AI agents need a way to remember important things like past decisions and design patterns. This skill gives them a persistent memory bank that stores knowledge and lets them search it later. It works alongside project documentation to keep everything in sync.
The memory system runs as a simple server. You can write new memories, read old ones, and search by topic or tags. A dashboard shows how the memory is being used. This helps agents avoid forgetting key information and makes their work more reliable.
Setting it up requires Node.js and a few commands. Once running, the agent can recall architecture choices, technical patterns, and important decisions whenever needed. This makes the agent smarter and more consistent over time.
Global
mkdir -p ~/.claude/skills/agent-memory-mcpProject
mkdir -p .claude/skills/agent-memory-mcpSource Repository
Obsidian Baseskepano/obsidian-skills
Build powerful database views inside Obsidian with filters formulas and summaries
Compressjuliusbrussee/caveman
Shrink memory files into caveman speak to save tokens and preserve code
Dbs Restoredontbesilent2025/dbskill
Continue your diagnosis where you last left off without repeating yourself
Remembergithub/awesome-copilot
Save lessons learned and build a smart knowledge base that grows with you
Remembering Conversationsobra/episodic-memory
Search past conversations to recall decisions, solutions, and avoid repeating mistakes
Rememberrohitg00/agentmemory
Save important insights with tags and recall them later easily
Session Historyrohitg00/agentmemory
See your recent session history in a clean timeline instantly
Recallrohitg00/agentmemory
Quickly recall past sessions and learnings from your agent's memory