An AI agent can forget important details between conversations. This skill helps the agent remember by storing facts, preferences, and project notes in a local database. It uses smart search to find the right memories before each reply.
You can set up hybrid retrieval that combines vector search with text matching. A reranker then picks the most useful memories. The system can automatically capture and organize information from your chats. It also supports multiple scopes so different agents or users keep their own memory.
Getting started is simple with a one-click setup script or through the OpenClaw CLI. The configuration has sensible defaults so the agent learns from conversations right away. This makes your agent smarter and more consistent over time.
Global
mkdir -p ~/.claude/skills/memory-lancedb-pro-openclawProject
mkdir -p .claude/skills/memory-lancedb-pro-openclawSource Repository
Compressjuliusbrussee/caveman
Shrink memory files into caveman speak to save tokens and preserve code
Obsidian Baseskepano/obsidian-skills
Build powerful database views inside Obsidian with filters formulas and summaries
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
Claude Md Improveranthropics/claude-plugins-official
Audit your CLAUDE.md files for better AI agent project memory
Dbs Restoredontbesilent2025/dbskill
Continue your diagnosis where you last left off without repeating yourself
Winmd Api Searchgithub/awesome-copilot
Find Windows APIs easily with complete methods, properties, and events
Mem Searchthedotmack/claude-mem
Easily search past work across all sessions then filter before fetching details