Stars
A suite of tools to develop RAG, semantic search, and other AI applications more easily with PostgreSQL
Because tinygrad got out of hand with line count
Comparing unsafe Rust vs Zig by writing a bytecode interpreter with GC in both langs
All-in-one infrastructure for search, recommendations, RAG, and analytics offered via API
PyTorch native quantization and sparsity for training and inference
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!
A high-throughput and memory-efficient inference and serving engine for LLMs
Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/
Distribute and run LLMs with a single file.
DuckDB is an analytical in-process SQL database management system
A lightweight, memory-protected, message-passing kernel for deeply embedded systems.
Instant is a modern Firebase. We make you productive by giving your frontend a real-time database.
PEASS - Privilege Escalation Awesome Scripts SUITE (with colors)
Select, put and delete data from JSON, TOML, YAML, XML and CSV files with a single tool. Supports conversion between formats and can be used as a Go package.
Programming framework for writing and deploying cloud applications.
the scott CPU from "But How Do It Know?" by J. Clark Scott
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
magic-trace collects and displays high-resolution traces of what a process is doing
The fast sync and async channel that Rust deserves
Cloud-native search engine for observability. An open-source alternative to Datadog, Elasticsearch, Loki, and Tempo.
A simple ZSH quickstart for using ZSH, zgenom, oh-my-zsh and a curated list of extra plugins. It is designed to be easy to customize without requiring you to maintain your own fork.