Results for “layer-caching”

Caching strategies across the RAG stack. Semantic caching with GPTCache and LangChain, Redis-based embedding-similarity cache, cache key design, TTL/invalidation, partial caching (cache retrieval only), provider-native prompt caching (Anthropic, OpenAI), and hierarchical L1/L2 caches. USE WHEN: user mentions "semantic cache", "GPTCache", "LLM cache", "prompt caching", "Redis vector cache", "cache invalidation for RAG", "reduce LLM cost", "latency reduction LLM" DO NOT USE FOR: retrieval accuracy - use `rag-patterns`; groundedness checks - use `rag-guardrails`; incremental indexing - use `rag-production`

Caching strategies for LLM prompts including Anthropic prompt caching, response caching, and CAG (Cache Augmented Generation) Use when: prompt caching, cache prompt, response cache, cag, cache augmented.

Build a persistent, compounding knowledge base that combines a wiki, knowledge graph, and raw source storage for structured retrieval with provenance.

Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications.

Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications. Use when: building RAG, vector search, embeddings, semantic search, document retrieval.

Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications. Use when: building RAG, vector search, embeddings, semantic search, document retrieval.

Shares memory between agents at the representation level by compacting the orchestrator's KV cache for efficient worker handoff, reducing token costs without summarization or retrieval.

Manage a multi-layered knowledge system for ingesting, organizing, syncing, and retrieving knowledge across local files, MCP memory, vector stores, and Git repos.

Designs and implements production-grade RAG systems by chunking documents, generating embeddings, configuring vector stores, building hybrid search pipelines, applying reranking, and evaluating retrieval quality.

Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications. Use when: building RAG, vector search, embeddings, semantic search, document retrieval.

Local RAG indexing with 97% storage reduction via anchor-based lazy recomputation. Graph-based selective embedding storage for memory-efficient semantic code search.

Caching strategies for LLM prompts including Anthropic prompt caching, response caching, and CAG (Cache Augmented Generation) Use when: prompt caching, cache prompt, response cache, cag, cache augmented.

SQLite-backed index over all entity files in the project. The read-side foundation for every other MCP server. Use whenever an agent needs to look up entities by ID, kind, state, or text — instead of grepping the filesystem.

Use with task-agent or review-agent for task-local cache scope, freshness, invalidation, and source-load risk. Do not use without a cache decision or as task owner.

跨多个存储层（本地文件、MCP memory、向量存储、Git 仓库）的知识库管理、摄取、同步和检索。在用户想要保存、组织、同步、去重或跨知识系统搜索时使用。

深度调研的多实例（多 Agent）编排工作流：把一个调研目标拆成可并行子目标，用 Codex CLI（`codex exec`）在默认 `workspace-write` 沙箱内运行子进程；联网与采集优先使用已安装的 skills，其次使用 MCP 工具；用脚本聚合子结果并分章精修，最终交付“成品报告文件路径 + 关键结论/建议摘要”。用于：系统性网页/资料调研、竞品/行业分析、批量链接/数据集分片检索、长文写作与证据整合，或用户提及“深度调研/Deep Research/Wide Research/多 Agent 并行调研/多进程调研”等场景。