Trustworthy Ai Python Packages

giskard

🐢 Open-Source Evaluation & Testing library for LLM Agents

adversarial-robustness-toolbox

Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams

encypher-ai

Embed invisible metadata in AI-generated text using zero-width characters.

langtest

Pacific AI provides a library for delivering safe & effective NLP models.

akios

Secure runtime for multi-agent AI. Kernel sandboxing (seccomp-bpf), real-time PII redaction, Merkle audit trails.

rhesis-sdk

The testing platform for AI teams. Bring engineers, PMs, and domain experts together to generate tests, simulate (adversarial) conversations, and trace every failure to its root cause.

aiverify-moonshot

Moonshot - A simple and modular tool to evaluate and red-team any LLM application.

nlptest

Deliver safe & effective language models

rhesis

The testing platform for AI teams. Bring engineers, PMs, and domain experts together to generate tests, simulate (adversarial) conversations, and trace every failure to its root cause.

detectors

Python package to accelerate research on generalized out-of-distribution (OOD) detection.

dqm-ml-core

A library to compute data quality metrics

dqm-ml-images

A library to compute data quality metrics

dqm-ml-pytorch

A library to compute data quality metrics

proof-citations

AI agent skill that creates formal, verifiable proofs of claims — every fact computed or cited, never asserted

trustllm

[ICML 2024] TrustLLM: Trustworthiness in Large Language Models

trustifai

TrustifAI: A Comprehensive Framework for AI Trustworthiness

trustlens

Open-source Python library for evaluating ML model reliability beyond accuracy — with calibration, failure, and fairness diagnostics for informed deployment decisions.

proof-engine-registry

AI agent skill that creates formal, verifiable proofs of claims — every fact computed or cited, never asserted

proof-engine-wiki

Attach verified Proof Engine proofs to LLM-wiki claims.

enforcecore

Lightweight runtime enforcement for agentic AI. PII masking, policy checks, and Merkle audit trails as a decorator.

dqm-ml

Python library designed to compute data quality metrics for Machine Learning

dqm-ml-job

Python library designed provide pipelining tools dqm-ml library to compute data quality metrics for Machine Learning

ai-privacy-toolkit

A toolkit for tools and techniques related to the privacy and compliance of AI models.

markdiffusion

An Open-Source Toolkit for Generative Watermarking of Latent Diffusion Models