Llm Guardrails Python Packages

deepteam

DeepTeam is a framework to red team LLMs and AI agents.

bastion-prompt-protection

Lightweight prompt-injection detector built for AI agents, copilots, and LLM apps. Fast, local, calibrated.

rail-score-sdk

Official Python SDK for RAIL Score. LLM evaluation across 8 dimensions, guardrails, safe regeneration, agent tool-call eval, and compliance (GDPR, HIPAA, EU AI Act, India DPDP).

guardix

A Input Prompt Guard Library with Bert model trained on prompt injection dataset

shadowshield

Unified open-source security shield for agentic AI systems — defense-in-depth prompt-injection protection (canary tokens, agent-trace alignment audit, tool-call guarding, PII/secret scanning).

agentic-security

Agentic LLM Vulnerability Scanner / AI red teaming kit 🧪

beava

Real-time decision features without streaming infra. Turn live events into product reflexes — no Kafka, no Flink, no feature store.

varden

A self-hosted runtime firewall for AI agents

promptgaurd

A Input Prompt Guard Library with Bert model trained on prompt injection dataset

promptshields

Production-Grade LLM Security Framework - Protect against prompt injection, jailbreaks, and data leakage

reasongate

Explainable security gate for LLM apps — blocks prompt injection with an auditable reason for every decision.

aegis-gateway-core

Aegis v2 — core kernel: plugin registry, typed config, pipeline contracts.

aegis-gateway-pack-classification

Aegis is an open-source, plugin-first AI gateway framework written in Python. It sits between applications and LLM providers, applying governance rules to every request and response.

last-layer

Ultra-fast, Low Latency LLM security solution

agentmoat

A security layer for AI agents: detects prompt injection, firewalls dangerous tool calls, scores inter-agent trust, and keeps a tamper-evident audit log. Works with the Anthropic & OpenAI SDKs, LangGraph, and any MCP server.

aixploit

AI redTeaming Python library

agentshield-guard

Official Python SDK for AgentShield — prompt-injection detection for LLM agents.

llama-index-postprocessor-bastion-guardrail

llama-index Bastion Prompt Protection guardrail integration

blackwall-llm-shield-python

Blackwall LLM Shield is an open-source AI security toolkit for JavaScript and Python that protects LLM apps from prompt injection, sensitive data leaks, unsafe tool calls, and hostile RAG content with prompt sanitization, PII masking, output inspection, policy enforcement, and audit trails.

agent-cordon

Zero-dependency prompt-injection and data-exfiltration firewall for LLM agents: scans untrusted text and outbound actions, sees through obfuscation, guards the MCP/tool boundary.

aegis-gateway-pack-residency

Aegis v2 — data residency policy pack.

aegis-gateway-pack-budgets

Aegis v2 — per-principal monthly budget caps policy pack.

aegis-gateway-pack-pii

Aegis is an open-source, plugin-first AI gateway framework written in Python. It sits between applications and LLM providers, applying governance rules to every request and response.

aegis-gateway-pack-llm-guard

Aegis is an open-source, plugin-first AI gateway framework written in Python. It sits between applications and LLM providers, applying governance rules to every request and response.