Stars
🛠️ Awesome tools & guides for harness engineering.
DeepInfer: High-performance, large-scale inference framework for DeepSeek models
Agentic enterprise data analytics: governed facts (DataBridge), reusable methodology (Skill-Hub), and controllable execution (Host)
AIInfra（AI 基础设施）指AI系统从底层芯片等硬件，到上层软件栈支持AI大模型训练和推理。
High-performance, scalable time-series database designed for Industrial IoT (IIoT) scenarios
Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
1st place solution for 2026 KDD Cup DataAgents . 2026年KDD Cup DataAgents 冠军方案。
Agentar-Scale-SQL is a novel framework that leverages scalable computation to significantly improve Text-to-SQL performance.
DeepSeek Harness: Everything is a Plugin.
A lightweight, powerful framework for multi-agent workflows
Flink Agents is an Agentic AI framework based on Apache Flink
Retrieval and Retrieval-augmented LLMs
The Context Platform for your Data and AI Stack
JuiceFS is a distributed POSIX file system built on top of Redis and S3.
Type-safe, distributed orchestration of agents, ML pipelines, and real-time inference on your k8s — in pure Python with async/await, also other languages (rust, go and ts)
Prefect is a workflow orchestration framework for building resilient data pipelines in Python.
An orchestration platform for the development, production, and observation of data assets.
Apache Fluss is a streaming storage built for real-time analytics.
Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.
Apache Kyuubi is a distributed and multi-tenant gateway to provide serverless SQL on data warehouses and lakehouses.
Apache Iceberg REST Catalog in Rust — access control, credential vending and audit for every engine and AI agent. Apache 2.0.