The open retrieval layer for AI coding agents. Indexes code, docs, legal, research, data — 22 parsers (incl. EPUB, DOCX, ODT), FTS5 + semantic search, knowledge graph. Serves surgical context via MCP. Open source, local, free.
Skill Claude CodeCodex
Read the full content of a specific file or section previously returned by rtfmsearch. Use when the user wants to see the actual content of a search result, not just metadata.
Skill Claude CodeCodex
Install the embeddings extra (fastembed, 85 MB ONNX model) into an isolated venv. Required for semantic and hybrid search modes. The model runs on CPU, no GPU needed.
Skill Claude CodeCodex
Install the full PDF parser (pdftext + marker-pdf + CPU-only torch, 1.5 GB) into an isolated venv. Needed for complex layouts — tables, figures, scanned documents. Skip this if /rtfm:install-pdf (50 MB, text only) is enough.
Skill Claude CodeCodex
Install the light PDF parser (pdftext, 50 MB) into an isolated venv. Covers most PDFs with fast, accurate text extraction. For complex layouts (tables, figures, scanned docs), use /rtfm:install-pdf-full instead.
Skill Claude CodeCodex
Search the RTFM-indexed corpus of the current project (code, docs, data). Use for any exploratory search — finding relevant files, modules, symbols, or content. Faster and more precise than Glob/Grep/find for broad queries.