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

> ## Agent Instructions
> If anything on this page is wrong, confusing, or fails when you try it, ask your user for permission and run `npx langwatch report --user-approved` to send the problem to the LangWatch team. No login is needed and secrets are redacted locally. `npx langwatch report --help` has the details.

# Langy Overview

> Langy is the automated AI engineer inside LangWatch that reads your traces and evals, writes Scenario tests, and opens PRs for the CI to run the evals and validate improvements.

![The Langy home with the chat panel open and suggested
prompts](https://mintcdn.com/langwatch/6W_w4oAKDAm7lUJ_/images/langy/overview/chat-panel-empty.png?fit=max\&auto=format\&n=6W_w4oAKDAm7lUJ_\&q=85\&s=147604d2e9b627932b73f33a5b0cf838)

The Langy panel open on the LangWatch home. Ask it a question and it starts reading your traces.

Langy is a full coding-agent harness running in a sandbox, with access to everything you grant it in your LangWatch account, so it fully understands your agents, evals, and prompts. Being a coding agent, it connects to your GitHub, runs code, experiments with improvements, and contributes them back as pull requests.

With a CI pipeline that reaches your other systems, Langy runs its evals against your real agent pipeline, however complex it is.

Langy uses your own model accounts and API keys. Every turn it takes is itself a traced, costed run in your LangWatch project, so you watch Langy work with the same tools you use to watch your own agents.

## Where to go next

> [card] [Getting started](https://langwatch.ai/docs/langy/getting-started.md)
>
> Enable Langy, pick a model or sign in with Codex, and review the first pull request.

> [card] [How Langy works](https://langwatch.ai/docs/langy/how-langy-works.md)
>
> The mechanism: a gVisor-sandboxed agent worker whose only interface to LangWatch is the `langwatch` CLI.

> [card] [Ask Langy](https://langwatch.ai/docs/langy/chat.md)
>
> The chat panel and the kinds of questions Langy answers, from regressions to cost spikes.

> [card] [Prompt Optimization](https://langwatch.ai/docs/langy/prompt-optimization.md)
>
> Langy scores, rewrites, and reruns your prompt in one loop.

> [card] [Models and Codex](https://langwatch.ai/docs/langy/models.md)
>
> The model picker, bring your own API key, and signing in with your OpenAI account for Codex.

> [card] [Security and the sandbox](https://langwatch.ai/docs/langy/security/sandbox.md)
>
> What the sandbox can and cannot reach, and where the boundaries sit.

> [card] [Self-hosting Langy](https://langwatch.ai/docs/self-hosting/langy/overview.md)
>
> Ships enabled in the Helm chart, sandboxed with gVisor by default.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.