Memory files help Claude remember important details across sessions. They can get cluttered with old rules and duplicates. This tool cleans them up in four simple steps.
First it finds and removes duplicate information. Then it moves rules into the right config files. Next it compresses what remains into shorter form. Finally it checks everything is correct.
Users often see a 30 to 50 percent reduction in token count. That means faster loading and lower costs. The process is interactive so you stay in control.
Global
mkdir -p ~/.claude/skills/memory-optimizeProject
mkdir -p .claude/skills/memory-optimizeSource 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