The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

Set of tools to assess and improve LLM security.

A lightweight library for portable low-level GPU computation using WebGPU.

Set-of-Mark Prompting for LMMs

Google's common Java, C++ and JavaScript library for parsing, formatting, and validating international phone numbers.

Beautiful & consistent icon toolkit made by the community. Open-source project and a fork of Feather Icons.

A very fast and expressive template engine.

Servo, the embeddable, independent, memory-safe, modular, parallel web rendering engine

Python bindings for llama.cpp

A USB-PD sniffer/injector/sink based on Google's Twinkie, re-designed to be manufactured by mere mortals.

build-once run-anywhere c library

A massively spiffy yet delicately unobtrusive compression library.

3D rendering toolkit for Dart and/or Flutter

Work-in-progress vector search SQLite extension that runs anywhere.

Named, vector icons for elementary OS

Instant Open Source docs with zero configuration.

Python ETL framework for stream processing, real-time analytics, LLM pipelines, and RAG.

Documentation around the Mainboard and other key parts of Framework Laptop 16

A cross-platform, linkable library implementation of Git that you can use in your application.

SVG icons for popular brands

A CLI tool to convert your codebase into a single LLM prompt with source tree, prompt templating, and token counting.

Tensor library for machine learning

A guidance language for controlling large language models.

Foundational Models for State-of-the-Art Speech and Text Translation

LLM Analytics

😸 Soothing pastel theme for the high-spirited!

Generative AI extensions for onnxruntime

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

TR-100 Machine Report