Neo4j graph construction from unstructured data using LLMs

A Production-ready Reinforcement Learning AI Agent Library brought by the Applied Reinforcement Learning team at Meta.

Codes/Notebooks for AI Projects

Superlinked is a Python framework for AI Engineers building high-performance search & recommendation applications that combine structured and unstructured data.

Official Implementation of "KBLaM: Knowledge Base augmented Language Model"

Single File, Single GPU, From Scratch, Efficient, Full Parameter Tuning library for "RL for LLMs"

Understanding Training Dynamics of Deep ReLU Networks

[ACL 2025] How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training

Official implementation of DynE, Dynamics-aware Embeddings for RL

🧢 Hummingbot Helper is an AI assistant that helps users craft advanced trading strategies, understand the codebase and docs, and control their bot instances! 🚀

Evolving LangChain agent architectures using the Quality-Diversity (QD) algorithm.