# Visceral

## Docs

- [API reference](https://docs.visceralai.dev/api-reference/introduction.md): The Visceral backend HTTP API.
- [CLI](https://docs.visceralai.dev/cli/overview.md): Sign in and manage your Visceral account from the terminal.
- [How it works](https://docs.visceralai.dev/concepts/how-it-works.md): Visceral only optimizes what it can prove is safe — and never makes anything worse.
- [Privacy & data](https://docs.visceralai.dev/concepts/privacy.md): Visceral records metadata about your LLM traffic — never the prompts, responses, or PII.
- [Visceral](https://docs.visceralai.dev/index.md): A performance engine for AI agents — it makes wasted LLM calls cheaper, but only once it can prove the cheaper call is safe.
- [Quickstart](https://docs.visceralai.dev/quickstart.md): Instrument your agent and start sending traffic to Visceral.
- [Installation](https://docs.visceralai.dev/sdk/installation.md): Add the Visceral SDK to a Python agent.
- [Instrumenting your agent](https://docs.visceralai.dev/sdk/instrumenting.md): Wrap a raw LLM client, or instrument the framework your agent is built on.

## OpenAPI Specs

- [openapi](https://docs.visceralai.dev/api-reference/openapi.json)