From engraph
Index and search document collections using hybrid semantic, graph, and full-text search. Use for knowledge bases, finding connections between documents, or querying markdown collections.
How this skill is triggered — by the user, by Claude, or both
Slash command
/engraph:engraphThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Local knowledge engine for markdown document collections. Combines semantic embeddings, full-text search (BM25), wikilink graph traversal, temporal scoring, and cross-encoder reranking.
Local knowledge engine for markdown document collections. Combines semantic embeddings, full-text search (BM25), wikilink graph traversal, temporal scoring, and cross-encoder reranking.
!engraph --version 2>/dev/null || echo "Not installed: brew install devwhodevs/tap/engraph"
engraph index /path/to/documents # Incremental; only changed files re-embedded
engraph index /path/to/documents --rebuild
engraph status # File count, stats, index freshness
engraph clear # Drop the index (--all also removes models)
engraph search "how does the auth flow work"
engraph search "performance regressions last month" --explain
engraph search "architecture decisions" -n 5 --json
| Flag | Description |
|---|---|
-n, --top-n <N> | Number of results (default: from config or 10) |
--explain | Show per-lane RRF score breakdown |
--json | Machine-readable JSON output |
engraph graph show "path/to/note.md" # Connections for a document
engraph graph show "#docid" # By document ID
engraph graph stats # Nodes, edges, density
engraph context topic "authentication" --budget 8000
engraph context who "Person Name"
engraph context project "Project Name"
engraph context vault-map # Collection structure overview
engraph context read "path/to/note.md" # Full content + metadata
engraph context list --tags architecture # Filter by tags, folder, created_by, etc.
Health diagnostics (orphans, broken links, stale notes, tag hygiene) are exposed through the MCP
healthtool and the HTTPGET /api/healthendpoint — seereferences/http-rest-api.md.
engraph index /path/to/documents
engraph search "your query"
references/mcp-setup.md — configure engraph as an MCP server (Claude Code, Claude Desktop).references/http-rest-api.md — HTTP REST API endpoints, authentication, and examples for web agents and scripts.npx claudepluginhub devwhodevs/engraph --plugin engraphSearches markdown knowledge bases via GitMark CLI (FTS5 BM25 + trigram/fuzzy matching). Use to find where something is documented instead of random file reads.
Performs local keyword, semantic, or hybrid search on markdown notes and docs to find relevant files before reading them, saving 90% tokens during codebase exploration.
Traverses docs/ knowledge graph via search and wikilinks to answer project questions on decisions, architecture, conventions. Supports /autology:explore-knowledge overview, neighborhood, path.