Index large-scale documents and perform semantic search with persistent memory.
npx skills add https://github.com/1012Lonin/Yushufang --skill openviking-1012lonin
Please help me install this Agent Skill. Skill: openviking Source: https://github.com/1012Lonin/Yushufang/tree/main/skills/openviking Command: npx skills add https://github.com/1012Lonin/Yushufang --skill openviking-1012lonin
OpenViking 集成为 AI 代理提供持久记忆与知识库，解决在长期对话和跨文档检索中的上下文丢失问题。
将需要索引的文档添加到 OpenViking 知识库并执行一次语义检索。
High-intent search queries and answers about installing and using this skill.
Persistent memory for AI agents solves long conversation context loss by indexing documents into a knowledge base. This enables cross-session memory queries and knowledge retrieval to maintain continuous context.
Semantic search across a large-scale knowledge base requires indexing diverse data sources first. Once documents are indexed, you can execute semantic retrieval queries to find relevant information across the entire dataset.
Document indexing supports structured summaries from diverse data sources by applying multi-layer summarization. This allows AI agents to browse and retrieve structured knowledge efficiently across indexed documents.
Cross-session knowledge retrieval for AI agents is achieved by configuring a persistent memory integration. This setup allows agents to query historical interactions and indexed documents across different conversations.
OpenViking integration supports browsing and summarizing indexed documents through provided scripts. It applies multi-layer summaries and structured browsing to help agents navigate large-scale document indexes.
Persistent memory configuration for AI agents is needed when standard context windows fail to retain information across long conversations or large-scale document retrieval, requiring a structured knowledge base for cross-session queries.
thinking-machines-labAutomate knowledge distillation from teacher to student models via the Tinker API.
GongLingRuiQuery vertical-screen short drama knowledge and retrieve structured summaries.
Syedyasir001Designs and implements agent memory architectures using vector stores, knowledge graphs, and temporal retrieval.
dalagerOptimize AgentDB vector search latency and memory usage with quantization and HNSW indexing.
