and push structured usage records into your control plane or marketplace integrations.

This quickstart walks through installing the SDK, running the CLI, and inspecting optimization telemetry.

## 1. Install the SDK

### Python (PyPI)

Install from PyPI (recommended):

```bash theme={null}
pip install agnitra
```

For editable installs while developing locally:

```bash theme={null}
pip install -e .[openai,rl]
```

Optional extras:

* `agnitra[openai]` – OpenAI Responses API client bindings.
* `agnitra[rl]` – Stable Baselines3 + Gymnasium reinforcement learning add-ons.
* `agnitra[nvml]` – GPU telemetry via NVIDIA NVML.
* `agnitra[marketplace]` – Cloud marketplace adapters (`boto3`, `httpx`, `google-auth`).

### JavaScript / TypeScript (npm)

Install the JavaScript SDK:

```bash theme={null}
npm install agnitra
# or
yarn add agnitra
```

Example usage:

```ts theme={null}
import { AgnitraClient } from "agnitra";

const client = new AgnitraClient({
  apiKey: process.env.AGNITRA_API_KEY!,
  baseUrl: process.env.AGNITRA_API_BASE_URL ?? "http://127.0.0.1:8080"
});

const result = await client.optimize({
  target: "A100",
  modelGraph,
  telemetry
});

console.log(result.bottleneck.expected_speedup_pct);
```

## 2. Optimize a Model

```bash theme={null}
agnitra optimize --model tinyllama.pt --input-shape 1,16,64
```

The CLI loads the model, generates an optimized artifact, and prints a billing snapshot (performance uplift, GPU hours saved, billable total). Pass `--output` to control the destination path.

From Python:

```python theme={null}
import torch
from agnitra import optimize

model = torch.jit.load("tinyllama.pt")
sample = torch.randn(1, 16, 64)

result = optimize(model, input_tensor=sample, project_id="demo")
print(result.usage_event.total_billable)
```

## 3. Explore the API Surface

* Launch the Starlette service: `agnitra-api --host 127.0.0.1 --port 8080`
* POST graph + telemetry payloads to `/optimize` for automatic kernel suggestions.
* Forward usage events to `/usage` to dispatch marketplace billing records.

Refer to the [Responses API contract](/docs/reference/responses-api) for the JSON schema and webhook semantics.

## 4. Next Steps

* Review the [CLI and SDK guide](/docs/guides/cli-and-sdk) for advanced flags, licensing, and offline mode.
* Plug telemetry into finance tooling via the [Marketplace & Billing guide](/docs/guides/marketplace).
* Browse the [Runtime Configuration reference](/docs/reference/configuration) to tailor Agnitra for your environment.