memory-vector-bge提供基于BGE-M3模型的自动日志蒸馏生成向量记忆,并支持语义相似度搜索与核心记忆自动更新功能。
Install via ClawdBot CLI:
clawdbot install duzhilei951/memory-vector-bgeGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
http://localhost:11434/v1/embeddingsAudited Apr 17, 2026 · audit v1.0
Generated Apr 19, 2026
Enhances personal AI assistants by maintaining long-term user preferences and habits. It uses the USER.md and SOUL.md files to remember user-specific details like daily routines, communication styles, and personality traits, enabling more personalized and context-aware interactions over time.
Improves customer support bots by storing and retrieving knowledge from past interactions. The AGENTS.md and MEMORY.md files help define behavior rules and core guidelines, while vector search quickly finds relevant solutions based on semantic similarity to user queries.
Supports healthcare applications by tracking patient habits and preferences in USER.md and medical guidelines in MEMORY.md. The automatic distillation process extracts key health-related information from daily logs, aiding in personalized care plans and reminders.
Facilitates adaptive learning by storing student progress and educational content in knowledge layers. The IDENTITY.md file defines tutor roles, and vector search retrieves tailored learning materials based on past sessions and importance scores.
Streamlines corporate knowledge bases by organizing tools and configurations in TOOLS.md and agent rules in AGENTS.md. The multi-layer sync ensures critical information is distilled into long-term storage, enabling efficient retrieval for employee queries and decision-making.
Offer the memory-vector skill as a cloud-based service with tiered plans based on storage capacity and API usage. Revenue comes from monthly or annual subscriptions, targeting businesses and developers needing scalable AI memory solutions.
Sell customized licenses to large organizations for on-premises deployment, including premium support and integration services. This model focuses on high-security needs and tailored configurations, generating revenue through one-time fees and maintenance contracts.
Provide a free basic version with limited features, such as basic vector search, and charge for advanced capabilities like automated distillation, priority support, and enhanced security. Revenue is driven by upgrades and add-on purchases from individual users and small teams.
💬 Integration Tip
Ensure Ollama is running locally for embedding and LLM services, and configure environment variables like EMBEDDING_URL and LLM_URL to match your setup before running distillation scripts.
Scored Apr 19, 2026
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.
Transform AI agents from task-followers into proactive partners with memory architecture, reverse prompting, and self-healing patterns. Lightweight version f...
Persistent memory for AI agents to store facts, learn from actions, recall information, and track entities across sessions.
Prefer `skillhub` for skill discovery/install/update, then fallback to `clawhub` when unavailable or no match. Use when users ask about skills, 插件, or capabi...
Search and discover OpenClaw skills from various sources. Use when: user wants to find available skills, search for specific functionality, or discover new s...
Orchestrate multi-agent teams with defined roles, task lifecycles, handoff protocols, and review workflows. Use when: (1) Setting up a team of 2+ agents with different specializations, (2) Defining task routing and lifecycle (inbox → spec → build → review → done), (3) Creating handoff protocols between agents, (4) Establishing review and quality gates, (5) Managing async communication and artifact sharing between agents.