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

# Introduction

Egma is an open-source platform for testing and monitoring voice agents. It helps you run simulation tests so that you can be confident in your agent's behavior before releases and then helps you monitor for issues in production.

You can use [Egma Cloud](https://app.egma.ai) or [self-host](/self-hosting/get-started) Egma on your own infrastructure.

## Quickstart

Follow the [five-minute quickstart](/docs/get-started/quickstart) guide to create, run, and grade your first test suite.

## Why we built Egma

We’ve built voice agents in production ourselves. And as developers, one of the most frustrating parts was calling the agent again and again, reciting the same script just to test its behavior. It felt like we’d signed up for creative work and ended up doing grunt work.

We disliked the grunt work, but we hated unreliable agents even more.

That frustration led us to a bigger question: how can developers trust the voice agents they’re shipping?

We believe building that trust takes two things.

First, you need a way to test the major scenarios your agent will face in production before you release it, without having to make every call yourself. But you can’t test for everything. Agents are probabilistic systems, and the real world is too messy to predict in advance.

Which brings us to the second: you need a way to find issues once your agent is in production, whether it’s handling a few dozen conversations or millions. And we don’t mean simply running an LLM as a judge against a fixed checklist. That can help you check for known problems. But what about the problems you haven’t thought to look for?

Good monitoring needs to do both: detect drift in known behaviors and surface unexpected ways your agent is going wrong.

We think it's a really hard problem to solve. And having felt it firsthand, we’re deeply motivated to take a shot at it. Egma exists to help developers trust the voice agents they are shipping.

## Our core principles & why you should probably choose Egma

* **Open source** - You should be able to inspect, modify, and improve the system that you rely on for your production agent's testing and monitoring.
* **Self-hostable** - Unfortunately, open source has not always meant easy to self-host. Voice agents are already handling sensitive data across industries. And in a lot of cases, you might not want to have a long vendor review cycle. Egma is designed to be self-hostable. We keep our self-hosting guides up to date. If you're looking to self-host Egma, we can help you with it.
* **Bring your own keys** - Platforms that help you do simulation testing already exist. But they all charge a heavy premium on top of inference costs. We believe if the industry truly wants to scale simulation testing of voice agents, we need to stop charging a premium on inference and start providing infrastructure to scale simulations. Egma allows you to bring your own STT, LLM, and TTS provider keys. We also provide inference directly within the platform at a 0% markup so you don't have to wrestle with multiple keys. Think of Egma as PostHog for voice agent testing and monitoring!
* **Keep tests with your code** - Egma tests are simple Markdown files that live alongside your agent code. They give developers and coding agents shared context on how the voice agent should behave. Tests evolve with your code and go through the same reviews, so keeping them in sync is part of your existing workflow.

## Further reading

1. Read about our [philosophy of voice agent testing](/docs/core-philosophies/testing-philosophy).
2. Read how we think about [monitoring built for voice agents](/docs/core-philosophies/monitoring-philosophy).

## Community & contact

1. Found a bug or have a feature request? [Open a GitHub issue](https://github.com/egma-ai/egma/issues).
2. Join our [Discord](https://discord.gg/v4KHSNHfPj) for faster replies!