Open memory infrastructure for LLM and agent systems.

The underlying AI memory infrastructure. Connects the memory of your AI apps and agents. Survives kill -9.

LangChain for Go, the easiest way to write LLM-based programs in Go

🎓 系统性大语言模型构建课程｜🛠️ 覆盖预训练数据工程、Tokenizer、Transformer、MoE、GPU 编程 (CUDA/Triton)、分布式训练、Scaling Laws、推理优化及对齐 (SFT/RLHF/GRPO)｜🚀 6 个渐进式作业 + 代码驱动，建立 LLM 全栈认知体系

大模型基础: 一文了解大模型基础知识

📚 从零开始构建大模型

rvLLM: High-performance LLM inference in Rust. Drop-in vLLM replacement.

本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）

分享AI Infra知识&代码练习：PyTorch/vLLM/SGLang框架入门⚡️、性能加速🚀、大模型基础🧠、AI软硬件🔧等

High-performance KV cache storage for LLM inference — GPU offloading, SSD caching, and cross-node sharing via RDMA. Works with vLLM and SGLang.

Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞

NobodyWho is an inference engine that lets you run LLMs locally and efficiently on any device.

A high-performance inference engine for AI models

♻️💾 Yet Another Memory Layer, inspired by Cognitive Science, designed for Cyber Waifu

RuVector is a High Performance, Real-Time, Self-Learning, Vector GNN, Memory DB built in Rust.

Fast, flexible LLM inference

pgvector support for Go

SCUT专硕考试内容

An open-source, code-first Go toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.

Scalable, fast, and disk-friendly vector search in Postgres, the successor of pgvecto.rs.

System Level Intelligent Router for Mixture-of-Models at Cloud, Data Center and Edge

Golang SDK for A2A Protocol

The official Go SDK for Model Context Protocol servers and clients. Maintained in collaboration with Google.

A Go implementation of the Model Context Protocol (MCP), enabling seamless integration between LLM applications and external data sources and tools.