> ## 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.

# Agnitra Platform

> Production-ready documentation for installing, optimizing, and operating Agnitra.

# Agnitra Platform

Agnitra gives your team an opinionated workflow for profiling, optimizing, and shipping large language models with built-in telemetry and billing. The SDK and CLI handle model compilation, surface runtime hotspots, and emit marketplace-ready usage events so you can move from prototype to production without standing up separate infrastructure.

## Platform Pillars

* **Optimization agents** adapt TorchScript/ONNX graphs with LLM + RL tuned kernels so you keep model accuracy while boosting throughput.
* **Telemetry-first workflows** capture latency, GPU hours, and savings in structured JSON so finance and infra teams share the same source of truth.
* **Usage-based monetization** maps optimization runs to Stripe, AWS Marketplace, and internal ledgers with auditable metadata and license enforcement.

## Start Building Fast

* Install the SDK from PyPI and ship your first optimized artifact via the [Quickstart](/docs/intro/quickstart).
* Explore repeatable automations and code samples in the [SDK & CLI Guide](/docs/guides/cli-and-sdk).
* Understand what telemetry and usage events look like in practice with the [Telemetry Playbook](/docs/guides/telemetry).

## Architecture Overview

The MVP couples a telemetry collector, FX graph extractor, AI optimizer, kernel generator, and runtime patcher behind a unified CLI and control plane. Read the [Architecture Deep Dive](/docs/intro/architecture) for module responsibilities, data flows, and performance targets drawn from the PRD.

## Key Workflows

* Monitor production uplift and route usage events using the [Telemetry Playbook](/docs/guides/telemetry).
* Connect finance tooling and marketplaces through the [Marketplace & Billing guide](/docs/guides/marketplace).
* Bring the control plane into your infrastructure with the [`agnitra-api` reference](/docs/reference/control-plane).

## Reference Materials

* Configure environments with the [Runtime Configuration reference](/docs/reference/configuration).
* Integrate the OpenAI Responses API using the [Responses API contract](/docs/reference/responses-api).
* Mirror telemetry exports and SDK helpers with code snippets across the repository (see `agnitra/core`, `agnitra/api`, and `cli/`).

## What's Next?

Run `pip install agnitra`, export `AGNITRA_API_KEY`, and launch `agnitra optimize` against the TinyLlama fixture to validate your workstation. From there, follow the linked guides to embed Agnitra into pipelines, dashboards, and billing loops.