Java 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发

A light-weight and powerful meta-prompting, context engineering and spec-driven development system for Claude Code by TÂCHES.

from vibe coding to agentic engineering - practice makes claude perfect

Spec-driven development (SDD) for AI coding assistants.

📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG

OpenViking is an open-source context database designed specifically for AI Agents(such as openclaw). OpenViking unifies the management of context (memory, resources, and skills) that Agents need through a file system paradigm, enabling hierarchical context delivery and self-evolving.

Knowledge Engine for AI Agent Memory in 6 lines of code

Agentic AI Framework for Java Developers

Incremental engine for long horizon agents 🌟 Star if you like it!

A powerful meta-prompting, context engineering and spec-driven development system that enables agents to work for long periods of time autonomously without losing track of the big picture

MineContext is your proactive context-aware AI partner（Context-Engineering+ChatGPT Pulse）

Agent Skills as a Memory Layer

🔥 Comprehensive survey on Context Engineering: from prompt engineering to production-grade AI systems. hundreds of papers, frameworks, and implementation guides for LLMs and AI agents.

Memory library for building stateful agents

🧠 Make your agents learn from experience. Now available as a hosted solution at kayba.ai

Auto-Manage Your Personal Task Context with AI.

Agent Package Manager

The context development platform. Store, enrich, and retrieve structured knowledge with graph-native infrastructure, semantic retrieval, and portable context cores.

Claude Code learns from your corrections: self-correcting memory that compounds over 50+ sessions. Context engineering, parallel worktrees, agent teams, and 17 battle-tested skills.

Vibe-Skills is an all-in-one AI skills package. It seamlessly integrates expert-level capabilities and context management into a general-purpose skills package， enabling any AI agent to instantly upgrade its functionality—eliminating the friction of fragmented tools and complex harnesses.