A lightweight, powerful framework for multi-agent workflows

Support git repo for the course IST597: Deep Learning Foundations.

Code for the paper "Language Models are Unsupervised Multitask Learners"

NLG and NLU for dialogue processing

Repository for the code created at Penn State University for the project Class Insight. This code focuses on automatic analysis of discourse.

Simple script to access Google's pre-trained sentence embeddings from TensorFlow Hub.

Model Context Protocol Servers

📄 A curated list of awesome .cursorrules files

The official Python SDK for Model Context Protocol servers and clients

Synthetic data generators for structured and unstructured text, featuring differentially private learning.

Deep Research for your internal data

An AI Hedge Fund Team

Roo Code (prev. Roo Cline) gives you a whole dev team of AI agents in your code editor.

LLM Frontend for Power Users.

Benchmark for LLM-based Agents in Computational Biology

An aviary-based data science agent based on jupyter notebooks

Python package built to ease deep learning on graph, on top of existing DL frameworks.

Implementation of GPT-who: A Machine-Text Detector

Toolkit for linearizing PDFs for LLM datasets/training

Convert any PDF into a podcast episode!

An open-source ML pipeline development platform

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

OctoTools: An agentic framework with extensible tools for complex reasoning

Magic to turn Cursor/Windsurf as 90% of Devin

Training-free Post-training Efficient Sub-quadratic Complexity Attention. Implemented with OpenAI Triton.