Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions docs/docs.json
Original file line number Diff line number Diff line change
Expand Up @@ -56,6 +56,7 @@
"gateway/integrations/langgraph",
"gateway/integrations/litellm",
"gateway/integrations/llamaindex",
"gateway/integrations/nexus-shield",
"gateway/integrations/openai-agents",
"gateway/integrations/n8n",
"gateway/integrations/posthog",
Expand Down
69 changes: 69 additions & 0 deletions docs/gateway/integrations/nexus-shield.mdx
Original file line number Diff line number Diff line change
@@ -0,0 +1,69 @@
---
title: "Nexus Shield Guardrail"
sidebarTitle: "Nexus Shield"
description: "Learn how to route Helicone requests through Nexus Shield for sub-10ms in-RAM PII sanitization."
"twitter:title": "Nexus Shield Integration - Helicone OSS LLM Observability"
iconType: "solid"
---

# Nexus Shield Integration

[Nexus Shield](https://api.nexusshield.ai) is a sub-10ms in-RAM PII sanitization and security guardrail proxy. You can seamlessly pair Helicone with Nexus Shield to monitor your LLM calls while sanitizing sensitive data before it hits upstream providers.

## How It Works

1. **Client** sends request to **Nexus Shield Proxy**.
2. **Nexus Shield** redacts PII in RAM (<10ms).
3. Request is forwarded to **Helicone Gateway** for logging and observability.
4. Helicone routes the sanitized request to the model provider (OpenAI, Anthropic, etc.).

## Quickstart (Python OpenAI Example)

```python
from openai import OpenAI

client = OpenAI(
base_url="https://api.nexusshield.ai/v1",
default_headers={
"X-API-Key": "nx_live_YOUR_NEXUS_KEY",
"Helicone-Auth": "Bearer YOUR_HELICONE_API_KEY",
"Helicone-Target-Url": "https://api.openai.com/v1",
},
)

response = client.chat.completions.create(
model="gpt-4o",
messages=[{"role": "user", "content": "My social security number is 000-12-3456"}],
)

print(response.choices[0].message.content)
```

## Features

- **Sub-10ms Overhead:** Real-time RAM pattern matching.
- **Zero Disk Persistence:** PII is stripped before Helicone logs or processes the payload.

## Get a Nexus Shield API Key

Start a 14-day free trial at [api.nexusshield.ai](https://api.nexusshield.ai):

```bash
curl -X POST https://api.nexusshield.ai/v1/auth/register-trial \
-H "Content-Type: application/json" \
-d '{"email":"you@company.com"}'
```

## Related Documentation

<CardGroup cols={2}>
<Card title="AI Gateway Overview" icon="arrow-progress" href="/gateway/overview">
Learn about Helicone's AI Gateway features and capabilities
</Card>
<Card title="Custom Headers" icon="tags" href="/helicone-headers/introduction">
Helicone headers for routing and observability
</Card>
<Card title="Nexus Shield Live Demo" icon="shield" href="https://api.nexusshield.ai">
Interactive playground and Trust Center
</Card>
</CardGroup>