CADAM is the open source text-to-CAD web application

Inspect and compare self-supervised vision model representations for DINOv2, I-JEPA, V-JEPA 2, EUPE

MathCode: A Frontier Mathematical Coding Agent

PyTorch code and models for the DINOv2 self-supervised learning method.

A high-throughput and memory-efficient inference and serving engine for LLMs

State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!

Efficient Universal Perception Encoder: a single on-device vision encoder with versatile representations that match or exceed specialized experts across multiple task domains.

Simplify your onnx model

Integrate Git version control with automatic commit-and-sync and other advanced features in Obsidian.md

A collection of pre-trained, state-of-the-art models in the ONNX format

Stylometric analysis of Satoshi & comparison of Satoshi with 75,000+ authors

Collection of DESIGN.md files that capture design systems from popular websites. Drop one into your project and let coding agents build matching UI.

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

Provable SHRIMPS: Post-quantum hash-based signatures verified in Cairo with STARK proofs

CommitLLM is a cryptographic commit-and-audit protocol for open-weight LLM inference.

You like pytorch? You like micrograd? You love tinygrad! ❤️

Comprehensive roadmap for aspiring Embedded Systems Engineers, featuring a curated list of learning resources

A powerful little TUI framework 🏗

Open-source compliance toolkit for the EU AI Act. Risk classification, conformity checklists, documentation templates.

Implemention of the GRASP world model planner for dino_wm environments

Linkedin Automation Tool: Describe your product. Define your target market. The AI finds the leads for you.

A Python package to assess and improve fairness of machine learning models.

Set of tools to assess and improve LLM security.

Adding guardrails to large language models.

Responsible AI Toolbox is a suite of tools providing model and data exploration and assessment user interfaces and libraries that enable a better understanding of AI systems. These interfaces and l…

Provable adversarial robustness at ImageNet scale

alpha-beta-CROWN: An Efficient, Scalable and GPU Accelerated Neural Network Verifier (winner of VNN-COMP 2021, 2022, 2023, 2024, 2025)

Inspect: A framework for large language model evaluations

A comprehensive set of fairness metrics for datasets and machine learning models, explanations for these metrics, and algorithms to mitigate bias in datasets and models.

RewardBench: the first evaluation tool for reward models.