orbitals 0.1.0

LLM Guardrails tailored to your Principles

LLM Guardrails tailored to your Principles

---

orbitals is an ecosystem of LLM guardrails, designed to provide a governance layer tailored to user-specific principles, requirements and use cases. Rather than enforcing generic notions of safety, correctness, etc., Orbitals evaluates inputs and outputs against user-defined specifications. This makes guardrails explicit, auditable, and aligned with the user's philosophy.

Orbitals guardrails fall into two typologies:

• Guards operate on the input of a guardrailed LLM, assessing whether a user request is legitimate under the provided specifications.
• Supervisors operate on the output of a guardrailed LLM, evaluating the assistant’s response before it is returned.

Guardrails may be released under different modality flavors:

• Open (open-source and open-weight), allowing users to run guardrails and underlying models on their own infrastructure.
• Hosted, accessible via simple HTTP calls (API key required).

Available Guardrails

Name	Flavor	Description
ScopeGuard	Open / Hosted	Validates whether a user request falls within the intended use of an AI service.
RagSupervisor	Coming soon	Ensures LLM responses remain grounded in retrieved context for RAG setups.

ScopeGuard

First, we need to install orbitals and scope-guard:

pip install orbitals[scope-guard-vllm]

Then:

from orbitals.scope_guard import ScopeGuard

scope_guard = ScopeGuard(
    backend="vllm",
    model="small"
)

ai_service_description = """
You are a virtual assistant for a parcel delivery service.
You can only answer questions about package tracking.
Never respond to requests for refunds.
"""

user_query = "If the package hasn't arrived by tomorrow, can I get my money back?"
result = scope_guard.validate(user_query, ai_service_description)

print(f"Scope: {result.scope_class.value}")
if result.evidences:
    print("Evidences:")
    for evidence in result.evidences:
        print(f"  - {evidence}")

# Scope: Restricted
# Evidences:
#   - Never respond to requests for refunds.