Supercharge Your LLM with the Fastest KV Cache Layer

Hindsight: Agent Memory That Learns

LiteRT, successor to TensorFlow Lite. is Google's On-device framework for high-performance ML & GenAI deployment on edge platforms, via efficient conversion, runtime, and optimization

Docker compose for Nebula Graph

A curated list of 120+ LLM libraries category wise.

Universal LLM Deployment Engine with ML Compilation

Repair malformed JSON from LLMs, APIs, logs, and user input in Python.

lock-free FIFO queue by C native built it, easy built cross platform(no extra dependencies needed) , guarantee thread safety memory management ever!

it's a smallest library that provides a lock-free thread pool sharing on multithreading, it design for scalability

lock-free LIFO stack by C native built it, easy built cross platform(no extra dependencies needed) , guarantee thread safety memory management ever!

atomic_hashtable for C, fast movement for read, write, and delete without locking while multithreading purposes, Simple and Stable

A complete computer science study plan to become a software engineer.