Convert text, code, or documents into 384-dimensional vectors, numerical representations used for meaning-based search, similarity comparison, and clustering. Save vectors to files, check their dimensions and magnitude, and optionally record metadata in AgentDB.
中文简介正在准备中。当前显示英语简介。
Generate embeddings via npx ruvector@0.3.3 embed text (ONNX all-MiniLM-L6-v2, 384-dim), normalize, and store in HNSW index
安装前可以查看交给 AI 代理的指令内容。
Generate and store vector embeddings using the ruvector npm package.
Use this skill to embed text, code, or documents into 384-dimensional vectors for semantic search, similarity comparison, or clustering. ruvector uses ONNX all-MiniLM-L6-v2 with HNSW indexing (52,000+ inserts/sec, ~0.045ms search).
npm ls ruvector 2>/dev/null | grep '0.3.3' || npm install ruvector@0.3.3
embed text reports ONNX WASM files not bundled, an older ruvector (0.2.x) is being resolved — rerun with the pinned npx -y ruvector@0.3.3.text subcommand, with text as a positional arg):
npx -y ruvector@0.3.3 embed text "your text here"npx -y ruvector@0.3.3 embed text "your text here" -o vec.json--batch/--glob flags.npx -y ruvector@0.3.3 embed text "..." --adaptive --domain codemcp__plugin_ruflo-core_ruflo__memory_store({ key: "embed-SOURCE", value: "VECTOR_METADATA", namespace: "vector-patterns" })Register the MCP server once with the pinned version:
claude mcp add ruvector -- npx -y ruvector@0.3.3 mcp start
Then call MCP tools directly: hooks_rag_context (semantic context), brain_search (collective brain), hooks_ast_analyze, hooks_route.
embed --batch --glob flags do not exist in ruvector@0.3.3. embed text accepts one text, --stdin, or --input-file <path> (keeps sensitive text off argv); call it per file.npx -y ruvector@0.3.3 doctor to diagnose.还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Compare models available through the HuggingFace router with chat-ui configuration, research missing models, and write short English descriptions of their architecture and capabilities. Add entries to both production and development configuration files and commit the changes.
中文简介正在准备中。当前显示英语简介。
Create an Architecture Decision Record, a document for recording important design choices, with the next sequential number. It generates a Markdown template, registers the record in AgentDB, and links related decisions found through search.
中文简介正在准备中。当前显示英语简介。
Build a searchable index and relationship graph from ADRs, records of architectural decisions. Import two supported document formats, refresh existing metadata without duplicate relationships, and review summaries of statuses, missing references, and inconsistencies.
中文简介正在准备中。当前显示英语简介。
Rebuild the index of ADRs, records of architectural decisions, after files or relationship lines are deleted. It clears stored records and relationships, indexes the files still present, and checks that the final record count matches.
中文简介正在准备中。当前显示英语简介。
Review code changes against accepted Architecture Decision Records, documents that capture agreed design choices. Report violations, outdated references, compliant changes, and areas without ADR coverage, then suggest code fixes or a new decision record where appropriate.
中文简介正在准备中。当前显示英语简介。
Check saved architecture decision records (ADRs) for broken references, circular replacement relationships, and inconsistent statuses. Use the results to verify imported records or stop a CI check when selected integrity rules fail.
中文简介正在准备中。当前显示英语简介。