triple-memory-baidu-embeddingComplete 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.
Install via ClawdBot CLI:
clawdbot install xqicxx/triple-memory-baidu-embeddingA comprehensive memory architecture combining three complementary systems for maximum context retention across sessions, with full privacy protection using Baidu Embedding technology.
Original Source: Triple Memory (by Clawdbot Team)
Modified By: [Your Clawdbot Instance]
Modifications: Replaced LanceDB with Baidu Embedding DB for enhanced privacy and Chinese language support
Original Triple Memory SKILL.md was adapted to create this version that:
User Message
↓
[Baidu Embedding auto-recall] → injects relevant conversation memories
↓
Agent responds (using all 3 systems)
↓
[Baidu Embedding auto-capture] → stores preferences/decisions automatically
↓
[Git-Notes] → structured decisions with entity extraction
↓
[File updates] → persistent workspace docsbaidu_memory_recall, baidu_memory_store, baidu_memory_forget (require API credentials)scripts/file-search.shclawdhub install git-notes-memory
clawdhub install memory-baidu-embedding-dbSet environment variables:
export BAIDU_API_STRING='your_bce_v3_api_string'
export BAIDU_SECRET_KEY='your_secret_key'Copy scripts/file-search.sh to your workspace.
python3 skills/git-notes-memory/memory.py -p $WORKSPACE sync --startpython3 skills/git-notes-memory/memory.py -p $WORKSPACE remember \
'{"decision": "Use PostgreSQL", "reason": "Team expertise"}' \
-t architecture,database -i h./scripts/file-search.sh "database config" 5Baidu Embedding handles this automatically when API credentials are available. Manual tools:
baidu_memory_recall "query" - search conversation memory using Baidu vectors (requires API credentials)baidu_memory_store "text" - manually store something with Baidu embedding (requires API credentials)baidu_memory_forget - delete memories (GDPR, requires API credentials)In Degraded Mode (without API credentials):
| Flag | Level | When to Use |
|------|-------|-------------|
| -i c | Critical | "always remember", explicit preferences |
| -i h | High | Decisions, corrections, preferences |
| -i n | Normal | General information |
| -i l | Low | Temporary notes |
| System | Use For |
|--------|---------|
| Baidu Embedding | Conversation context, auto-retrieval with privacy |
| Git-Notes | Structured decisions, searchable by entity/tag |
| File Search | Workspace docs, daily logs, MEMORY.md |
workspace/
├── MEMORY.md # Long-term curated memory
├── memory/
│ ├── active-context.md # Current session state
│ └── YYYY-MM-DD.md # Daily logs
├── scripts/
│ └── file-search.sh # Workspace search
└── skills/
├── triple-memory-baidu-embedding/ # Enhanced memory system
├── git-notes-memory/ # Structured memory
└── memory-baidu-embedding-db/ # Vector storageThis skill can be integrated with Clawdbot's startup hooks for automatic initialization:
To ensure the Triple Memory Baidu system starts automatically when the gateway starts:
memory-boot-loader hook can be configured to run /root/clawd/session-init-triple-baidu.shThe system can be integrated with the gateway startup sequence to ensure:
Never announce memory operations to users. Just do it:
skills/ directoryBased on original Triple Memory system by Clawdbot Team. Contributions welcome to enhance the Baidu Embedding integration.
Original license applies with modifications noted above. Credit given to original authors.
Generated Mar 1, 2026
Deploy this skill in a customer support AI agent handling sensitive conversations, such as in healthcare or finance, where privacy is paramount. It uses Baidu Embedding for Chinese-language context recall without exposing data to third-party APIs, while Git-Notes logs structured decisions like issue resolutions for compliance.
Integrate the skill into an AI assistant for software development teams to manage project decisions and preferences across git branches. It automatically captures technical choices via Baidu Embedding and stores them in Git-Notes, enabling persistent context across coding sessions without external dependencies.
Use this skill in a personal AI coach that helps users track habits and goals with full data privacy. Baidu Embedding auto-recalls past preferences, while Git-Notes structures daily logs and file search accesses workspace documents, all operating offline in degraded mode if API credentials are unavailable.
Employ the skill in an AI research assistant to manage literature notes and findings across long-term projects. It leverages Baidu Embedding for semantic search of conversation history in Chinese, Git-Notes for tagging key insights, and file search to query workspace documents like MEMORY.md.
Offer this skill as part of a subscription-based platform for businesses deploying AI agents with enhanced memory capabilities. Revenue comes from tiered plans based on usage, such as higher API call limits for Baidu Embedding or premium support for integration with existing systems like Clawdbot.
Provide consulting services to help organizations integrate this skill into their AI workflows, tailoring it for specific industries like finance or healthcare. Revenue is generated through project-based fees for setup, customization, and ongoing maintenance of the memory system.
Distribute the skill as a freemium tool where basic features like Git-Notes and file search are free, while advanced capabilities such as Baidu Embedding auto-recall require a paid license. Revenue streams include one-time purchases for premium features or donations from open-source users.
💬 Integration Tip
Ensure Baidu API credentials are set as environment variables for full functionality, and integrate with Clawdbot startup hooks to automate memory initialization on agent launch.
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Search and analyze your own session logs (older/parent conversations) using jq.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vibe-coding ready.
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection