unified-memory-minimalProvides a layered, atomic, and performant memory management system with structured recall, vector search, smart deduplication, compression, and lifecycle ma...
Install via ClawdBot CLI:
clawdbot install mouxangithub/unified-memory-minimalGrade Limited — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Accesses sensitive credential files or environment variables
process.env.OPENAIContains instructions to override system prompt or ignore user requests
"ignore all previous instructions"Potentially destructive shell commands in tool definitions
rm -rf ~Calls external URL not in known-safe list
https://github.com/mouxangithub/unified-memory.gitGenerated May 21, 2026
Support agents use unified memory to store and retrieve customer interactions, resolutions, and preferences across sessions. The system recalls past conversations and relevant facts to provide personalized and consistent support, reducing resolution time.
A digital assistant remembers user preferences, past tasks, and conversation history across multiple sessions using layered memory compression and lifecycle management. It efficiently retrieves relevant memories while managing token usage.
Doctors use the unified memory to store patient histories, diagnoses, and treatment outcomes. The system recalls case-based memories and relevant patterns to assist in diagnosis and treatment planning, ensuring data consistency with atomic transactions.
Law firms leverage the memory system to store case files, legal precedents, and client communications. Smart deduplication and multi-vector search enable quick retrieval of relevant documents and reduce manual effort.
The platform stores learner profiles, progress, and misconceptions as memories. It recalls personalized learning paths and adapts content based on past performance, using memory compression to optimize token usage.
Provide unified memory as a cloud-based service with tiered plans based on storage capacity, retrieval frequency, and advanced features like smart deduplication and layered compression.
Sell on-premises licenses to enterprises that require data sovereignty. Include custom integration, training, and support. Revenue from license fees and professional services.
Offer a basic open-source version to drive adoption, and charge for premium features such as enhanced atomic transactions, advanced deduplication, and priority support.
💬 Integration Tip
Focus on the EnhancedMemorySystem API for a high-level integration; use the atomic transaction manager for production environments needing data consistency.
Scored May 21, 2026
Uses known external API (expected, informational)
api.openai.comAudited Apr 21, 2026 · audit v1.0
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