elsai Guardrails

Comprehensive Protection

Detect and block toxic content, sensitive data, jailbreak attempts, and malicious requests

Off-Topic Detection

Keep conversations focused by defining allowed topics and blocking off-topic inputs

SQL Syntax Validation

Validate SQL queries for 7 major dialects before execution to catch errors early

PII/PHI Detection

Identify sensitive personal and health information with configurable policies, masking, and audit logging

Token Budget Enforcement

Compute full-context token usage and reject oversized requests before LLM processing

Tool Authorization

Restrict agent tool access with role-based allowlists, denylists, and sensitive tool gating

Rate Limiting

Prevent abuse with per-session request, tool call, and execution time limits

Data Exfiltration Detection

Block or mask LLM responses that leak credentials, bulk PII, or export-style payloads

ARMS Storage

Persist guardrail runs to MongoDB, DynamoDB, or ClickHouse via the ARMS Backend

Flexible Configuration

YAML-based or programmatic configuration with customizable thresholds and rules

Easy Integration

Simple Python API with async support, detailed results, and input/output validation

Multi-LLM Support

Works with OpenAI, Azure OpenAI, Anthropic, Gemini, AWS Bedrock, and more

Why elsai Guardrails?

elsai Guardrails provides a comprehensive solution for securing your LLM-based applications. With built-in protection against common threats and flexible configuration options, you can ensure your AI applications are safe and compliant.

Key Features

Toxicity Detection: Automatically detect and block offensive or harmful content

Sensitive Data Protection: Identify and protect personal information like emails, phone numbers, and credit cards

Content Classification: Detect jailbreak attempts, prompt injection, and malicious code using semantic routing

Off-Topic Detection: Keep AI conversations focused by defining allowed topics and blocking off-topic inputs

SQL Syntax Validation: Validate SQL queries for major dialects (PostgreSQL, MySQL, SQLite, and more) before execution

PII/PHI Detection and Data Masking: Entity-based detection with configurable policies, confidence thresholds, data masking, and audit logging

Token Budget Enforcement: Compute full-context token usage and reject oversized requests before LLM processing

Tool Authorization: Role-based tool allowlists and denylists with agent hook integration

Rate Limiting & Abuse Prevention: Per-session request, tool call, and execution time quotas

Data Exfiltration Detection: Block or mask credentials, bulk sensitive data, and export-style payloads in LLM output

ARMS Storage: Persist guardrail runs to MongoDB, DynamoDB, or ClickHouse through the ARMS Backend

Multi-LLM Integration: Seamless integration with major LLM providers

Flexible Deployment: Use as a wrapper or perform separate input/output checks

Quick Example

python

from elsai_guardrails.guardrails import LLMRails

# Initialize with configuration
rails = LLMRails.from_config("config.yml")

# Safe LLM calls with automatic guardrails
response = rails.generate(
    messages=[{"role": "user", "content": "Hello!"}]
)

What's New

Version 0.1.5 introduces powerful new features:

ARMS Storage - Persist guardrail runs to MongoDB, DynamoDB, or ClickHouse via the ARMS Backend

Data Exfiltration Detection - Block or mask credential leaks and bulk data exports in LLM output

Migration - Direct database storage removed; use ARMS Backend storage instead

Get Started

Ready to secure your LLM application? Check out our Installation Guide to get started in minutes!

elsai GuardrailsProgrammable Guardrails