viking-memoryOpenViking 长期记忆系统。用于语义检索用户偏好、历史对话、重要信息等。当需要召回用户之前提到的信息、查找相关上下文时使用此 Skill。
Install via ClawdBot CLI:
clawdbot install forvendettaw/viking-memory基于 OpenViking 的向量化记忆系统,提供语义搜索能力。
http://127.0.0.1:18790POST /api/v1/search/findPOST /api/v1/resourcesPOST /api/v1/content/readcurl -s -X POST http://127.0.0.1:18790/api/v1/search/find \
-H "Content-Type: application/json" \
-d '{"query": "用户的工作习惯", "limit": 5}'
curl -s -X POST http://127.0.0.1:18790/api/v1/resources \
-H "Content-Type: application/json" \
-d '{"uri": "viking://user/memories/preferences/咖啡偏好", "content": "用户喜欢喝拿铁,不加糖"}'
curl -s -X POST http://127.0.0.1:18790/api/v1/content/read \
-H "Content-Type: application/json" \
-d '{"uri": "viking://user/memories/preferences/咖啡偏好"}'
Generated Feb 25, 2026
In customer service, this skill can recall past interactions and preferences to provide tailored assistance. For example, when a user asks about previous issues or saved settings, it quickly retrieves relevant memory entries to enhance response accuracy and efficiency.
In healthcare, it can store and search patient histories, symptoms, and treatment plans. When a clinician queries a patient's past conditions, the skill semantically retrieves related records to support diagnosis and continuity of care.
In education, it can track student progress and preferences over time. When an educator needs to review a student's past performance or learning habits, the skill searches memories to inform personalized teaching strategies.
In e-commerce, it can store user purchase history and preferences. When a customer browses products, the skill recalls past interactions to suggest relevant items, improving user experience and sales conversion.
Offer this skill as a cloud-based service with tiered pricing based on usage or features. Revenue comes from monthly or annual subscriptions, targeting businesses needing scalable memory management without infrastructure costs.
Sell perpetual licenses for on-premise deployment to large organizations with strict data privacy requirements. Revenue includes upfront license fees and optional support contracts for maintenance and updates.
Monetize the API endpoints by charging per API call or data volume. This model suits developers and startups integrating semantic memory into custom applications, with revenue based on usage metrics.
💬 Integration Tip
Ensure the base URL is correctly configured and test API endpoints with sample queries before full deployment to avoid connectivity issues.
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