onnx-go gives the ability to import a pre-trained neural network within Go without being linked to a framework or library.

🔍 LangKit: An open-source toolkit for monitoring Large Language Models (LLMs). 📚 Extracts signals from prompts & responses, ensuring safety & security. 🛡️ Features include text quality, relevance m…

Stringlifier is on Opensource ML Library for detecting random strings in raw text. It can be used in sanitising logs, detecting accidentally exposed credentials and as a pre-processing step in unsu…

A PyTorch implementation of Context Vector Data Description (CVDD), a method for Anomaly Detection on text.

TODS: An Automated Time-series Outlier Detection System

Anomaly detection related books, papers, videos, and toolboxes

LLM Prompt Injection Detector

Context aware, pluggable and customizable data protection and de-identification SDK for text and images

Easy to use, state-of-the-art Neural Machine Translation for 100+ languages

Go bindings for YARA

A collection of prompt injection mitigation techniques.

⚡ Vigil ⚡ Detect prompt injections, jailbreaks, and other potentially risky Large Language Model (LLM) inputs

NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

Examples and guides for using the OpenAI API

Set of tools to assess and improve LLM security.

🦜🔗 Build context-aware reasoning applications

An Autonomous LLM Agent for Complex Task Solving

the LLM vulnerability scanner

Universal and Transferable Attacks on Aligned Language Models

cloc counts blank lines, comment lines, and physical lines of source code in many programming languages.

Train transformer language models with reinforcement learning.

a prompt injection scanner for custom LLM applications

PFRL: a PyTorch-based deep reinforcement learning library

Implementation of ChatGPT RLHF (Reinforcement Learning with Human Feedback) on any generation model in huggingface's transformer (blommz-176B/bloom/gpt/bart/T5/MetaICL)

Go HTTP framework with high-performance and strong-extensibility for building micro-services.

Inference code for Llama models

A guidance language for controlling large language models.

Fast, portable, non-Turing complete expression evaluation with gradual typing (Go)