2,121 tagged RAG and vectors, measured the same way as everything else here.
Browse within: LLM 385knowledge-graph 243agent 225Multi-Agent 209dsh-plugin 203persistent memory 201skills 164agents 133workflow 122knowledge-base 118wanwu 107local-llm 97enterprise-ai 95gdpr 93
Skill Claude CodeCodex
Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.
Skill Claude CodeCodex
Query the ChromaDB Manager document base over MCP.
Skill Claude CodeCodex
Turn text into embedding vectors with Forge (Voxell's hosted embedding API) for semantic search, RAG retrieval, clustering, dedup, or similarity. Use when the user wants to embed text/documents/queries, build or query a vector index, find similar or duplicate text, or pick an embedding model and dimension. Provides…
Skill Claude Code
A skill that sends a search query to a script and receives text from a retrieval-augmented generation system, which finds relevant source material before producing an answer.
Skill Claude CodeCodex
Expert guide for building applications with Qdrant Edge — the embedded, offline-capable vector search engine for edge devices (robots, kiosks, mobile phones, IoT, home assistants). Use this skill whenever the user mentions Qdrant Edge, qdrant-edge-py, EdgeShard, on-device vector search, offline vector search, embedded…
Skill Claude CodeCodex
Qdrant MCP Server management and diagnostics skill. Use whenever working with the qmcp (QDrant MCP Server) project for semantic code search. Activates on queries about: Qdrant database state, collections, or indexed content Cleaning up vector database (orphans, stale vectors, missing files) Understanding what's…
Unity-Billal-mesloub/mcp-documentation-server
Skill Claude CodeCodex
Use when you need to store, retrieve, search, or manage documents in a local knowledge base with semantic search and hybrid (vector + full-text) retrieval. Also use when interacting with the documentation server web interface, managing uploads, or performing AI-powered document analysis. Use this instead of MCP-native…
Skill Codex
Use a self-hosted knowledge-engine MCP for structured project orientation, text and image RAG, source verification, file contributions and durable work closeout. Applies to the configured deployment, both personal and collaborative.
Skill Claude CodeCodex
Search, retrieve, version, and persist prompts, documents, and collections through the hosted Context Repo MCP. Use this skill whenever the user mentions Context Repo, saved prompts, prompt templates, stored documents, collections, semantic search, hierarchical document navigation, cited answers over stored documents…
Skill Claude CodeCodex
A Chinese-language skill for saving, searching, updating, and deleting information across conversations through a Feishu memory service. Feishu is a collaboration platform, and RAG is a way to retrieve relevant stored documents or notes for an agent.
Skill Claude CodeCodex
Use this skill when retrieving context from a pre-synchronized Confluence RAG MCP index.
Skill Claude Code
Consolidate the brain — refresh the index, review sessions since the last reflection, distill durable facts into memory files, compact the store, propose skills, commit. Use when asked to "reflect" or "consolidate memory"; also invoked headless by the nightly job.
Skill Claude CodeCodex needs its repo
Set up an accreta knowledge base over a corpus — pick a preset, write the config and a source declaration, generate the constitution, wire up MCP, and verify the first ingest. Use when someone wants an agent-maintained knowledge base with provenance and drift detection over a codebase, a document collection, or a…
Skill Claude CodeCodex
Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community…
Skill Codex
Work with a WeKnora knowledge base through its REST API — list and inspect knowledge bases, search one or many of them, import files, URLs, or Markdown, confirm an import finished parsing, read and edit chunks, and ask questions with a streamed answer. Use when the task targets a user's own WeKnora instance and its…
Skill Claude CodeCodex
Skill da REST API do Base de Conhecimento na MCP.AI: 7 endpoints em /api/kb. Sua base de conhecimento privada: suba documentos (.md, .txt, .docx, PDF, imagens), a plataforma indexa tudo semanticamente e o agente busca o contexto relevante na hora. Ideal pra escritórios. Cada base é isolada, o conteúdo fica…
Skill Claude CodeCodex
Hybrid semantic search (dense vectors + BM25) over local markdown/code knowledge bases. Indexes files into Qdrant via LlamaIndex. Exposed as a CLI (sage) and an MCP server (sage-mcp-mcp). Agents inside an MCP-capable host should prefer MCP tools — shared persistent connection, no subprocess overhead, no Qdrant…
Skill Claude CodeCodex
Search, ingest, expand chunk context, or manage local documents via a local RAG MCP server (tools: querydocuments, readchunkneighbors, ingestfile, ingestdata, deletefile, listfiles). Use when user says "search my docs", "save this page", "read around that chunk", "what did I save about X", or invokes npx local-rag.
Skill Claude CodeCodex
Semantic search and retrieval over the OpenClaw vault via an MCP server + watcher.
yyisahandsomeboy/rag_anything_mcp_sever
Skill Claude CodeCodex
A skill for operating the RAG-Anything MCP service, which lets an agent index and search information in files such as PDFs, documents, spreadsheets, web pages, and code.
Skill Claude CodeCodex
How this household runs its Sunday weekly review.
Skill Claude CodeCodex
Launch or reuse the loopback Memex Workspace UI when the user asks to browse conversations, manage facts, inspect taxonomy or pipeline health, or explore the knowledge map.
Skill Claude CodeCodex needs its repo
Ingest a source path into a specified collection and report file, chunk, vector, and BM25 counts.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: