Starred repositories
2026最新悄咪咪收集的10000+个Telegram群合集、tg导航、电报导航、telegram导航，附全网最有趣好用的机器人BOT🤖【tg10000.com】
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
The Open Context Layer for Data and AI , OpenMetadata is the open platform for building trusted data context and business semantics for humans, AI assistants, and agents.
World's most powerful open data catalog for building a high-performance, geo-distributed and federated metadata lake.
🎖️🏆🏅 100 most popular open source AI projects 🌟 Star if you like it! 🌟
DocTranslator is a powerful document AI translation tool that supports multiple file formats, OpenAI APIs, batch operations, multi-threading, and Docker deployment for efficient translation tasks! …
🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. 🍊YC W23
A library for efficient similarity search and clustering of dense vectors.
Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search
A high-throughput and memory-efficient inference and serving engine for LLMs
The batteries-included agent harness.
Apache Airflow - A platform to programmatically author, schedule, and monitor workflows
Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
StarRocks MCP (Model Context Protocol) Server
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…
The Future of Data Engineering — A CLI SQL client for the modern data stack, enabling AI-native context engineering for data.
Tantivy is a full-text search engine library inspired by Apache Lucene and written in Rust
Automatically identify anti-patterns in SQL queries
BlpCache is a lightweight distributed caching system that supports standard Redis protocol, read-write separation, and High Availability (HA) mode. It is designed to provide a simple, efficient, an…
D2X | Modern C++ Core Language Features - "A C++ tutorial project focused on practical"
JSONBench: a Benchmark For Data Analytics On JSON
SuperSonic is the next-generation AI+BI platform that unifies Chat BI (powered by LLM) and Headless BI (powered by semantic layer) paradigms.
Papers for database systems powered by artificial intelligence (machine learning for database)