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.
Provides pluggable security guardrails for LLM applications through a framework that integrates with existing GenAI stacks without requiring application rewrites. Enables real-time detection and mitigation of risks like prompt injection, data leakage, and unsafe outputs via modular safety modules. Includes observability features for monitoring model behavior and security events across deployed applications.
213 stars. No commits in the last 6 months.
Stars
213
Forks
223
Language
CSS
License
Apache-2.0
Category
Last pushed
Aug 05, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/privacera/paig"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
miquido/draive
All-in-one Python framework for building production-ready LLM agents and workflows. Developed by Miquido.
monocle2ai/monocle
Monocle is a framework for tracing GenAI app code. This repo contains implementation of Monocle...
binome-dev/graphite
Graphite Agentic Framework by Binome Technologies
skaiworldwide-oss/agensgraph-python
A Python driver for AgensGraph Multi-Model Database
paragon-intelligence/agentle
Build production-ready AI agents in days, not months. Python 3.13+. Save development time with...