An AI agent can remember important things across sessions using a tool called mem. It stores notes, facts, decisions, code snippets, and even images in a local database. The stored information can be searched quickly with full-text search.
This tool helps the agent avoid asking the same questions again. It can recall user preferences, project decisions, or technical details. The agent can also attach images like screenshots or diagrams to its memories.
Using mem is simple. The agent adds memories with a plus sign, searches with words, and forgets with a minus sign. It organizes memories with tags like prefs or deploy for easy filtering.
Global
mkdir -p ~/.claude/skills/memProject
mkdir -p .claude/skills/memObsidian 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