[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77MT2MKWH8MZHMX89DHMXAD":3,"skill-same:01M77MT2MKWH8MZHMX89DHMXAD":45},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":20,"frontMatter":21,"refName":22,"commitSha":23,"skillDirectory":24,"forksCount":25,"repositoryHtmlUrl":26,"repositoryHomepageUrl":27,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":29,"updatedAt":30,"install":31,"resources":44},"01M77MT2MKWH8MZHMX89DHMXAD","memcore",null,"Lord1Egypt\u002Fawesome-skill-forge","Lord1Egypt","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F99746359?v=4","01M7592YDNT0XK9WJ0T2MQVPDN","Mohamed Mounir Ali AL Keshita","01M75GRFNHC8VZNWEB8DKDE433",3,"MIT","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fm\u002Fmemcore\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"# MemCore Enhanced - 增强版五层记忆系统\n\n> 基于原版 MemCore，新增四大核心功能：情景记忆、语义压缩、记忆触发器、遗忘曲线\n\n## 架构概览\n\n```\n┌─────────────────────────────────────────────────────┐\n│  Context Memory    - 当前对话 (秒-分钟级)    │ 原有\n│  (滑动窗口 + Token限制)                 │\n├─────────────────────────────────────────────────────┤\n│  Task Memory       - 任务状态 (分钟-小时级)   │ 原有\n│  (状态机管理)                           │\n├─────────────────────────────────────────────────────┤\n│  User Memory       - 用户偏好 (持久化)    │ 原有\n│  (版本控制)                             │\n├─────────────────────────────────────────────────────┤\n│  Knowledge Memory  - 外部知识 (持久化)    │ 原有\n│  (向量检索)                             │\n├─────────────────────────────────────────────────────┤\n│  Experience Memory - 执行历史 (长期)      │ 原有\n│  (强化学习)                             │\n├─────────────────────────────────────────────────────┤\n│  ✨ 新增四大功能                            │ 增强\n├─────────────────────────────────────────────────────┤\n│  Episodic Memory   - 情景记忆 (事件\u002F结论)  │ ✓ 新增\n│  (上次讨论X时，结论是Y)               │\n├─────────────────────────────────────────────────────┤\n│  Semantic          - 语义压缩              │ ✓ 新增\n│  Compression       (10条→1条摘要)          │\n├─────────────────────────────────────────────────────┤\n│  Memory Triggers   - 记忆触发器            │ ✓ 新增\n│  (关键词→自动加载相关记忆)                │\n├─────────────────────────────────────────────────────┤\n│  Forgetting Curve  - 遗忘曲线              │ ✓ 新增\n│  (艾宾浩斯遗忘模型)                     │\n└─────────────────────────────────────────────────────┘\n│  🔧 额外增强功能                           │\n├─────────────────────────────────────────────────────┤\n│  Persistent Storage - SQLite持久化          │ ✓ 新增\n│  Vector Knowledge   - 向量语义检索        │ ✓ 新增\n│  Conflict Resolver  - 智能冲突解决        │ ✓ 新增\n│  Confidence Tracker - 记忆置信度跟踪      │ ✓ 新增\n└─────────────────────────────────────────────────────┘\n```\n\n## 快速开始\n\n### 安装依赖\n\n```bash\npip install numpy\n```\n\n### 基本使用\n\n```python\nfrom memcore_enhanced import MemCoreEnhanced, MemoryPriority, MemorySource\n\n# 初始化（启用持久化）\nmc = MemCoreEnhanced(db_path=\"~\u002F.memcore\u002Fmemory.db\")\n\n# 记录情景记忆\nepisode_id = mc.record_episode(\n    episode_type=\"discussion\",\n    context_summary=\"用户询问优化建议\",\n    conclusion=\"建议添加四个新功能\",\n    related_topics=[\"MemCore\", \"AI记忆\"],\n    priority=MemoryPriority.HIGH,\n    confidence=1.0,\n    source=MemorySource.EXPLICIT\n)\n\n# 查询时触发相关记忆\nresult = mc.process_input(\"我想继续弄MemCore\")\nprint(result['suggested_context'])\n```\n\n## 核心功能详解\n\n### 1. Episodic Memory (情景记忆)\n\n记录具体事件和结论，支持自然语言回忆。\n\n```python\n# 记录情景\nmc.record_episode(\n    episode_type=\"discussion\",  # discussion | decision | event\n    context_summary=\"用户询问优化建议\",\n    conclusion=\"建议添加四个模块\",\n    related_topics=[\"MemCore\", \"AI记忆\"],\n    participants=[\"user\", \"assistant\"],\n    priority=MemoryPriority.HIGH\n)\n\n# 回忆相关情景\nepisodes = mc.recall_episodes(topic=\"MemCore\", limit=5)\nfor ep in episodes:\n    print(ep.to_natural_language())\n    # 输出: [2025-01-13 14:30] discussion: 关于 '用户询问优化建议' 的讨论，结论是：建议添加四个模块\n```\n\n### 2. Semantic Compression (语义压缩)\n\n自动压缩冗余信息，保持上下文窗口精简。\n\n```python\n# 添加大量对话上下文\nfor msg in conversation:\n    mc.add_to_context(msg)\n\n# 超过20条消息时自动触发压缩\nmc.compress_memories(\"context\")\n# 压缩后保留: [最近2条, {摘要}]\n```\n\n### 3. Memory Triggers (记忆触发器)\n\n关键词触发，自动加载相关背景。\n\n```python\n# 创建触发器（也会自动根据情景记忆创建）\nmc.create_trigger(\n    keywords=[\"项目X\", \"Project X\"],\n    target_memory_ids=[\"ep_abc123\", \"user_pref_456\"]\n)\n\n# 处理用户输入\nresult = mc.process_input(\"我想继续搞项盯x\")\n# 返回: {\n#   \"triggered\": True,\n#   \"loaded_memories\": [...],\n#   \"suggested_context\": \"...\",\n#   \"related_knowledge\": [...]\n# }\n```\n\n### 4. Forgetting Curve (遗忘曲线)\n\n模拟艾宾浩斯遗忘曲线，智能清理低价值记忆。\n\n```python\n# 运行遗忘周期（通常每天运行一次）\nresult = mc.run_forgetting_cycle()\n# 返回: {\n#   \"checked\": 100,      # 检查的记忆数\n#   \"deleted\": 5,        # 删除的记忆数\n#   \"deleted_ids\": [...]\n# }\n\n# 查看记忆健康报告\nhealth = mc.get_health_report()\n```\n\n**Forgetting Score 计算:**\n```\n9057忘分数 = 1 - R(t)\nR(t) = e^(-t\u002FS) + 最近访问奖励 - 压缩惩罚\n\nS = 优先级 × (1 + 访问次数 × 0.1)  # 记忆强度\n```\n\n### 5. Persistent Storage (持久化存储)\n\nSQLite 数据库持久化存储，支持跨会话记忆。\n\n```python\n# 初始化时指定数据库路径\nmc = MemCoreEnhanced(db_path=\"~\u002F.memcore\u002Fmemory.db\")\n\n# 所有操作自动持久化\n# - 情景记忆\n# - 用户偏好\n# - 触发器\n# - 任务状态\n\n# 重启后自动恢复\nmc2 = MemCoreEnhanced(db_path=\"~\u002F.memcore\u002Fmemory.db\")\n# 所有记忆已加载\n```\n\n### 6. Vector Knowledge (向量知识检索)\n\n语义相似度检索，无需精确关键词匹配。\n\n```python\n# 添加知识\nmc.add_knowledge(\n    content=\"MemCore 采用五层记忆架构\",\n    metadata={\"topics\": [\"architecture\", \"MemCore\"]},\n    source=\"docs\"\n)\n\n# 语义查询\nresults = mc.query_knowledge(\"记忆系统怎么设计的？\")\n# 返回高相似度结果，即使关键词不完全匹配\n```\n\n支持外部 Embedding 模型：\n\n```python\nfrom vector_knowledge import OpenAIEmbeddingWrapper\n\nmc = MemCoreEnhanced(\n    embedding_fn=OpenAIEmbeddingWrapper(api_key=\"sk-...\")\n)\n```\n\n### 7. Conflict Resolution (记忆冲突解决)\n\n自动检测并解决新旧记忆矛盾。\n\n```python\n# 当记录新记忆时自动检测冲突\nmc.record_episode(\n    context_summary=\"用户偏好\",\n    conclusion=\"用户喜欢Python\"\n)\n\nmc.record_episode(\n    context_summary=\"用户偏好\",\n    conclusion=\"用户讨厌Python\"  # 检测到矛盾！\n)\n\n# 解决策略:\n# - TIME_PRIORITY: 新的覆盖旧的\n# - CONFIDENCE_PRIORITY: 高置信度优先\n# - MERGE: 尝试合并\n# - KEEP_BOTH: 保留两者\n```\n\n### 8. Confidence Tracking (记忆置信度跟踪)\n\n每条记忆都有置信度和来源溯源。\n\n```python\n# 注册时指定来源和置信度\nmc.record_episode(\n    context_summary=\"用户告知姓名\",\n    conclusion=\"用户叫露丝\",\n    confidence=1.0,\n    source=MemorySource.EXPLICIT  # 用户明确说的\n)\n\n# 用户验证增加置信度\nmc.confidence_tracker.verify(\"ep_xxx\", verifier=\"user\")\n\n# 用户否认降低置信度\nmc.confidence_tracker.contradict(\"ep_xxx\", reason=\"姓名错误\")\n\n# 查看置信度报告\nreport = mc.confidence_tracker.get_confidence_report(\"ep_xxx\")\n# {\n#   \"effective_confidence\": 0.95,\n#   \"trust_level\": \"💚 高度可信\"\n# }\n```\n\n## 高级使用\n\n### 与原版 MemCore 兼容\n\n```python\n# 也可以单独使用原有层\nfrom memcore_enhanced import ContextMemory, TaskMemory, UserMemory\n\ncontext = ContextMemory(max_messages=20, max_tokens=4000)\ncontext.add_message(\"user\", \"Hello\")\nmessages = context.get_context()\n```\n\n### 用户偏好管理\n\n```python\n# 更新用户偏好\nmc.update_user_preference(\n    user_id=\"user_123\",\n    key=\"response_style\",\n    value=\"concise\",\n    confidence=1.0,\n    source=MemorySource.EXPLICIT\n)\n\n# 查询用户偏好\nprefs = mc.backend.load_user_memory(\"user_123\")\n```\n\n### 健康监控\n\n```python\n# 获取系统健康报告\nhealth = mc.get_health_report()\n# {\n#   \"episodic_memory\": {\"count\": 100, \"by_priority\": {...}},\n#   \"triggers\": {\"count\": 20, \"total_triggered\": 150},\n#   \"knowledge\": {...},\n#   \"database\": {...}\n# }\n\n# 查看低置信度记忆\nlow_conf = mc.confidence_tracker.get_low_confidence_memories(threshold=0.5)\n```\n\n## API 参考\n\n### MemCoreEnhanced\n\n主要类，提供统一入口。\n\n**Methods:**\n- `record_episode(...)` - 记录情景\n- `recall_episodes(...)` - 回忆情景\n- `create_trigger(...)` - 创建触发器\n- `process_input(text)` - 处理输入\n- `add_knowledge(...)` - 添加知识\n- `query_knowledge(...)` - 查询知识\n- `run_forgetting_cycle()` - 运行遗忘\n- `get_health_report()` - 健康报告\n\n### 枚举类\n\n**MemoryPriority:** `CRITICAL`, `HIGH`, `MEDIUM`, `LOW`, `EPHEMERAL`\n\n**MemorySource:** `EXPLICIT`, `IMPLICIT`, `INFERRED`, `IMPORTED`, `DERIVED`\n\n**ConflictStrategy:** `TIME_PRIORITY`, `CONFIDENCE_PRIORITY`, `MERGE`, `KEEP_BOTH`, `MANUAL_REVIEW`\n\n## 性能指标\n\n| 操作 | 复杂度 |\n|------|--------|\n| 记录情景 | O(1) |\n| 回忆查询 | O(n) |\n| 触发器检查 | O(m×k) |\n| 向量检索 | O(n) |\n| 数据库查询 | O(log n) |\n\n## 版本历史\n\n- **v0.2.0** - 增强版\n  - 新增情景记忆\n  - 新增语义压缩\n  - 新增记忆触发器\n  - 新增遗忘曲线\n  - 新增SQLite持久化\n  - 新增向量检索\n  - 新增冲突解决\n  - 新增置信度跟踪\n\n- **v0.1.0** - 原版\n  - 五层记忆架构\n\n## 贡献者\n\n- 原版架构: [@laojun509](https:\u002F\u002Fclawhub.ai\u002Flaojun509\u002Fmemcore)\n- 增强版协助: Hermes Agent (露丝)\n\n## 许可证\n\nMIT-0 - 完全开源，可自由使用、修改和分发\n",{},"master","4aa004da461d820f4ea5499e58eb8d196cf99016","community\u002Fclawhub\u002Fm\u002Fmemcore",0,"https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge","https:\u002F\u002Fskill-explorer-rho.vercel.app","https:\u002F\u002Fgithub.com\u002FLord1Egypt","Unbreakable. Unstoppable. Unmatched⚡.\r\n Speaker of machine tongues 🤖  | World-builder of decentralized dreams 🌐 | Defender of the digital realm🛡️.","2026-06-10 08:21:01",{"source":7,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add Lord1Egypt\u002Fawesome-skill-forge --skill memcore",{"tool":37,"command":38},"bunx","bunx skills add Lord1Egypt\u002Fawesome-skill-forge --skill memcore",{"tool":40,"command":41},"pnpm","pnpm dlx skills add Lord1Egypt\u002Fawesome-skill-forge --skill memcore","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fm\u002Fmemcore\u002FSKILL.md",true,[],[46,53,60,67,74,81],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":18},"01M785WKJB99G3STR1NF9NRTJW","youtube-content","YouTube transcripts to summaries, threads, blogs.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fyoutube-content\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":18},"01M785WEFHB0G2S9YA6EPR3H0E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fxurl\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":18},"01M785W98EDN4EFJXJPMQEHCRC","touchdesigner-mcp","Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftouchdesigner-mcp\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":18},"01M785W5S9FP3QBH2V191E025P","test-driven-development","TDD: enforce RED-GREEN-REFACTOR, tests before code.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":18},"01M785W2AS08NSSH9YATCV6FJB","teams-meeting-pipeline","Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fteams-meeting-pipeline\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":18},"01M785VXKW4T34BTP1SCHW1R7F","systematic-debugging","4-phase root cause debugging: understand bugs before fixing.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fsystematic-debugging\u002FSKILL.md",[],[]]