Synthesizing High-quality Text-to-SQL Data at Scale. SynSQL-2.5M is the first million-scale cross-domain text-to-SQL dataset.

No fortress, purely open ground. OpenManus is Coming.

DoWhy is a Python library for causal inference that supports explicit modeling and testing of causal assumptions. DoWhy is based on a unified language for causal inference, combining causal graphic…

Amundsen is a metadata driven application for improving the productivity of data analysts, data scientists and engineers when interacting with data.

Fluss is a streaming storage built for real-time analytics.

Aura is like Siri, but in your browser. An AI voice assistant optimized for low latency responses.

SQL Parser for C++. Building C++ object structure from SQL statements.

Uses tokenized query returned by python-sqlparse and generates query metadata

Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and…

LlamaIndex is the leading framework for building LLM-powered agents over your data.

🔥🔥 AllData可定义数据中台，以数据平台为底座，以数据中台为桥梁，以机器学习平台为工厂，以大模型应用为上游产品，提供全链路数字化解决方案。采购商业版、加入技术社区：https://docs.qq.com/doc/DVHlkSEtvVXVCdEFo

Utilities intended for use with Llama models.

🔥🔥🔥 灵活，可靠和快速的分布式任务重试和分布式任务调度平台

Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…

Support agile DataOps Based on Flink, DataX and Flink-CDC, Chunjun with Web-UI

A framework for writing performant user-defined functions (UDFs) that are portable across a variety of engines including Apache Spark, Apache Hive, and Presto.

Coral is a translation, analysis, and query rewrite engine for SQL and other relational languages.

Analyze SQL and stored procedure data lineage using Java

基于antlr4的sql解析，实现格式化，元数据，血源等自定义解析，包括hive

【2025最新版】 大数据 数据分析 电商系统 实时数仓 离线数仓 数据湖 建设方案及实战代码，涉及组件 #flink #paimon #doris #seatunnel #dolphinscheduler #datart #dinky #hudi #iceberg。

DorisDB SQL解析器Java实现；Clickhouse SQL解析器Java实现

利用Druid SQL Parser解析HiveSQL日志，自动构建字段级别的血缘关系及主外键的自动抽取

KDP(Kubernetes Data Platform) delivers a modern, hybrid and cloud-native data platform based on Kubernetes.

General-purpose web UI for Kubernetes clusters

concurrent, cache-efficient, and Dockerfile-agnostic builder toolkit

Production-Grade Container Scheduling and Management

Chat-based SQL Client and Editor for the next decade

Data Copilot is the framework which makes your chat bot enterprise ready with only few lines of code.

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