Integrations

Model-agnostic, by construction.

AetherLab operates at the data layer: you send the text or image, we return the verdict. Which model produced the content (OpenAI, Anthropic, Google, open-source, or your own) never matters to the check.

01How it fits

One check, three places to put it.

Inbound

Before the model

Screen user prompts before they reach your model: injection attempts, prohibited requests, abuse patterns.

Outbound

After the model

Screen generated text and images before they reach users: policy violations, unsafe claims, brand breaks.

Anywhere

Any content flow

The checks accept any data, AI-generated or human, so moderation queues, UGC, and agent pipelines use the same policy line.

02Stack

Python-first, REST underneath.

Use the SDK (aetherlab on PyPI) or call the REST endpoints from any language. Two endpoints cover the surface: /v1/guardrails/prompt for text and /v1/guardrails/media for images.

Guardrails are one pip install aetherlab away. The same API screens text with check_prompt and images with check_media, against the policies you define.

quickstart.pyaetherlab 0.4.1
from aetherlab import AetherLabClient

client = AetherLabClient()  # reads AETHERLAB_API_KEY

result = client.check_prompt(
    "user or model text to screen",
    blacklisted_keywords=["guaranteed returns"],
)

print(result.compliance_status)  # "Non-Compliant"
print(result.avg_threat_level)   # 0.94

Bring your stack. Keep your policies.

If your content flows over HTTP, it can be checked. Tell us about your architecture and we'll map the integration points.

Ask about the Evidence Pack

Leave your email and we'll walk you through what an Evidence Pack contains for your use case: severity-scored findings, business-impact mapping, and the approval record.