Beads provides a persistent, structured memory for AI coding agents, replacing traditional markdown plans with a dependency-aware graph. It excels at managing long-horizon tasks and multi-agent workflows by preserving context and preventing conflicts across sessions.

This repository offers a comprehensive, practical guide to Claude Code, covering everything from initial setup and prompt engineering to advanced topics like Skills, Hooks, MCP, and multi-agent automation. It serves as an invaluable resource for both new users seeking a guided path and power users aiming for in-depth understanding and complex workflow implementation.

This kit provides persistent memory for Claude Code agents, solving the problem of Claude forgetting context between sessions. It features a four-layer memory architecture (daily logs, hot cache, knowledge concepts, rules) and an agent-driven promotion pipeline where patterns observed in conversations are audited and proposed for inclusion in the knowledge base or rules. The "user only talks, agent writes" principle ensures seamless operation. It supports multi-project isolation, offers silent safety hooks, and direct control via slash operators, all stored in plain text files for easy versio