Stars
Python package that aligns LLM judges with human scores
A tool that validates academic paper references
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
Showcase of a line-of-business agent with evaluation framework
Precio is a Rust library that implements the Precio protocol for computing private layered histograms and sums.
Flow Integrity Deterministic Enforcement System. Mechanisms for securing AI agents with information-flow control.
Repository for numerically computing the privacy parameter in Gaussian Differential Privacy
LLMail prompt injection challenge GUI
A C++ interpreter for the OPA policy language Rego
On-device Machine Learning model analyzer and extractor for Android Apps, check out our USENIX Security'21 paper "Mind Your Weight(s): A Large-scale Study on Insufficient Machine Learning Model Pro…
🤫 Code and benchmark for our ICLR 2024 spotlight paper: "Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory"
Generates synthetic data and user interfaces for privacy-preserving data sharing and analysis.
Adding guardrails to large language models.
Generative AI extensions for onnxruntime
Graph-structured Indices for Scalable, Fast, Fresh and Filtered Approximate Nearest Neighbor Search
Prompty makes it easy to create, manage, debug, and evaluate LLM prompts for your AI applications. Prompty is an asset class and format for LLM prompts designed to enhance observability, understand…
Inspect: A framework for large language model evaluations
PerfView is a CPU and memory performance-analysis tool
A benchmark for prompt injection detection systems.
A small collection of terminal shaders
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
A term rewriting system for experimental programming language development.
Chat with your database or your datalake (SQL, CSV, parquet). PandasAI makes data analysis conversational using LLMs and RAG.