rookie-memoryRookie-Memory 三级记忆管理系统 v2.0。专为 AI 代理设计的进化版记忆系统,包含 L0 永久记忆、L1 短期记忆、L2 中期记忆,支持 bootstrap 启动加载、autosave 自动保存、混合检索、自动清理等高级功能。
Install via ClawdBot CLI:
clawdbot install rrrker/rookie-memoryGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://open.bigmodel.cn/api/paas/v4Audited Apr 18, 2026 · audit v1.0
Generated Mar 22, 2026
AI agents use the memory system to maintain context across customer interactions, storing preferences and past issues in long-term memory for personalized support. The sliding window ensures recent conversation flow, while automatic summaries compress lengthy support histories.
The system manages user habits, schedules, and preferences across sessions, with L0 storing stable identity data and L3 enabling semantic retrieval for dynamic tasks. Daily logs and health analysis help optimize memory usage over time.
Tutors track student progress, learning gaps, and session summaries using the three-tier memory, with medium-term summaries condensing lesson content and long-term storage for curriculum adaptation. Conflict resolution ensures accurate knowledge retention.
AI agents monitor patient symptoms and treatment responses, storing critical decisions in L0 and using vector retrieval for similar case histories. The cleanup feature removes outdated data to maintain compliance and relevance.
Agents manage project timelines, decisions, and team communications, with key decisions automatically logged and hybrid retrieval aiding in task prioritization. Health analysis identifies redundant or obsolete project notes.
Offer the memory system as a cloud-based service with tiered plans based on storage capacity and advanced features like health analysis. Revenue comes from monthly or annual subscriptions for businesses integrating AI agents.
Sell on-premise licenses to large organizations requiring data privacy, with customization for specific industries and premium support. Revenue is generated through one-time license fees and ongoing maintenance contracts.
Provide a free basic version with limited memory tiers and charge for advanced features like automated cleanup, hybrid retrieval, and detailed analytics. Revenue streams from upgrades and add-on modules.
💬 Integration Tip
Ensure ChromaDB dependencies are installed in a virtual environment, and configure YAML files before initializing the memory system to avoid runtime errors.
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