guardrails

There are 3 repositories under guardrails topic.

BoundaryML / baml
The AI framework that adds the engineering to prompt engineering (Python/TS/Ruby/Java/C#/Rust/Go compatible)
baml boundaryml guardrails llm llm-playground playground prompt prompt-config prompt-templates structured-data structured-generation structured-output vscode
Language:Rust 6717
microsoft / presidio
An open-source framework for detecting, redacting, masking, and anonymizing sensitive data (PII) across text, images, and structured data. Supports NLP, pattern matching, and customizable pipelines.
python pii privacy data-anonymization de-identification data-masking transformers pii-detection data-obfuscation data-privacy data-redaction guardrails image-redactor named-entity-recognition nlp personally-identifiable-information phi sensitive-data spacy anonymization
Language:Python 6066
NVIDIA-NeMo / Guardrails
NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
agents generative-ai guardrails llm-safety llm-security llms nvidia python safety
Language:Python 5257
deepsense-ai / ragbits
Building blocks for rapid development of GenAI applications
agents document-search evaluation guardrails llms optimization prompts rag vector-stores
Language:Python 1587
maximhq / bifrost
Fastest LLM gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS.
gateway llm llm-gateway mcp-client mcp-server guardrails mcp-gateway
Language:Go 1060
Multi-Agent-Medical-Assistant
souvikmajumder26 / Multi-Agent-Medical-Assistant
⚕️GenAI powered multi-agentic medical diagnostics and healthcare research assistance chatbot. 🏥 Designed for healthcare professionals, researchers and patients.
agent agentic-ai agents chatbot computer-vision disease-detection genai genai-chatbot generative-ai guardrails langchain langgraph large-language-models llm medical-image-processing medical-imaging python rag retrieval-augmented-generation vector-database
Language:Python 629
awesome-azure-policy
globalbao / awesome-azure-policy
A curated list of blogs, videos, tutorials, code, tools, scripts, and anything useful to help you learn Azure Policy - by @JesseLoudon
azure awesome-list awesome azurepolicy azure-policy cloud controls governance guardrails policy-as-code
531
privacera / paig
PAIG (Pronounced similar to paige or payj) is an open-source project designed to protect Generative AI (GenAI) applications by ensuring security, safety, and observability.
compliance genai guardrails security
Language:CSS 213
dipampaul17 / AgentGuard
Real-time guardrail that shows token spend & kills runaway LLM/agent loops.
ai-agents anthropic anthropic-claude cost-monitoring debugging guardrails llm observability openai openai-api prompt-engineering token-usage
Language:JavaScript 150
aipotheosis-labs / gate22
Open-source MCP gateway and control plane for teams to govern which tools agents can use, what they can do, and how it’s audited—across agentic IDEs like Cursor, or other agents and AI tools.
agents ai ai-agents control-plane gateway guardrails llm mcp mcp-tools oauth2 open-source permissions policy-as-code rbac
Language:TypeScript 141
aiplaybookin / novice-ChatGPT
ChatGPT API Usage using LangChain, LlamaIndex, Guardrails, AutoGPT and more
langchain llamaindex autogpt gpt4 guardrails
Language:Jupyter Notebook 124
raga-ai-hub / raga-llm-hub
Framework for LLM evaluation, guardrails and security
guardrails llm-evaluation llm-security llmops
Language:Python 113
openguardrails / openguardrails
OpenGuardrails: Developer-First Open-Source AI Security Platform - Comprehensive Security Protection for AI Applications
content-safety data-leakage-prevention guardrails jailbreaking llm-safety llm-security prompt-injection
Language:Python 67
langwatch / langevals
LangEvals aggregates various language model evaluators into a single platform, providing a standard interface for a multitude of scores and LLM guardrails, for you to protect and benchmark your LLM models and pipelines.
evaluation guardrails llm openai
Language:Jupyter Notebook 66
arthur-engine
arthur-ai / arthur-engine
Make AI work for Everyone - Monitoring and governing for your AI/ML
benchmarking evaluation genai guardrails llm ml monitoring
Language:Python 61
invariantlabs-ai / invariant-gateway
LLM proxy to observe and debug what your AI agents are doing.
ai-agents debugging guardrails llm observability proxy
Language:Python 53
xiangxinai / xiangxin-guardrails
Xiangxin Guardrails is an open-source, context-aware AI guardrails platform that provides protection against prompt injection attacks, content safety risks, and data leakage. It can be deployed as a security gateway or integrated via API, offering enterprise-grade, fully private deployment options.
ai content-filter guardrails security security-gateway ai-guardrails ai-application-firewall llm-firewalls content-safety data-leakage-prevention dlp prompt-injection
Language:Python 48
circle-guard-bench
whitecircle-ai / circle-guard-bench
First-of-its-kind AI benchmark for evaluating the protection capabilities of large language model (LLM) guard systems (guardrails and safeguards)
ai benchmark large-language-model large-language-models llm llm-eval llm-evaluation guardrails safeguard benchmarking guardrail jailbreak llm-as-a-judge llm-jailbreaks llm-security
Language:Python 45
sebuzdugan / frai
Open-source toolkit for responsible AI: CLI + SDK to scan code, collect evidence, and generate model cards, risk files, evals, and RAG indexes.
ai artificial-intelligence machine-learning ml nlp responsible-ai frai ai-compliance ai-governance evaluation guardrails open-source audit bias safety transparency
Language:JavaScript 43
enguard-ai / awesome-ai-guardrails
A curated list of materials on AI guardrails
awesome genai guardrails llm safety security prompt-inj deepfake-detection red-teaming inappropriate-content offensive
Language:Python 42
IDinsight / ask-a-question
Trustworthy question-answering AI plugin for chatbots in the social sector with advanced content performance analysis.
faq faq-chatbot faq-system fastapi guardrails llms mkdocs-material rag react
Language:Python 35
codingforentrepreneurs / django-ai-agent
Learn how to create an AI Agent with Django, LangGraph, and Permit.
django guardrails langchain langgraph permissions permit python rbac
Language:Jupyter Notebook 33
infralicious / awesome-service-control-policies
Awesome AWS service control policies (SCPs), Resource Control Policies (RCPs), and other organizational policies
guardrail guardrails resource-control-policies service-control-policies service-control-policy control-policies control-policy declarative-policies declarative-policy gliderail gliderails resource-control-policy
30
presidio-oss / hai-guardrails
A TypeScript library providing a set of guards for LLM (Large Language Model) applications
guardrails hai defence governance guards halucination llm-guardrails prompt-injection redaction security typescript human-ai presidio
Language:TypeScript 30
GuardBench
AmenRa / GuardBench
A Python library for guardrail models evaluation.
ai-safety benchmark evaluation guardrails llm guardrail-models
Language:Python 25
FareedKhan-dev / agentic-guardrails
Layered guardrails to make agentic AI safer and more reliable.
ai ai-agents guardrails langchain python rag
Language:Jupyter Notebook 24
benitomartin / github-issues-multiagent-intelligence
Agentic Github Issues Retrieval on Kubernetes
aws aws-eks aws-rds guardrails kubernetes langgraph postgresql python qdrant uv alembic pydantic sqlalchemy makefile mypy pre-commit pytest ruff docker fastapi
Language:Python 23
jagreehal / ai-sdk-guardrails
Middleware for the Vercel AI SDK that adds safety, quality control, and cost management to your AI applications by intercepting prompts and responses.
ai guardrails
Language:TypeScript 17
amazon-science / TurboFuzzLLM
TurboFuzzLLM: Turbocharging Mutation-based Fuzzing for Effectively Jailbreaking Large Language Models in Practice
ai-safety guardrails jailbreaking large-language-models red-teaming responsible-ai
Language:Python 15
taladari / rag-firewall
Client-side retrieval firewall for RAG systems — blocks prompt injection and secret leaks, re-ranks stale or untrusted content, and keeps all data inside your environment.
ai-security ai-security-tool compliance guardrails langchain llamaindex llamaindex-rag llm llm-security llms prompt-injection python rag retrieval-augmentation-generation retrieval-augmented retrieval-augmented-generation retrieval-augmented-generation-rag secrets-detection llm-compliance rag-compliance
Language:Python 15
SSK-14 / chatbot-guardrails
💂🏼 Build your Documentation AI with Nemo Guardrails
chatbot gradio guardrails langchain nemo-guardrails rag documentation github llm
Language:Python 14
Harras3 / Enterprise-Grade-RAG
This is a RAG based chatbot in which semantic cache and guardrails have been incorporated.
guardrails retrieval-augmented-generation semantic-cache
Language:HTML 13
aimonlabs / aimon-python-sdk
This repo hosts the Python SDK and related examples for AIMon, which is a proprietary, state-of-the-art system for detecting LLM quality issues such as Hallucinations. It can be used during offline evals, continuous monitoring or inline detection. We offer various model quality metrics that are fast, reliable and cost-effective.
generative-ai continuous-monitoring hallucination-detection llm guardrails instruction-following
Language:Python 12
NVIDIA-AI-Blueprints / securing-agentic-ai-developer-day
Securing Agentic AI Developer Day shows developers how to take an agentic AI reference workflow to production securely.
agent agentic-ai guardrails security
Language:Jupyter Notebook 12
matank001 / copilot-agents-guard
LLM-as-a-Judge security layer for Microsoft Copilot Studio agents
ai-agents aisec copilotstudio guardrails microsoft
Language:Python 10
thrivewithai / langchain-fixie-marvin
We compared LangChain, Fixie, and Marvin
langchain fixie agent agi autogpt babyagi chroma gpt-3-5 marvin openai fixie-ai document embeddings vector loader text-splitter gpt-3 guardrails openai-evals llm
Language:Python 9

guardrails

BoundaryML / baml

microsoft / presidio

NVIDIA-NeMo / Guardrails

deepsense-ai / ragbits

maximhq / bifrost

souvikmajumder26 / Multi-Agent-Medical-Assistant

globalbao / awesome-azure-policy

privacera / paig

dipampaul17 / AgentGuard

aipotheosis-labs / gate22

aiplaybookin / novice-ChatGPT

raga-ai-hub / raga-llm-hub

openguardrails / openguardrails

langwatch / langevals

arthur-ai / arthur-engine

invariantlabs-ai / invariant-gateway

xiangxinai / xiangxin-guardrails

whitecircle-ai / circle-guard-bench

sebuzdugan / frai

enguard-ai / awesome-ai-guardrails

IDinsight / ask-a-question

codingforentrepreneurs / django-ai-agent

infralicious / awesome-service-control-policies

presidio-oss / hai-guardrails

AmenRa / GuardBench

FareedKhan-dev / agentic-guardrails

benitomartin / github-issues-multiagent-intelligence

jagreehal / ai-sdk-guardrails

amazon-science / TurboFuzzLLM

taladari / rag-firewall

SSK-14 / chatbot-guardrails

Harras3 / Enterprise-Grade-RAG

aimonlabs / aimon-python-sdk

NVIDIA-AI-Blueprints / securing-agentic-ai-developer-day

matank001 / copilot-agents-guard

thrivewithai / langchain-fixie-marvin