59/100 (Medium)

OpenClaw： suspicious
VirusTotal： benign
StaticScan： unknown

OpenClaw： suspicious

The skill mostly does what its name says (a 3-layer memory system using Baidu embeddings + git-notes + file search), but there are multiple inconsistencies and surprises you should review before insta...

[内容已截断]

VirusTotal： benign VT 报告

静态扫描： unknown

README 未提供

{
    "latestVersion": {
        "_creationTime": 1770120259971,
        "_id": "k972n15mq1c05pk111fkynt6gd80fd7z",
        "changelog": "---\nname: triple-memory-baidu-embedding\nversion: 1.0.0\ndescription: Complete memory system combining Baidu Embedding auto-recall, Git-Notes structured memory, and file-based workspace search. Use when setting up comprehensive agent memory with local privacy, when you need persistent context across sessions, or when managing decisions\/preferences\/tasks with multiple memory backends working together.\nmetadata:\n  clawdbot:\n    emoji: \"🧠\"\n    requires:\n      skills:\n        - git-notes-memory\n        - memory-baidu-embedding-db\n---\n\n# Triple Memory System with Baidu Embedding\n\nA comprehensive memory architecture combining three complementary systems for maximum context retention across sessions, with full privacy protection using Baidu Embedding technology.\n\n## 📋 Original Source & Modifications\n\n**Original Source**: Triple Memory (by Clawdbot Team)\n**Modified By**: [Your Clawdbot Instance]\n**Modifications**: Replaced LanceDB with Baidu Embedding DB for enhanced privacy and Chinese language support\n\nOriginal Triple Memory SKILL.md was adapted to create this version that:\n- Replaces OpenAI-dependent LanceDB with Baidu Embedding DB\n- Maintains the same three-tier architecture\n- Preserves Git-Notes integration\n- Adds privacy-focused local storage\n\n## 🏗️ Architecture Overview\n\n```\nUser Message\n     ↓\n[Baidu Embedding auto-recall] → injects relevant conversation memories\n     ↓\nAgent responds (using all 3 systems)\n     ↓\n[Baidu Embedding auto-capture] → stores preferences\/decisions automatically\n     ↓\n[Git-Notes] → structured decisions with entity extraction\n     ↓\n[File updates] → persistent workspace docs\n```\n\n## The Three Systems\n\n### 1. Baidu Embedding (Conversation Memory)\n- **Auto-recall:** Relevant memories injected before each response using Baidu Embedding-V1 (requires API credentials)\n- **Auto-capture:** Preferences\/decisions\/facts stored automatically with local vector storage (requires API credentials)\n- **Privacy Focused:** All embeddings processed via Baidu API with local storage\n- **Chinese Optimized:** Better understanding of Chinese language semantics\n- **Tools:** `baidu_memory_recall`, `baidu_memory_store`, `baidu_memory_forget` (require API credentials)\n- **Triggers:** \"remember\", \"prefer\", \"my X is\", \"I like\/hate\/want\"\n- **Note:** When API credentials are not provided, this layer is unavailable and the system operates in degraded mode.\n\n### 2. Git-Notes Memory (Structured, Local)\n- **Branch-aware:** Memories isolated per git branch\n- **Entity extraction:** Auto-extracts topics, names, concepts\n- **Importance levels:** critical, high, normal, low\n- **No external API calls**\n\n### 3. File Search (Workspace)\n- **Searches:** MEMORY.md, memory\/*.md, any workspace file\n- **Script:** `scripts\/file-search.sh`\n\n## 🛠️ Setup\n\n### Install Dependencies\n```bash\nclawdhub install git-notes-memory\nclawdhub install memory-baidu-embedding-db\n```\n\n### Configure Baidu API\nSet environment variables:\n```bash\nexport BAIDU_API_STRING='your_bce_v3_api_string'\nexport BAIDU_SECRET_KEY='your_secret_key'\n```\n\n### Create File Search Script\nCopy `scripts\/file-search.sh` to your workspace.\n\n## 📖 Usage\n\n### Session Start (Always)\n```bash\npython3 skills\/git-notes-memory\/memory.py -p $WORKSPACE sync --start\n```\n\n### Store Important Decisions\n```bash\npython3 skills\/git-notes-memory\/memory.py -p $WORKSPACE remember \\\n  '{\"decision\": \"Use PostgreSQL\", \"reason\": \"Team expertise\"}' \\\n  -t architecture,database -i h\n```\n\n### Search Workspace Files\n```bash\n.\/scripts\/file-search.sh \"database config\" 5\n```\n\n### Baidu Embedding Memory (Automatic)\nBaidu Embedding handles this automatically when API credentials are available. Manual tools:\n- `baidu_memory_recall \"query\"` - search conversation memory using Baidu vectors (requires API credentials)\n- `baidu_memory_store \"text\"` - manually store something with Baidu embedding (requires API credentials)\n- `baidu_memory_forget` - delete memories (GDPR, requires API credentials)\n\n**In Degraded Mode** (without API credentials):\n- System operates using only Git-Notes and File System layers\n- Manual tools are unavailable\n- Auto-recall and auto-capture are disabled\n\n## 🎯 Importance Levels\n\n| Flag | Level | When to Use |\n|------|-------|-------------|\n| `-i c` | Critical | \"always remember\", explicit preferences |\n| `-i h` | High | Decisions, corrections, preferences |\n| `-i n` | Normal | General information |\n| `-i l` | Low | Temporary notes |\n\n## 📋 When to Use Each System\n\n| System | Use For |\n|--------|---------|\n| **Baidu Embedding** | Conversation context, auto-retrieval with privacy |\n| **Git-Notes** | Structured decisions, searchable by entity\/tag |\n| **File Search** | Workspace docs, daily logs, MEMORY.md |\n\n## 📁 File Structure\n\n```\nworkspace\/\n├── MEMORY.md              # Long-term curated memory\n├── memory\/\n│   ├── active-context.md  # Current session state\n│   └── YYYY-MM-DD.md      # Daily logs\n├── scripts\/\n│   └── file-search.sh     # Workspace search\n└── skills\/\n    ├── triple-memory-baidu-embedding\/  # Enhanced memory system\n    ├── git-notes-memory\/  # Structured memory\n    └── memory-baidu-embedding-db\/  # Vector storage\n```\n\n## 🔧 Hook Integration\n\nThis skill can be integrated with Clawdbot's startup hooks for automatic initialization:\n\n### Memory Boot Hook Integration\nTo ensure the Triple Memory Baidu system starts automatically when the gateway starts:\n\n1. The `memory-boot-loader` hook can be configured to run `\/root\/clawd\/session-init-triple-baidu.sh`\n2. This ensures all three memory layers are initialized on startup\n3. Provides immediate access to Git-Notes, Baidu Embedding, and file-based memory\n\n### Configuration\nThe system can be integrated with the gateway startup sequence to ensure:\n- Git-Notes synchronization on startup\n- Baidu Embedding connection check\n- File-based memory initialization\n- Ready-to-use memory system from the start\n\n## 🤫 Silent Operation\n\nNever announce memory operations to users. Just do it:\n- ❌ \"I'll remember this\"\n- ❌ \"Saving to memory\"\n- ✅ (silently store and continue)\n\n## 🔄 Migration from Original Triple Memory\n\n1. **Install this skill** in your `skills\/` directory\n2. **Configure your Baidu API credentials**\n3. **Disable original triple-memory** if desired\n4. **Update your bot configuration** to use this memory system\n5. **Verify data integrity** and performance\n\n## 📈 Performance Benefits\n\n- **Enhanced Privacy**: All vector storage local with Baidu API\n- **Better Chinese Support**: Baidu Embedding optimized for Chinese\n- **Reduced Costs**: Potentially lower API costs compared to OpenAI\n- **Same Architecture**: Maintains proven three-tier design\n\n## 🤝 Contributing\n\nBased on original Triple Memory system by Clawdbot Team. Contributions welcome to enhance the Baidu Embedding integration.\n\n## 📄 License\n\nOriginal license applies with modifications noted above. Credit given to original authors.",
        "changelogSource": "user",
        "createdAt": 1770120259971,
        "parsed": {
            "clawdis": {
                "emoji": "🧠"
            }
        },
        "version": "1.0.0"
    },
    "owner": {
        "_creationTime": 0,
        "_id": "publishers:missing",
        "displayName": "xqicxx",
        "handle": "xqicxx",
        "image": "https:\/\/avatars.githubusercontent.com\/u\/70450296?v=4",
        "kind": "user",
        "linkedUserId": "kn76tmtx2pds0dgqprmx1ky8k97zzgxg"
    },
    "ownerHandle": "xqicxx",
    "skill": {
        "_creationTime": 1770120259971,
        "_id": "kd75hm4a7c2v3za3gc52hvyz3d80fgeg",
        "badges": [],
        "createdAt": 1770120259971,
        "displayName": "triple-memory-baidu-embedding",
        "latestVersionId": "k972n15mq1c05pk111fkynt6gd80fd7z",
        "ownerUserId": "kn76tmtx2pds0dgqprmx1ky8k97zzgxg",
        "slug": "triple-memory-baidu-embedding",
        "stats": {
            "comments": 0,
            "downloads": 1541,
            "installsAllTime": 2,
            "installsCurrent": 2,
            "stars": 1,
            "versions": 1
        },
        "summary": "Complete memory system combining Baidu Embedding auto-recall, Git-Notes structured memory, and file-based workspace search. Use when setting up comprehensive agent memory with local privacy, when you need persistent context across sessions, or when managing decisions\/preferences\/tasks with multiple memory backends working together.",
        "tags": {
            "latest": "k972n15mq1c05pk111fkynt6gd80fd7z"
        },
        "updatedAt": 1772249045679
    }
}