Install via ClawdBot CLI:
clawdbot install lizhelong0907/memory-engineGrade Limited — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Potentially destructive shell commands in tool definitions
exec(Calls external URL not in known-safe list
https://github.com/lizhelong0907/memory-engine.gitAI Analysis
The skill definition describes a local memory system using SQLite and ONNX models, with no evidence of sending data to external servers. The only external reference is the GitHub repository for installation, which is expected. The primary risk is the potential for unsafe shell commands in the underlying code, but the definition itself does not reveal hidden data exfiltration or credential harvesting.
Audited Apr 16, 2026 · audit v1.0
Generated Mar 21, 2026
Integrate Memory Engine into a customer support chatbot to store user preferences and past issues, enabling personalized responses and faster resolution by recalling previous interactions without manual lookup.
Use the plugin in an educational AI to track student progress, store learned concepts, and adapt lessons based on memory of past difficulties and preferences, improving engagement and outcomes.
Deploy Memory Engine in a healthcare app to log patient symptoms, treatment responses, and preferences over time, aiding in continuity of care and personalized health recommendations.
Implement the plugin to analyze customer interactions, save purchase history and preferences, and enhance product recommendations through semantic search of stored memories for better sales.
Incorporate into project management software to automatically extract and store key decisions, lessons learned, and team preferences from discussions, facilitating knowledge retention and team collaboration.
Offer Memory Engine as a cloud-based service with tiered pricing based on storage capacity and API calls, targeting businesses needing scalable AI memory solutions without infrastructure management.
Sell on-premise licenses to large organizations requiring data privacy and customization, including support and integration services for seamless deployment in regulated industries.
Provide a free basic version with limited features to attract individual developers and small teams, then upsell to premium plans with advanced capabilities like increased memory types and priority support.
💬 Integration Tip
Start by integrating the memory_save tool in OpenClaw to log key user interactions, then use memory_search for retrieval to enhance context without overcomplicating initial setup.
Scored Apr 19, 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