Let your Claude able to think

AI-data warehouse to enrich, transform and analyze unstructured data

Lyric: A Rust-powered secure runtime for AI-Agent.

Secure open source cloud runtime for AI apps & AI agents

Natural Language Processing for the next decade. Tokenization, Part-of-Speech Tagging, Named Entity Recognition, Syntactic & Semantic Dependency Parsing, Document Classification

Libro: A Notebook Product Solution with Flexible Customization and Easy Integration.

World's most powerful open data catalog for building a high-performance, geo-distributed and federated metadata lake.

☘️ A visualization grammar based on G2 for streamlit.

SuperSonic is the next-generation AI BI platform that unifies Chat BI (powered by LLM) and Headless BI (powered by semantic layer) paradigms.

agentUniverse is a LLM multi-agent framework that allows developers to easily build multi-agent applications.

A one-stop data processing system to make data higher-quality, juicier, and more digestible for (multimodal) LLMs! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷为大模型提供更高质量、更丰富、更易”消化“的数据！

Redpanda is a streaming data platform for developers. Kafka API compatible. 10x faster. No ZooKeeper. No JVM!

Apache Iceberg

LLM101n: Let's build a Storyteller

Cloud Native DataOps & AIOps Platform | 云原生数智运维平台

The Memory layer for your AI apps

A library that provides an embeddable, persistent key-value store for fast storage optimized for AWS

An open-source storage framework that enables building a Lakehouse architecture with compute engines including Spark, PrestoDB, Flink, Trino, and Hive and APIs

3D Visualization of an GPT-style LLM

An easy to use and powerful chaos engineering experiment toolkit.（阿里巴巴开源的一款简单易用、功能强大的混沌实验注入工具）

Doing simple retrieval from LLM models at various context lengths to measure accuracy

Alluxio, data orchestration for analytics and machine learning in the cloud

A generative speech model for daily dialogue.

Deep Insight into open-source graph on GitHub.

TuGraph is a high performance graph database.

TuGraph Analytics is a distributed graph compute engine.

The PyTorch implementation of Generative Pre-trained Transformers (GPTs) using Kolmogorov-Arnold Networks (KANs) for language modeling

Accepted as [NeurIPS 2024] Spotlight Presentation Paper