msrivastava

fastify

Fast and low overhead web framework, for Node.js

pino

🌲 super fast, all natural json logger

mmtracking

NeMo-Guardrails

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

garak

LLM vulnerability scanner

LLaSA

Large Language and Sensor Assistant: Multimodal LLM for sensor and human activity interpretation

HypOp

Hypergraph Neural Network-Based Combinatorial Optimization

leeky

leeky - training data contamination techniques for blackbox models

Samba

Official implementation of "Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling"

scallop-lang.github.io

Official Website of Scallop Language

puter

🌐 The Web OS! Free, Open-Source, and Self-Hostable.

pykan

Kolmogorov Arnold Networks

mTAN

Code for "Multi-Time Attention Networks for Irregularly Sampled Time Series", ICLR 2021.

robocasa

RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots

Capstone-Project

bringup-bench

Bringup-Bench is a collection of standalone minimal library and system dependence benchmarks useful for bringing up newly designed CPUs, accelerators, compilers and operating systems. You probably don't need Bringup-Bench, but if you do, you probably need it badly!

viz-js

Graphviz in your browser

DrEureka

Official Repository for "DrEureka: Language Model Guided Sim-To-Real Transfer" (RSS 2024)

graph-talk

Library for structured information processing: parsing, interpreting, converting, etc.

exposing-the-csi

Dataset and resources for CSI-based activity recognition applications using 802.11ax signals

granite-code-models

Granite Code Models: A Family of Open Foundation Models for Code Intelligence

milvus

A cloud-native vector database, storage for next generation AI applications

weaviate

Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database​.

marqo

Unified embedding generation and search engine. Also available on cloud - cloud.marqo.ai

chroma

the AI-native open-source embedding database

RAGatouille

Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.

ColBERT

ColBERT: state-of-the-art neural search (SIGIR'20, TACL'21, NeurIPS'21, NAACL'22, CIKM'22, ACL'23, EMNLP'23)

pkl

A configuration as code language with rich validation and tooling.

wasmCloud

wasmCloud allows for simple, secure, distributed application development using WebAssembly components and capability providers.

colima

Container runtimes on macOS (and Linux) with minimal setup