mnemo完整的记忆系统 - 文件系统记忆 + 支持搜索 + 自动加载 + 内存刷新
Install via ClawdBot CLI:
clawdbot install minmengxhw-cpu/mnemoGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://ollama.comAudited Apr 16, 2026 · audit v1.0
Generated Mar 21, 2026
Individuals use this skill to maintain a private, searchable journal of daily thoughts, ideas, and reflections stored locally. The semantic search helps recall specific past entries or themes, while automatic loading ensures context is available at the start of each session. This is ideal for personal knowledge management without cloud dependency.
Software development teams utilize the skill to document project requirements, decisions, and user preferences in Markdown files per project group. The semantic search allows quick retrieval of past discussions, and safeguard flushing prevents loss of critical context during long coding sessions. Group isolation keeps different project memories separate.
Support agents in small to medium businesses use this to store and recall customer interaction histories locally. Each customer or ticket can be a separate group, with semantic search helping find relevant past solutions. The automatic loading ensures agents have immediate context when resuming conversations, improving response accuracy.
Researchers and students employ the skill to organize notes, literature summaries, and experimental data in Markdown files. Semantic search aids in connecting ideas across documents, while the file-based system allows easy manual editing and backup. Group isolation can separate different research projects or subjects.
Writers and content creators use the memory system to store character profiles, plot points, and world-building details. Semantic search helps maintain consistency by recalling earlier elements, and the safeguard flush ensures no creative ideas are lost during long writing sessions. The Markdown format allows easy integration with other writing tools.
Offer a basic version of the memory skill for free within an AI assistant platform, then charge for advanced features like enhanced semantic search models, cloud backup synchronization, or team collaboration tools. Revenue comes from subscription tiers based on usage limits or premium integrations.
License the skill as part of a larger AI toolkit for businesses requiring local data storage for compliance or security. Provide customization, dedicated support, and integration services. Revenue is generated through one-time licensing fees, annual maintenance contracts, and professional services for deployment.
Package the skill as a standalone library or API that developers can integrate into their own applications. Monetize through a tiered pricing model based on API call volume, number of users, or advanced features like custom embedding models. Offer documentation, SDKs, and community support to drive adoption.
💬 Integration Tip
Ensure Ollama is installed and running locally if semantic search is required; otherwise, the skill defaults to keyword matching. Configure memoryDir with proper write permissions and consider using safeguard flush mode for reliable data persistence.
Scored Jun 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