MCP server for building knowledge graphs from documents. It ingests PDF/PPTX/DOCX files, transcribes to Markdown, and uses LLM to bootstrap entity patterns and build a JSONL knowledge graph with RAG chunks.
Builds a queryable knowledge graph from a pack of repos, papers, and notes, and serves it to agents via MCP, enabling search, source reading, and neighbor exploration.
MCP server that indexes Markdown, Word, HTML, and PDF documents into a SQLite knowledge graph with CJK+Latin full-text search and cross-document reference tracking. Runs drift audits to surface stale policies, conflicting research claims, superseded ADRs, and undocumented code exports.
Builds a keyword-searchable index from markdown documentation bundles and serves it to LLM agents via MCP, with retrieval logging and reporting for curation.