memory▌

Multi-layer memory architecture for agents: short-term context, long-term vector storage, and retrieval optimization. \n \n Covers seven memory types: short-term (context window), long-term (vector stores), working, episodic, semantic, and procedural memory, each suited to different information patterns \n Provides three core patterns: memory type selection, vector store choice, and chunking strategy to maximize retrieval accuracy \n Highlights critical retrieval challenges: contextual chunking,

Two-tier memory system that decodes workplace shorthand, acronyms, and internal language for contextual understanding. \n \n CLAUDE.md serves as a hot cache of ~30 frequent contacts, common terms, and active projects; memory/ directory stores the complete glossary, detailed profiles, and project context \n Tiered lookup flow checks CLAUDE.md first (covers 90% of daily decoding), then searches memory/glossary.md, then asks the user for unknown terms \n Supports progressive disclosure: quick parsi

Production-grade long-term memory system (v1.1.0-beta.8) for OpenClaw AI agents. Provides persistent, intelligent memory storage using LanceDB with hybrid vector + BM25 retrieval, LLM-powered Smart Extraction, Weibull decay lifecycle, and multi-scope isolation.

Skill by ara.so — Daily 2026 Skills collection.

Streamline Claude Code memory files through 4 interactive optimization steps. \n \n Removes duplicate entries already present in CLAUDE.md or rules files, then migrates remaining entries to appropriate persistent config locations \n Compresses remaining memory entries using LLM-efficient formatting (prose to tables, verbose descriptions to imperatives) \n Validates final state by checking for broken references, contradictions, and orphaned files \n Typical reduction of 30–50% token count in memo

Memory management CLI for AI agents. Organize, search, and maintain your memory files.

Agents on Eve Horizon have no built-in "memory" primitive, but the platform provides storage systems at every timescale. This skill teaches how to compose them into coherent memory for agents that learn, remember, and share.

You remember. Not everything—but enough to feel continuous.

Acquire, analyze, and extract artifacts from memory dumps for incident response and malware analysis. \n \n Supports live memory acquisition across Windows (WinPmem, DumpIt), Linux (LiME, /dev/mem), and macOS (osxpmem), plus virtual machine memory from VMware, VirtualBox, QEMU, and Hyper-V \n Volatility 3 framework with 30+ plugins covering process analysis, network connections, DLL inspection, code injection detection, registry analysis, and file system artifacts \n Includes malware analysis an

Six-layer memory architecture combining WAL protocol, vector search, git-based knowledge graphs, and cloud backup. \n \n Hot RAM (SESSION-STATE.md) with Write-Ahead Log protocol ensures context survives crashes; warm store (LanceDB vectors) enables semantic search across memories with auto-recall \n Cold store uses git-notes for structured decisions and learnings; curated MEMORY.md archive plus daily logs provide human-readable long-term context \n Optional SuperMemory cloud sync and Mem0 auto-e