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

> ## Agent Instructions
> These docs cover three products: TrustGate (AI agent gateway), TrustGuard (runtime security), and TrustTest (AI red teaming). Start from each product overview for the definition and How it works. Prefer the .md URL next to a page in /llms.txt when you need the full article. Use /llms-full.txt for a single-file dump of the site.

# SDKs

> Which NeuralTrust SDK your code needs: the TrustGate SDK to reach governed tools and models, the TrustGuard SDK to evaluate content yourself

NeuralTrust publishes two SDKs. They solve different problems, and many
applications use only one of them.

|                  | TrustGate SDK                                                                                                 | TrustGuard SDK                                                                                                                                                                                  |
| ---------------- | ------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **What it does** | Connects your code to a TrustGate application: its MCP tools, its models, and the end users it acts for       | Sends a prompt, a completion or a tool call to TrustGuard and returns a verdict your code enforces                                                                                              |
| **Use it when**  | Your agent calls tools and models through TrustGate                                                           | Your code sits in the data path and must apply a policy itself                                                                                                                                  |
| **Credential**   | The application's key (`ag_…`)                                                                                | A collector key (`tgk_…`)                                                                                                                                                                       |
| **Who enforces** | The gateway, on every call it serves                                                                          | Your code, on the verdict                                                                                                                                                                       |
| **Python**       | `pip install trustgate-sdk` (Python 3.10+)                                                                    | `pip install trustguard-sdk`                                                                                                                                                                    |
| **TypeScript**   | `npm install @neuraltrust/trustgate` (Node.js 22+)                                                            | `npm install @neuraltrust/trustguard-sdk`                                                                                                                                                       |
| **Go**           | —                                                                                                             | `github.com/NeuralTrust/trustguard-sdk/go`                                                                                                                                                      |
| **Packages**     | [PyPI](https://pypi.org/project/trustgate-sdk/) · [npm](https://www.npmjs.com/package/@neuraltrust/trustgate) | [PyPI](https://pypi.org/project/trustguard-sdk/) · [npm](https://www.npmjs.com/package/@neuraltrust/trustguard-sdk) · [pkg.go.dev](https://pkg.go.dev/github.com/NeuralTrust/trustguard-sdk/go) |
| **Source**       | [NeuralTrust/trustgate-sdk](https://github.com/NeuralTrust/trustgate-sdk)                                     | [NeuralTrust/trustguard-sdk](https://github.com/NeuralTrust/trustguard-sdk)                                                                                                                     |

When a TrustGuard policy is attached to the gateway, traffic that goes through
TrustGate is already evaluated there, so an agent built on the TrustGate SDK does
not also need the TrustGuard SDK for those calls. Reach for the TrustGuard SDK for
content that never passes through a gateway: a model you call directly, a
document you index, a reply you generate.

## TrustGate SDK

<div className="nt-cat-grid">
  <a className="nt-cat-card" href="/sdks/trustgate/overview">
    <span className="nt-cat-logo nt-brand-mark nt-mark-trustgate" aria-hidden="true" />

    <span className="nt-cat-text">
      <span className="nt-cat-name">Quickstart</span>
      <span className="nt-cat-meta"><span className="nt-cat-note">One key, the gateway found for you</span></span>
    </span>
  </a>

  <a className="nt-cat-card" href="/sdks/trustgate/tools">
    <span className="nt-cat-logo nt-harness-logo nt-logo-code nt-cat-icon" aria-hidden="true" />

    <span className="nt-cat-text">
      <span className="nt-cat-name">Tools</span>
      <span className="nt-cat-meta"><span className="nt-cat-note">MCP endpoint or provider tool calls</span></span>
    </span>
  </a>

  <a className="nt-cat-card" href="/sdks/trustgate/end-users">
    <span className="nt-cat-logo nt-harness-logo nt-logo-globe nt-cat-icon" aria-hidden="true" />

    <span className="nt-cat-text">
      <span className="nt-cat-name">Acting for end users</span>
      <span className="nt-cat-meta"><span className="nt-cat-note">Per-user accounts and connect links</span></span>
    </span>
  </a>

  <a className="nt-cat-card" href="/sdks/trustgate/models">
    <span className="nt-cat-logo nt-brand-mark nt-mark-openai" aria-hidden="true" />

    <span className="nt-cat-text">
      <span className="nt-cat-name">Models</span>
      <span className="nt-cat-meta"><span className="nt-cat-note">A provider client pointed at the LLM plane</span></span>
    </span>
  </a>

  <a className="nt-cat-card" href="/sdks/trustgate/configuration">
    <span className="nt-cat-logo nt-harness-logo nt-logo-code nt-cat-icon" aria-hidden="true" />

    <span className="nt-cat-text">
      <span className="nt-cat-name">Configuration</span>
      <span className="nt-cat-meta"><span className="nt-cat-note">Options, environment, Hybrid</span></span>
    </span>
  </a>

  <a className="nt-cat-card" href="/sdks/trustgate/errors">
    <span className="nt-cat-logo nt-harness-logo nt-logo-code nt-cat-icon" aria-hidden="true" />

    <span className="nt-cat-text">
      <span className="nt-cat-name">Errors</span>
      <span className="nt-cat-meta"><span className="nt-cat-note">Every failure, and whose it is to fix</span></span>
    </span>
  </a>
</div>

## TrustGuard SDK

<div className="nt-cat-grid">
  <a className="nt-cat-card" href="/sdks/trustguard/python">
    <span className="nt-cat-logo nt-brand-mark nt-mark-python" aria-hidden="true" />

    <span className="nt-cat-text">
      <span className="nt-cat-name">Python</span>
      <span className="nt-cat-meta"><span className="nt-cat-note">trustguard-sdk</span></span>
    </span>
  </a>

  <a className="nt-cat-card" href="/sdks/trustguard/node">
    <span className="nt-cat-logo nt-brand-mark nt-mark-node" aria-hidden="true" />

    <span className="nt-cat-text">
      <span className="nt-cat-name">Node.js</span>
      <span className="nt-cat-meta"><span className="nt-cat-note">@neuraltrust/trustguard-sdk</span></span>
    </span>
  </a>

  <a className="nt-cat-card" href="https://github.com/NeuralTrust/trustguard-sdk/tree/main/go" target="_blank" rel="noreferrer">
    <span className="nt-cat-logo nt-harness-logo nt-logo-go" aria-hidden="true" />

    <span className="nt-cat-text">
      <span className="nt-cat-name">Go</span>
      <span className="nt-cat-meta"><span className="nt-cat-note">On GitHub</span></span>
    </span>
  </a>
</div>

For route-level coverage without a call at each site, the
[Python](/integrations/python-middleware) and
[Node.js](/integrations/node-middleware) middleware wrap the TrustGuard SDK. From
any other language, call the [Evaluate API](/trustguard/api/evaluate) directly.