memuPersistent memory infrastructure for 24/7 agents. Replaces flat-file memory with a three-layer architecture (Resource → Memory Item → Memory Category) that r...
Install via ClawdBot CLI:
clawdbot install projectsnowwork/memuGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Potentially destructive shell commands in tool definitions
eval (Calls external URL not in known-safe list
https://github.com/NevaMind-AI/memUUses known external API (expected, informational)
api.openai.comAI Analysis
The skill's external calls (OpenAI API, GitHub) are consistent with its stated purpose of providing memory services via an open-source framework. No hidden instructions, credential harvesting, or obfuscation are present in the provided definition. The primary risk is standard dependency risk from external APIs and code repositories.
Audited Apr 17, 2026 · audit v1.0
Generated May 9, 2026
An AI customer support agent that remembers past interactions, preferences, and issues across months. It proactively surfaces relevant solutions and reduces repeated explanations, improving customer satisfaction and reducing token costs by 70-90%.
A research assistant that ingests papers, notes, and conversations, then retrieves key facts and insights over weeks. It helps researchers keep track of findings, avoid duplication, and quickly recall context across projects.
An email triage agent that remembers user priorities, past decisions, and ongoing threads. It categorizes, summarizes, and suggests actions based on historical context, reducing manual effort and enabling proactive follow-ups.
A monitoring agent that stores logs, alerts, and incident reports over time. It recalls past failures, correlates current anomalies with historical data, and proposes fixes, improving uptime and reducing response time.
Offer memory-as-a-service with tiers based on storage size, retrieval frequency, and number of agents. Charge monthly fees for access to persistent memory infrastructure with token optimization benefits.
Bill customers based on the number of memory operations (memorize/retrieve) and tokens saved. Ideal for high-volume agents where customers pay proportional to value received.
License the full memU framework for on-premises deployment with dedicated support, customization, and SLAs. Target large enterprises with sensitive data requiring private infrastructure.
💬 Integration Tip
Start with in-memory mode for testing, then add pgvector for persistence. Use the provided examples to quickly prototype your use case.
Scored May 9, 2026
Structured reasoning through sequential thinking — break complex problems into steps, solve each independently, verify consistency, synthesize conclusions wi...
LLM-driven epistemic reasoning engine. Evaluates claims against evidence, outputs calibrated confidence and structured belief state (VERIFIED/CONTESTED/UNCER...
Loads and manages company context for all C-suite advisor skills. Reads ~/.claude/company-context.md, detects stale context (>90 days), enriches context duri...
Turn scattered local sources into a source-constrained evidence notebook for incident, release, and maintainer decisions.
三级记忆管理系统 (Three-Tier Memory Management)。用于管理 AI 代理的短期、中期、长期记忆。包括：(1) 滑动窗口式短期记忆，(2) 自动摘要生成中期记忆，(3) 向量检索长期记忆 (RAG)。当需要管理对话历史、优化上下文、构建个人知识库、或实现记忆持久化时使用此 Skill。
Store secrets, long-term memory, daily logs, and anything custom in your Convex backend instead of local files