Fast, small, and fully autonomous AI assistant infrastructure — deploy anywhere, swap anything 🦀

《深入理解 AI Infra：量化分析与系统设计》（李博杰 著）开源书稿：从硬件约束和模型架构出发，量化推导 LLM 推理与训练系统设计。含全书正文、PDF、配套计算工具与实验

Docker configuration for running VLLM on dual DGX Sparks

DeepSeek 4 Flash local inference engine for Metal and CUDA

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra

Your 24/7 all-scenario AI agent that gets work done for you.

Production-ready platform for agentic workflow development.

Quick Start for Large Language Models (Theoretical Learning and Practical Fine-tuning) 大语言模型快速入门（理论学习与微调实战）

Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search

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/

Cloud-native search engine for observability. An open-source alternative to Datadog, Elasticsearch, Loki, and Tempo.

Tantivy is a full-text search engine library inspired by Apache Lucene and written in Rust

A fast reverse proxy to help you expose a local server behind a NAT or firewall to the internet.

Apache Druid: a high performance real-time analytics database.

An open-source, cloud-native, distributed time-series database with PromQL/SQL/Python supported.

GlareDB: A light and fast SQL database for analytics

MCP实战

A library for building fast, reliable and evolvable network services.

深度学习经典、新论文逐段精读

《动手学深度学习》习题解答，在线阅读地址如下：

《动手学深度学习》：面向中文读者、能运行、可讨论。中英文版被70多个国家的500多所大学用于教学。

A Rust port of shadowsocks

A fast Rust JSON library based on SIMD.

A Java version of simdjson

A multi-modal vector database that supports upserts and vector queries using unified SQL (MySQL-Compatible) on structured and unstructured data, while meeting the requirements of high concurrency a…

PromQL Rust parser