graphify

name	graphify
description	any input (code, docs, papers, images) → knowledge graph → clustered communities → HTML + JSON + audit report
trigger	/graphify

/graphify

Turn any folder of files into a navigable knowledge graph with community detection, an honest audit trail, and three outputs: interactive HTML, GraphRAG-ready JSON, and a plain-language GRAPH_REPORT.md.

Usage

/graphify                                             # full pipeline on current directory → Obsidian vault
/graphify <path>                                      # full pipeline on specific path
/graphify <path> --mode deep                          # thorough extraction, richer INFERRED edges
/graphify <path> --update                             # incremental - re-extract only new/changed files
/graphify <path> --cluster-only                       # rerun clustering on existing graph
/graphify <path> --no-viz                             # skip visualization, just report + JSON
/graphify <path> --html                               # (HTML is generated by default - this flag is a no-op)
/graphify <path> --svg                                # also export graph.svg (embeds in Notion, GitHub)
/graphify <path> --graphml                            # export graph.graphml (Gephi, yEd)
/graphify <path> --neo4j                              # generate graphify-out/cypher.txt for Neo4j
/graphify <path> --neo4j-push bolt://localhost:7687   # push directly to Neo4j
/graphify <path> --mcp                                # start MCP stdio server for agent access
/graphify <path> --watch                              # watch folder, auto-rebuild on code changes (no LLM needed)
/graphify add <url>                                   # fetch URL, save to ./raw, update graph
/graphify add <url> --author "Name"                   # tag who wrote it
/graphify add <url> --contributor "Name"              # tag who added it to the corpus
/graphify query "<question>"                          # BFS traversal - broad context
/graphify query "<question>" --dfs                    # DFS - trace a specific path
/graphify query "<question>" --budget 1500            # cap answer at N tokens
/graphify path "AuthModule" "Database"                # shortest path between two concepts
/graphify explain "SwinTransformer"                   # plain-language explanation of a node

What graphify is for

graphify is built around Andrej Karpathy's /raw folder workflow: drop anything into a folder - papers, tweets, screenshots, code, notes - and get a structured knowledge graph that shows you what you didn't know was connected.

Three things it does that Claude alone cannot:

1. Persistent graph - relationships are stored in graphify-out/graph.json and survive across sessions. Ask questions weeks later without re-reading everything.
2. Honest audit trail - every edge is tagged EXTRACTED, INFERRED, or AMBIGUOUS. You know what was found vs invented.
3. Cross-document surprise - community detection finds connections between concepts in different files that you would never think to ask about directly.

Use it for:

• A codebase you're new to (understand architecture before touching anything)
• A reading list (papers + tweets + notes → one navigable graph)
• A research corpus (citation graph + concept graph in one)
• Your personal /raw folder (drop everything in, let it grow, query it)

What You Must Do When Invoked

If no path was given, use . (current directory). Do not ask the user for a path.

Follow these steps in order. Do not skip steps.

Step 1 - Ensure graphify is installed

# Detect the correct Python interpreter (handles pipx, venv, system installs)
GRAPHIFY_BIN=$(which graphify 2>/dev/null)
if [ -n "$GRAPHIFY_BIN" ]; then
    PYTHON=$(head -1 "$GRAPHIFY_BIN" | tr -d '#!')
else
    PYTHON="python3"
fi
$PYTHON -c "import graphify" 2>/dev/null || pip install graphifyy -q --break-system-packages 2>&1 | tail -3
# Write interpreter path for all subsequent steps
$PYTHON -c "import sys; open('.graphify_python', 'w').write(sys.executable)"

If the import succeeds, print nothing and move straight to Step 2.

In every subsequent bash block, replace python3 with $(cat .graphify_python) to use the correct interpreter.

Step 2 - Detect files

$(cat .graphify_python) -c "
import json
from graphify.detect import detect
from pathlib import Path
result = detect(Path('INPUT_PATH'))
print(json.dumps(result))
" > .graphify_detect.json

Replace INPUT_PATH with the actual path the user provided. Do NOT cat or print the JSON - read it silently and present a clean summary instead:

Corpus: X files · ~Y words
  code:     N files (.py .ts .go ...)
  docs:     N files (.md .txt ...)
  papers:   N files (.pdf ...)
  images:   N files

Then act on it:

• If total_files is 0: stop with "No supported files found in [path]."
• If skipped_sensitive is non-empty: mention file count skipped, not the file names.
• If total_words > 2,000,000 OR total_files > 200: show the warning and the top 5 subdirectories by file count, then ask which subfolder to run on. Wait for the user's answer before proceeding.
• Otherwise: proceed directly to Step 3 - no need to ask anything.

Step 3 - Extract entities and relationships

Before starting: note whether --mode deep was given. You must pass DEEP_MODE=true to every subagent in Step B2 if it was. Track this from the original invocation - do not lose it.

This step has two parts: structural extraction (deterministic, free) and semantic extraction (Claude, costs tokens).

Run Part A (AST) and Part B (semantic) in parallel. Dispatch all semantic subagents AND start AST extraction in the same message. Both can run simultaneously since they operate on different file types. Merge results in Part C as before.

Note: Parallelizing AST + semantic saves 5-15s on large corpora. AST is deterministic and fast; start it while subagents are processing docs/papers.

Part A - Structural extraction for code files

For any code files detected, run AST extraction in parallel with Part B subagents:

$(cat .graphify_python) -c "
import sys, json
from graphify.extract import collect_files, extract
from pathlib import Path
import json

code_files = []
detect = json.loads(Path('.graphify_detect.json').read_text())
for f in detect.get('files', {}).get('code', []):
    code_files.extend(collect_files(Path(f)) if Path(f).is_dir() else [Path(f)])

if code_files:
    result = extract(code_files)
    Path('.graphify_ast.json').write_text(json.dumps(result, indent=2))
    print(f'AST: {len(result[\"nodes\"])} nodes, {len(result[\"edges\"])} edges')
else:
    Path('.graphify_ast.json').write_text(json.dumps({'nodes':[],'edges':[],'input_tokens':0,'output_tokens':0}))
    print('No code files - skipping AST extraction')
"

Part B - Semantic extraction (parallel subagents)

Fast path: If detection found zero docs, papers, and images (code-only corpus), skip Part B entirely and go straight to Part C. AST handles code - there is nothing for semantic subagents to do.

MANDATORY: You MUST use the Agent tool here. Reading files yourself one-by-one is forbidden - it is 5-10x slower. If you do not use the Agent tool you are doing this wrong.

Before dispatching subagents, print a timing estimate:

• Load total_words and file counts from .graphify_detect.json
• Estimate agents needed: ceil(uncached_non_code_files / 22) (chunk size is 20-25)
• Estimate time: ~45s per agent batch (they run in parallel, so total ≈ 45s × ceil(agents/parallel_limit))
• Print: "Semantic extraction: ~N files → X agents, estimated ~Ys"

Step B0 - Check extraction cache first

Before dispatching any subagents, check which files already have cached extraction results:

$(cat .graphify_python) -c "
import json
from graphify.cache import check_semantic_cache
from pathlib import Path

detect = json.loads(Path('.graphify_detect.json').read_text())
all_files = [f for files in detect['files'].values() for f in files]

cached_nodes, cached_edges, cached_hyperedges, uncached = check_semantic_cache(all_files)

if cached_nodes or cached_edges or cached_hyperedges:
    Path('.graphify_cached.json').write_text(json.dumps({'nodes': cached_nodes, 'edges': cached_edges, 'hyperedges': cached_hyperedges}))
Path('.graphify_uncached.txt').write_text('\n'.join(uncached))
print(f'Cache: {len(all_files)-len(uncached)} files hit, {len(uncached)} files need extraction')
"

Only dispatch subagents for files listed in .graphify_uncached.txt. If all files are cached, skip to Part C directly.

Step B1 - Split into chunks

Load files from .graphify_uncached.txt. Split into chunks of 20-25 files each. Each image gets its own chunk (vision needs separate context).

Step B2 - Dispatch ALL subagents in a single message (OpenCode)

OpenCode platform: Uses @mention dispatch instead of the Agent tool. All mentions in a single message run in parallel.

Dispatch one @mention per chunk — ALL in the same response:

@agent Chunk CHUNK_NUM of TOTAL_CHUNKS: [extraction prompt below with FILE_LIST, CHUNK_NUM, TOTAL_CHUNKS, DEEP_MODE substituted]

@agent Chunk 2 of TOTAL_CHUNKS: [next chunk]

Wait for all agents to return. Parse each response as JSON. Accumulate nodes/edges/hyperedges across all results and write to .graphify_semantic_new.json.

The extraction prompt each agent receives (substitute FILE_LIST, CHUNK_NUM, TOTAL_CHUNKS, DEEP_MODE):

You are a graphify extraction subagent. Read the files listed and extract a knowledge graph fragment.
Output ONLY valid JSON matching the schema below - no explanation, no markdown fences, no preamble.

Files (chunk CHUNK_NUM of TOTAL_CHUNKS):
FILE_LIST

Rules:
- EXTRACTED: relationship explicit in source (import, call, citation, "see §3.2")
- INFERRED: reasonable inference (shared data structure, implied dependency)
- AMBIGUOUS: uncertain - flag for review, do not omit

Code files: focus on semantic edges AST cannot find (call relationships, shared data, arch patterns).
  Do not re-extract imports - AST already has those.
Doc/paper files: extract named concepts, entities, citations. Also extract rationale — sections that explain WHY a decision was made, trade-offs chosen, or design intent. These become nodes with `rationale_for` edges pointing to the concept they explain.
Image files: use vision to understand what the image IS - do not just OCR.
  UI screenshot: layout patterns, design decisions, key elements, purpose.
  Chart: metric, trend/insight, data source.
  Tweet/post: claim as node, author, concepts mentioned.
  Diagram: components and connections.
  Research figure: what it demonstrates, method, result.
  Handwritten/whiteboard: ideas and arrows, mark uncertain readings AMBIGUOUS.

DEEP_MODE (if --mode deep was given): be aggressive with INFERRED edges - indirect deps,
  shared assumptions, latent couplings. Mark uncertain ones AMBIGUOUS instead of omitting.

Semantic similarity: if two concepts in this chunk solve the same problem or represent the same idea without any structural link (no import, no call, no citation), add a `semantically_similar_to` edge marked INFERRED with a confidence_score reflecting how similar they are (0.6-0.95). Examples:
- Two functions that both validate user input but never call each other
- A class in code and a concept in a paper that describe the same algorithm
- Two error types that handle the same failure mode differently
Only add these when the similarity is genuinely non-obvious and cross-cutting. Do not add them for trivially similar things.

Hyperedges: if 3 or more nodes clearly participate together in a shared concept, flow, or pattern that is not captured by pairwise edges alone, add a hyperedge to a top-level `hyperedges` array. Examples:
- All classes that implement a common protocol or interface
- All functions in an authentication flow (even if they don't all call each other)
- All concepts from a paper section that form one coherent idea
Use sparingly — only when the group relationship adds information beyond the pairwise edges. Maximum 3 hyperedges per chunk.

If a file has YAML frontmatter (--- ... ---), copy source_url, captured_at, author,
  contributor onto every node from that file.

confidence_score is REQUIRED on every edge - never omit it, never use 0.5 as a default:
- EXTRACTED edges: confidence_score = 1.0 always
- INFERRED edges: reason about each edge individually.
  Direct structural evidence (shared data structure, clear dependency): 0.8-0.9.
  Reasonable inference with some uncertainty: 0.6-0.7.
  Weak or speculative: 0.4-0.5. Most edges should be 0.6-0.9, not 0.5.
- AMBIGUOUS edges: 0.1-0.3

Output exactly this JSON (no other text):
{"nodes":[{"id":"filestem_entityname","label":"Human Readable Name","file_type":"code|document|paper|image","source_file":"relative/path","source_location":null,"source_url":null,"captured_at":null,"author":null,"contributor":null}],"edges":[{"source":"node_id","target":"node_id","relation":"calls|implements|references|cites|conceptually_related_to|shares_data_with|semantically_similar_to|rationale_for","confidence":"EXTRACTED|INFERRED|AMBIGUOUS","confidence_score":1.0,"source_file":"relative/path","source_location":null,"weight":1.0}],"hyperedges":[{"id":"snake_case_id","label":"Human Readable Label","nodes":["node_id1","node_id2","node_id3"],"relation":"participate_in|implement|form","confidence":"EXTRACTED|INFERRED","confidence_score":0.75,"source_file":"relative/path"}],"input_tokens":0,"output_tokens":0}

Step B3 - Collect, cache, and merge

Wait for all subagents. For each result:

• If a subagent returned valid JSON with nodes and edges, include it and save each file's nodes/edges to the cache
• If a subagent failed or returned invalid JSON, print a warning and skip that chunk - do not abort

If more than half the chunks failed, stop and tell the user.

Save new results to cache:

$(cat .graphify_python) -c "
import json
from graphify.cache import save_semantic_cache
from pathlib import Path

new = json.loads(Path('.graphify_semantic_new.json').read_text()) if Path('.graphify_semantic_new.json').exists() else {'nodes':[],'edges':[],'hyperedges':[]}
saved = save_semantic_cache(new.get('nodes', []), new.get('edges', []), new.get('hyperedges', []))
print(f'Cached {saved} files')
"

Merge cached + new results into .graphify_semantic.json:

$(cat .graphify_python) -c "
import json
from pathlib import Path

cached = json.loads(Path('.graphify_cached.json').read_text()) if Path('.graphify_cached.json').exists() else {'nodes':[],'edges':[],'hyperedges':[]}
new = json.loads(Path('.graphify_semantic_new.json').read_text()) if Path('.graphify_semantic_new.json').exists() else {'nodes':[],'edges':[],'hyperedges':[]}

all_nodes = cached['nodes'] + new.get('nodes', [])
all_edges = cached['edges'] + new.get('edges', [])
all_hyperedges = cached.get('hyperedges', []) + new.get('hyperedges', [])
seen = set()
deduped = []
for n in all_nodes:
    if n['id'] not in seen:
        seen.add(n['id'])
        deduped.append(n)

merged = {
    'nodes': deduped,
    'edges': all_edges,
    'hyperedges': all_hyperedges,
    'input_tokens': new.get('input_tokens', 0),
    'output_tokens': new.get('output_tokens', 0),
}
Path('.graphify_semantic.json').write_text(json.dumps(merged, indent=2))
print(f'Extraction complete - {len(deduped)} nodes, {len(all_edges)} edges ({len(cached[\"nodes\"])} from cache, {len(new.get(\"nodes\",[]))} new)')
"

Clean up temp files: rm -f .graphify_cached.json .graphify_uncached.txt .graphify_semantic_new.json

Part C - Merge AST + semantic into final extraction

$(cat .graphify_python) -c "
import sys, json
from pathlib import Path

ast = json.loads(Path('.graphify_ast.json').read_text())
sem = json.loads(Path('.graphify_semantic.json').read_text())

# Merge: AST nodes first, semantic nodes deduplicated by id
seen = {n['id'] for n in ast['nodes']}
merged_nodes = list(ast['nodes'])
for n in sem['nodes']:
    if n['id'] not in seen:
        merged_nodes.append(n)
        seen.add(n['id'])

merged_edges = ast['edges'] + sem['edges']
merged_hyperedges = sem.get('hyperedges', [])
merged = {
    'nodes': merged_nodes,
    'edges': merged_edges,
    'hyperedges': merged_hyperedges,
    'input_tokens': sem.get('input_tokens', 0),
    'output_tokens': sem.get('output_tokens', 0),
}
Path('.graphify_extract.json').write_text(json.dumps(merged, indent=2))
total = len(merged_nodes)
edges = len(merged_edges)
print(f'Merged: {total} nodes, {edges} edges ({len(ast[\"nodes\"])} AST + {len(sem[\"nodes\"])} semantic)')
"

Step 4 - Build graph, cluster, analyze, generate outputs

mkdir -p graphify-out
$(cat .graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.cluster import cluster, score_all
from graphify.analyze import god_nodes, surprising_connections, suggest_questions
from graphify.report import generate
from graphify.export import to_json
from pathlib import Path

extraction = json.loads(Path('.graphify_extract.json').read_text())
detection  = json.loads(Path('.graphify_detect.json').read_text())

G = build_from_json(extraction)
communities = cluster(G)
cohesion = score_all(G, communities)
tokens = {'input': extraction.get('input_tokens', 0), 'output': extraction.get('output_tokens', 0)}
gods = god_nodes(G)
surprises = surprising_connections(G, communities)
labels = {cid: 'Community ' + str(cid) for cid in communities}
# Placeholder questions - regenerated with real labels in Step 5
questions = suggest_questions(G, communities, labels)

report = generate(G, communities, cohesion, labels, gods, surprises, detection, tokens, 'INPUT_PATH', suggested_questions=questions)
Path('graphify-out/GRAPH_REPORT.md').write_text(report)
to_json(G, communities, 'graphify-out/graph.json')

analysis = {
    'communities': {str(k): v for k, v in communities.items()},
    'cohesion': {str(k): v for k, v in cohesion.items()},
    'gods': gods,
    'surprises': surprises,
    'questions': questions,
}
Path('.graphify_analysis.json').write_text(json.dumps(analysis, indent=2))
if G.number_of_nodes() == 0:
    print('ERROR: Graph is empty - extraction produced no nodes.')
    print('Possible causes: all files were skipped, binary-only corpus, or extraction failed.')
    raise SystemExit(1)
print(f'Graph: {G.number_of_nodes()} nodes, {G.number_of_edges()} edges, {len(communities)} communities')
"

If this step prints ERROR: Graph is empty, stop and tell the user what happened - do not proceed to labeling or visualization.

Replace INPUT_PATH with the actual path.

Step 5 - Label communities

Read .graphify_analysis.json. For each community key, look at its node labels and write a 2-5 word plain-language name (e.g. "Attention Mechanism", "Training Pipeline", "Data Loading").

Then regenerate the report and save the labels for the visualizer:

$(cat .graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.cluster import score_all
from graphify.analyze import god_nodes, surprising_connections, suggest_questions
from graphify.report import generate
from pathlib import Path

extraction = json.loads(Path('.graphify_extract.json').read_text())
detection  = json.loads(Path('.graphify_detect.json').read_text())
analysis   = json.loads(Path('.graphify_analysis.json').read_text())

G = build_from_json(extraction)
communities = {int(k): v for k, v in analysis['communities'].items()}
cohesion = {int(k): v for k, v in analysis['cohesion'].items()}
tokens = {'input': extraction.get('input_tokens', 0), 'output': extraction.get('output_tokens', 0)}

# LABELS - replace these with the names you chose above
labels = LABELS_DICT

# Regenerate questions with real community labels (labels affect question phrasing)
questions = suggest_questions(G, communities, labels)

report = generate(G, communities, cohesion, labels, analysis['gods'], analysis['surprises'], detection, tokens, 'INPUT_PATH', suggested_questions=questions)
Path('graphify-out/GRAPH_REPORT.md').write_text(report)
Path('.graphify_labels.json').write_text(json.dumps({str(k): v for k, v in labels.items()}))
print('Report updated with community labels')
"

Replace LABELS_DICT with the actual dict you constructed (e.g. {0: "Attention Mechanism", 1: "Training Pipeline"}). Replace INPUT_PATH with the actual path.

Step 6 - Generate Obsidian vault (opt-in) + HTML

Generate HTML always (unless --no-viz). Obsidian vault only if --obsidian was explicitly given — skip it otherwise, it generates one file per node.

If --obsidian was given:

$(cat .graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.export import to_obsidian, to_canvas
from pathlib import Path

extraction = json.loads(Path('.graphify_extract.json').read_text())
analysis   = json.loads(Path('.graphify_analysis.json').read_text())
labels_raw = json.loads(Path('.graphify_labels.json').read_text()) if Path('.graphify_labels.json').exists() else {}

G = build_from_json(extraction)
communities = {int(k): v for k, v in analysis['communities'].items()}
cohesion = {int(k): v for k, v in analysis['cohesion'].items()}
labels = {int(k): v for k, v in labels_raw.items()}

n = to_obsidian(G, communities, 'graphify-out/obsidian', community_labels=labels or None, cohesion=cohesion)
print(f'Obsidian vault: {n} notes in graphify-out/obsidian/')

to_canvas(G, communities, 'graphify-out/obsidian/graph.canvas', community_labels=labels or None)
print('Canvas: graphify-out/obsidian/graph.canvas - open in Obsidian for structured community layout')
print()
print('Open graphify-out/obsidian/ as a vault in Obsidian.')
print('  Graph view   - nodes colored by community (set automatically)')
print('  graph.canvas - structured layout with communities as groups')
print('  _COMMUNITY_* - overview notes with cohesion scores and dataview queries')
"

Generate the HTML graph (always, unless --no-viz):

$(cat .graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.export import to_html
from pathlib import Path

extraction = json.loads(Path('.graphify_extract.json').read_text())
analysis   = json.loads(Path('.graphify_analysis.json').read_text())
labels_raw = json.loads(Path('.graphify_labels.json').read_text()) if Path('.graphify_labels.json').exists() else {}

G = build_from_json(extraction)
communities = {int(k): v for k, v in analysis['communities'].items()}
labels = {int(k): v for k, v in labels_raw.items()}

if G.number_of_nodes() > 5000:
    print(f'Graph has {G.number_of_nodes()} nodes - too large for HTML viz. Use Obsidian vault instead.')
else:
    to_html(G, communities, 'graphify-out/graph.html', community_labels=labels or None)
    print('graph.html written - open in any browser, no server needed')
"

Step 7 - Neo4j export (only if --neo4j or --neo4j-push flag)

If --neo4j - generate a Cypher file for manual import:

$(cat .graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.export import to_cypher
from pathlib import Path

G = build_from_json(json.loads(Path('.graphify_extract.json').read_text()))
to_cypher(G, 'graphify-out/cypher.txt')
print('cypher.txt written - import with: cypher-shell < graphify-out/cypher.txt')
"

If --neo4j-push <uri> - push directly to a running Neo4j instance. Ask the user for credentials if not provided:

$(cat .graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.cluster import cluster
from graphify.export import push_to_neo4j
from pathlib import Path

extraction = json.loads(Path('.graphify_extract.json').read_text())
analysis   = json.loads(Path('.graphify_analysis.json').read_text())
G = build_from_json(extraction)
communities = {int(k): v for k, v in analysis['communities'].items()}

result = push_to_neo4j(G, uri='NEO4J_URI', user='NEO4J_USER', password='NEO4J_PASSWORD', communities=communities)
print(f'Pushed to Neo4j: {result[\"nodes\"]} nodes, {result[\"edges\"]} edges')
"

Replace NEO4J_URI, NEO4J_USER, NEO4J_PASSWORD with actual values. Default URI is bolt://localhost:7687, default user is neo4j. Uses MERGE - safe to re-run without creating duplicates.

Step 7b - SVG export (only if --svg flag)

$(cat .graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.export import to_svg
from pathlib import Path

extraction = json.loads(Path('.graphify_extract.json').read_text())
analysis   = json.loads(Path('.graphify_analysis.json').read_text())
labels_raw = json.loads(Path('.graphify_labels.json').read_text()) if Path('.graphify_labels.json').exists() else {}

G = build_from_json(extraction)
communities = {int(k): v for k, v in analysis['communities'].items()}
labels = {int(k): v for k, v in labels_raw.items()}

to_svg(G, communities, 'graphify-out/graph.svg', community_labels=labels or None)
print('graph.svg written - embeds in Obsidian, Notion, GitHub READMEs')
"

Step 7c - GraphML export (only if --graphml flag)

$(cat .graphify_python) -c "
import json
from graphify.build import build_from_json
from graphify.export import to_graphml
from pathlib import Path

extraction = json.loads(Path('.graphify_extract.json').read_text())
analysis   = json.loads(Path('.graphify_analysis.json').read_text())

G = build_from_json(extraction)
communities = {int(k): v for k, v in analysis['communities'].items()}

to_graphml(G, communities, 'graphify-out/graph.graphml')
print('graph.graphml written - open in Gephi, yEd, or any GraphML tool')
"

Step 7d - MCP server (only if --mcp flag)

python3 -m graphify.serve graphify-out/graph.json

This starts a stdio MCP server that exposes tools: query_graph, get_node, get_neighbors, get_community, god_nodes, graph_stats, shortest_path. Add to Claude Desktop or any MCP-compatible agent orchestrator so other agents can query the graph live.

To configure in Claude Desktop, add to claude_desktop_config.json:

{
  "mcpServers": {
    "graphify": {
      "command": "python3",
      "args": ["-m", "graphify.serve", "/absolute/path/to/graphify-out/graph.json"]
    }
  }
}

Step 8 - Token reduction benchmark (only if total_words > 5000)

If total_words from .graphify_detect.json is greater than 5,000, run:

$(cat .graphify_python) -c "
import json
from graphify.benchmark import run_benchmark, print_benchmark
from pathlib import Path

detection = json.loads(Path('.graphify_detect.json').read_text())
result = run_benchmark('graphify-out/graph.json', corpus_words=detection['total_words'])
print_benchmark(result)
"

Print the output directly in chat. If total_words <= 5000, skip silently - the graph value is structural clarity, not token compression, for small corpora.

---

Step 9 - Save manifest, update cost tracker, clean up, and report

$(cat .graphify_python) -c "
import json
from pathlib import Path
from datetime import datetime, timezone
from graphify.detect import save_manifest

# Save manifest for --update
detect = json.loads(Path('.graphify_detect.json').read_text())
save_manifest(detect['files'])

# Update cumulative cost tracker
extract = json.loads(Path('.graphify_extract.json').read_text())
input_tok = extract.get('input_tokens', 0)
output_tok = extract.get('output_tokens', 0)

cost_path = Path('graphify-out/cost.json')
if cost_path.exists():
    cost = json.loads(cost_path.read_text())
else:
    cost = {'runs': [], 'total_input_tokens': 0, 'total_output_tokens': 0}

cost['runs'].append({
    'date': datetime.now(timezone.utc).isoformat(),
    'input_tokens': input_tok,
    'output_tokens': output_tok,
    'files': detect.get('total_files', 0),
})
cost['total_input_tokens'] += input_tok
cost['total_output_tokens'] += output_tok
cost_path.write_text(json.dumps(cost, indent=2))

print(f'This run: {input_tok:,} input tokens, {output_tok:,} output tokens')
print(f'All time: {cost[\"total_input_tokens\"]:,} input, {cost[\"total_output_tokens\"]:,} output ({len(cost[\"runs\"])} runs)')
"
rm -f .graphify_detect.json .graphify_extract.json .graphify_ast.json .graphify_semantic.json .graphify_analysis.json .graphify_labels.json .graphify_python
rm -f graphify-out/.needs_update 2>/dev/null || true

Tell the user (omit the obsidian line unless --obsidian was given):

Graph complete. Outputs in PATH_TO_DIR/graphify-out/

  graph.html            - interactive graph, open in browser
  GRAPH_REPORT.md       - audit report
  graph.json            - raw graph data
  obsidian/             - Obsidian vault (only if --obsidian was given)

Replace PATH_TO_DIR with the actual absolute path of the directory that was processed.

Then paste these sections from GRAPH_REPORT.md directly into the chat:

• God Nodes
• Surprising Connections
• Suggested Questions

Do NOT paste the full report - just those three sections. Keep it concise.

Then immediately offer to explore. Pick the single most interesting suggested question from the report - the one that crosses the most community boundaries or has the most surprising bridge node - and ask:

"The most interesting question this graph can answer: [question]. Want me to trace it?"

If the user says yes, run /graphify query "[question]" on the graph and walk them through the answer using the graph structure - which nodes connect, which community boundaries get crossed, what the path reveals. Keep going as long as they want to explore. Each answer should end with a natural follow-up ("this connects to X - want to go deeper?") so the session feels like navigation, not a one-shot report.

The graph is the map. Your job after the pipeline is to be the guide.

---

For --update (incremental re-extraction)

Use when you've added or modified files since the last run. Only re-extracts changed files - saves tokens and time.

$(cat .graphify_python) -c "
import sys, json
from graphify.detect import detect_incremental, save_manifest
from pathlib import Path

result = detect_incremental(Path('INPUT_PATH'))
new_total = result.get('new_total', 0)
print(json.dumps(result, indent=2))
Path('.graphify_incremental.json').write_text(json.dumps(result))
if new_total == 0:
    print('No files changed since last run. Nothing to update.')
    raise SystemExit(0)
print(f'{new_total} new/changed file(s) to re-extract.')
"

If new files exist, first check whether all changed files are code files:

$(cat .graphify_python) -c "
import json
from pathlib import Path

result = json.loads(open('.graphify_incremental.json').read()) if Path('.graphify_incremental.json').exists() else {}
code_exts = {'.py','.ts','.js','.go','.rs','.java','.cpp','.c','.rb','.swift','.kt','.cs','.scala','.php','.cc','.cxx','.hpp','.h','.kts'}
new_files = result.get('new_files', {})
all_changed = [f for files in new_files.values() for f in files]
code_only = all(Path(f).suffix.lower() in code_exts for f in all_changed)
print('code_only:', code_only)
"

If code_only is True: print [graphify update] Code-only changes detected - skipping semantic extraction (no LLM needed), run only Step 3A (AST) on the changed files, skip Step 3B entirely (no subagents), then go straight to merge and Steps 4–8.

If code_only is False (any changed file is a doc/paper/image): run the full Steps 3A–3C pipeline as normal.

Then:

$(cat .graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.export import to_json
from networkx.readwrite import json_graph
import networkx as nx
from pathlib import Path

# Load existing graph
existing_data = json.loads(Path('graphify-out/graph.json').read_text())
G_existing = json_graph.node_link_graph(existing_data, edges='links')

# Load new extraction
new_extraction = json.loads(Path('.graphify_extract.json').read_text())
G_new = build_from_json(new_extraction)

# Merge: new nodes/edges into existing graph
G_existing.update(G_new)
print(f'Merged: {G_existing.number_of_nodes()} nodes, {G_existing.number_of_edges()} edges')
" 

Then run Steps 4–8 on the merged graph as normal.

After Step 4, show the graph diff:

$(cat .graphify_python) -c "
import json
from graphify.analyze import graph_diff
from graphify.build import build_from_json
from networkx.readwrite import json_graph
import networkx as nx
from pathlib import Path

# Load old graph (before update) from backup written before merge
old_data = json.loads(Path('.graphify_old.json').read_text()) if Path('.graphify_old.json').exists() else None
new_extract = json.loads(Path('.graphify_extract.json').read_text())
G_new = build_from_json(new_extract)

if old_data:
    G_old = json_graph.node_link_graph(old_data, edges='links')
    diff = graph_diff(G_old, G_new)
    print(diff['summary'])
    if diff['new_nodes']:
        print('New nodes:', ', '.join(n['label'] for n in diff['new_nodes'][:5]))
    if diff['new_edges']:
        print('New edges:', len(diff['new_edges']))
"

Before the merge step, save the old graph: cp graphify-out/graph.json .graphify_old.json Clean up after: rm -f .graphify_old.json

---

For --cluster-only

Skip Steps 1–3. Load the existing graph from graphify-out/graph.json and re-run clustering:

$(cat .graphify_python) -c "
import sys, json
from graphify.cluster import cluster, score_all
from graphify.analyze import god_nodes, surprising_connections
from graphify.report import generate
from graphify.export import to_json
from networkx.readwrite import json_graph
import networkx as nx
from pathlib import Path

data = json.loads(Path('graphify-out/graph.json').read_text())
G = json_graph.node_link_graph(data, edges='links')

detection = {'total_files': 0, 'total_words': 99999, 'needs_graph': True, 'warning': None,
             'files': {'code': [], 'document': [], 'paper': []}}
tokens = {'input': 0, 'output': 0}

communities = cluster(G)
cohesion = score_all(G, communities)
gods = god_nodes(G)
surprises = surprising_connections(G, communities)
labels = {cid: 'Community ' + str(cid) for cid in communities}

report = generate(G, communities, cohesion, labels, gods, surprises, detection, tokens, '.')
Path('graphify-out/GRAPH_REPORT.md').write_text(report)
to_json(G, communities, 'graphify-out/graph.json')

analysis = {
    'communities': {str(k): v for k, v in communities.items()},
    'cohesion': {str(k): v for k, v in cohesion.items()},
    'gods': gods,
    'surprises': surprises,
}
Path('.graphify_analysis.json').write_text(json.dumps(analysis, indent=2))
print(f'Re-clustered: {len(communities)} communities')
"

Then run Steps 5–9 as normal (label communities, generate viz, benchmark, clean up, report).

---

For /graphify query

Two traversal modes - choose based on the question:

Mode	Flag	Best for
BFS (default)	(none)	"What is X connected to?" - broad context, nearest neighbors first
DFS	--dfs	"How does X reach Y?" - trace a specific chain or dependency path

First check the graph exists:

$(cat .graphify_python) -c "
from pathlib import Path
if not Path('graphify-out/graph.json').exists():
    print('ERROR: No graph found. Run /graphify <path> first to build the graph.')
    raise SystemExit(1)
"

If it fails, stop and tell the user to run /graphify <path> first.

Load graphify-out/graph.json, then:

1. Find the 1-3 nodes whose label best matches key terms in the question.
2. Run the appropriate traversal from each starting node.
3. Read the subgraph - node labels, edge relations, confidence tags, source locations.
4. Answer using only what the graph contains. Quote source_location when citing a specific fact.
5. If the graph lacks enough information, say so - do not hallucinate edges.

$(cat .graphify_python) -c "
import sys, json
from networkx.readwrite import json_graph
import networkx as nx
from pathlib import Path

data = json.loads(Path('graphify-out/graph.json').read_text())
G = json_graph.node_link_graph(data, edges='links')

question = 'QUESTION'
mode = 'MODE'  # 'bfs' or 'dfs'
terms = [t.lower() for t in question.split() if len(t) > 3]

# Find best-matching start nodes
scored = []
for nid, ndata in G.nodes(data=True):
    label = ndata.get('label', '').lower()
    score = sum(1 for t in terms if t in label)
    if score > 0:
        scored.append((score, nid))
scored.sort(reverse=True)
start_nodes = [nid for _, nid in scored[:3]]

if not start_nodes:
    print('No matching nodes found for query terms:', terms)
    sys.exit(0)

subgraph_nodes = set()
subgraph_edges = []

if mode == 'dfs':
    # DFS: follow one path as deep as possible before backtracking.
    # Depth-limited to 6 to avoid traversing the whole graph.
    visited = set()
    stack = [(n, 0) for n in reversed(start_nodes)]
    while stack:
        node, depth = stack.pop()
        if node in visited or depth > 6:
            continue
        visited.add(node)
        subgraph_nodes.add(node)
        for neighbor in G.neighbors(node):
            if neighbor not in visited:
                stack.append((neighbor, depth + 1))
                subgraph_edges.append((node, neighbor))
else:
    # BFS: explore all neighbors layer by layer up to depth 3.
    frontier = set(start_nodes)
    subgraph_nodes = set(start_nodes)
    for _ in range(3):
        next_frontier = set()
        for n in frontier:
            for neighbor in G.neighbors(n):
                if neighbor not in subgraph_nodes:
                    next_frontier.add(neighbor)
                    subgraph_edges.append((n, neighbor))
        subgraph_nodes.update(next_frontier)
        frontier = next_frontier

# Token-budget aware output: rank by relevance, cut at budget (~4 chars/token)
token_budget = BUDGET  # default 2000
char_budget = token_budget * 4

# Score each node by term overlap for ranked output
def relevance(nid):
    label = G.nodes[nid].get('label', '').lower()
    return sum(1 for t in terms if t in label)

ranked_nodes = sorted(subgraph_nodes, key=relevance, reverse=True)

lines = [f'Traversal: {mode.upper()} | Start: {[G.nodes[n].get(\"label\",n) for n in start_nodes]} | {len(subgraph_nodes)} nodes']
for nid in ranked_nodes:
    d = G.nodes[nid]
    lines.append(f'  NODE {d.get(\"label\", nid)} [src={d.get(\"source_file\",\"\")} loc={d.get(\"source_location\",\"\")}]')
for u, v in subgraph_edges:
    if u in subgraph_nodes and v in subgraph_nodes:
        d = G.edges[u, v]
        lines.append(f'  EDGE {G.nodes[u].get(\"label\",u)} --{d.get(\"relation\",\"\")} [{d.get(\"confidence\",\"\")}]--> {G.nodes[v].get(\"label\",v)}')

output = '\n'.join(lines)
if len(output) > char_budget:
    output = output[:char_budget] + f'\n... (truncated at ~{token_budget} token budget - use --budget N for more)'
print(output)
"

Replace QUESTION with the user's actual question, MODE with bfs or dfs, and BUDGET with the token budget (default 2000, or whatever --budget N specifies). Then answer based on the subgraph output above.

After writing the answer, save it back into the graph so it improves future queries:

$(cat .graphify_python) -c "
from graphify.ingest import save_query_result
from pathlib import Path
save_query_result(
    question='QUESTION',
    answer='ANSWER',
    memory_dir=Path('graphify-out/memory'),
    query_type='query',
    source_nodes=SOURCE_NODES,  # list of node labels cited, or []
)
print('Query result saved to graphify-out/memory/')
"

Replace QUESTION with the question, ANSWER with your full answer text, SOURCE_NODES with the list of node labels you cited. This closes the feedback loop: the next --update will extract this Q&A as a node in the graph.

---

For /graphify path

Find the shortest path between two named concepts in the graph.

First check the graph exists:

$(cat .graphify_python) -c "
from pathlib import Path
if not Path('graphify-out/graph.json').exists():
    print('ERROR: No graph found. Run /graphify <path> first to build the graph.')
    raise SystemExit(1)
"

If it fails, stop and tell the user to run /graphify <path> first.

$(cat .graphify_python) -c "
import json, sys
import networkx as nx
from networkx.readwrite import json_graph
from pathlib import Path

data = json.loads(Path('graphify-out/graph.json').read_text())
G = json_graph.node_link_graph(data, edges='links')

a_term = 'NODE_A'
b_term = 'NODE_B'

def find_node(term):
    term = term.lower()
    scored = sorted(
        [(sum(1 for w in term.split() if w in G.nodes[n].get('label','').lower()), n)
         for n in G.nodes()],
        reverse=True
    )
    return scored[0][1] if scored and scored[0][0] > 0 else None

src = find_node(a_term)
tgt = find_node(b_term)

if not src or not tgt:
    print(f'Could not find nodes matching: {a_term!r} or {b_term!r}')
    sys.exit(0)

try:
    path = nx.shortest_path(G, src, tgt)
    print(f'Shortest path ({len(path)-1} hops):')
    for i, nid in enumerate(path):
        label = G.nodes[nid].get('label', nid)
        if i < len(path) - 1:
            edge = G.edges[nid, path[i+1]]
            rel = edge.get('relation', '')
            conf = edge.get('confidence', '')
            print(f'  {label} --{rel}--> [{conf}]')
        else:
            print(f'  {label}')
except nx.NetworkXNoPath:
    print(f'No path found between {a_term!r} and {b_term!r}')
except nx.NodeNotFound as e:
    print(f'Node not found: {e}')
"

Replace NODE_A and NODE_B with the actual concept names from the user. Then explain the path in plain language - what each hop means, why it's significant.

After writing the explanation, save it back:

$(cat .graphify_python) -c "
from graphify.ingest import save_query_result
from pathlib import Path
save_query_result(
    question='Path from NODE_A to NODE_B',
    answer='ANSWER',
    memory_dir=Path('graphify-out/memory'),
    query_type='path_query',
    source_nodes=PATH_NODES,  # list of node labels on the path
)
print('Path result saved to graphify-out/memory/')
"

---

For /graphify explain

Give a plain-language explanation of a single node - everything connected to it.

First check the graph exists:

$(cat .graphify_python) -c "
from pathlib import Path
if not Path('graphify-out/graph.json').exists():
    print('ERROR: No graph found. Run /graphify <path> first to build the graph.')
    raise SystemExit(1)
"

If it fails, stop and tell the user to run /graphify <path> first.

$(cat .graphify_python) -c "
import json, sys
import networkx as nx
from networkx.readwrite import json_graph
from pathlib import Path

data = json.loads(Path('graphify-out/graph.json').read_text())
G = json_graph.node_link_graph(data, edges='links')

term = 'NODE_NAME'
term_lower = term.lower()

# Find best matching node
scored = sorted(
    [(sum(1 for w in term_lower.split() if w in G.nodes[n].get('label','').lower()), n)
     for n in G.nodes()],
    reverse=True
)
if not scored or scored[0][0] == 0:
    print(f'No node matching {term!r}')
    sys.exit(0)

nid = scored[0][1]
data_n = G.nodes[nid]
print(f'NODE: {data_n.get(\"label\", nid)}')
print(f'  source: {data_n.get(\"source_file\",\"unknown\")}')
print(f'  type: {data_n.get(\"file_type\",\"unknown\")}')
print(f'  degree: {G.degree(nid)}')
print()
print('CONNECTIONS:')
for neighbor in G.neighbors(nid):
    edge = G.edges[nid, neighbor]
    nlabel = G.nodes[neighbor].get('label', neighbor)
    rel = edge.get('relation', '')
    conf = edge.get('confidence', '')
    src_file = G.nodes[neighbor].get('source_file', '')
    print(f'  --{rel}--> {nlabel} [{conf}] ({src_file})')
"

Replace NODE_NAME with the concept the user asked about. Then write a 3-5 sentence explanation of what this node is, what it connects to, and why those connections are significant. Use the source locations as citations.

After writing the explanation, save it back:

$(cat .graphify_python) -c "
from graphify.ingest import save_query_result
from pathlib import Path
save_query_result(
    question='Explain NODE_NAME',
    answer='ANSWER',
    memory_dir=Path('graphify-out/memory'),
    query_type='explain',
    source_nodes=['NODE_NAME'],
)
print('Explanation saved to graphify-out/memory/')
"

---

For /graphify add

Fetch a URL and add it to the corpus, then update the graph.

$(cat .graphify_python) -c "
import sys
from graphify.ingest import ingest
from pathlib import Path

try:
    out = ingest('URL', Path('./raw'), author='AUTHOR', contributor='CONTRIBUTOR')
    print(f'Saved to {out}')
except ValueError as e:
    print(f'error: {e}', file=sys.stderr)
    sys.exit(1)
except RuntimeError as e:
    print(f'error: {e}', file=sys.stderr)
    sys.exit(1)
"

Replace URL with the actual URL, AUTHOR with the user's name if provided, CONTRIBUTOR likewise. If the command exits with an error, tell the user what went wrong - do not silently continue. After a successful save, automatically run the --update pipeline on ./raw to merge the new file into the existing graph.

Supported URL types (auto-detected):

• Twitter/X → fetched via oEmbed, saved as .md with tweet text and author
• arXiv → abstract + metadata saved as .md
• PDF → downloaded as .pdf
• Images (.png/.jpg/.webp) → downloaded, Claude vision extracts on next run
• Any webpage → converted to markdown via html2text

---

For --watch

Start a background watcher that monitors a folder and auto-updates the graph when files change.

python3 -m graphify.watch INPUT_PATH --debounce 3

Replace INPUT_PATH with the folder to watch. Behavior depends on what changed:

• Code files only (.py, .ts, .go, etc.): re-runs AST extraction + rebuild + cluster immediately, no LLM needed. graph.json and GRAPH_REPORT.md are updated automatically.
• Docs, papers, or images: writes a graphify-out/needs_update flag and prints a notification to run /graphify --update (LLM semantic re-extraction required).

Debounce (default 3s): waits until file activity stops before triggering, so a wave of parallel agent writes doesn't trigger a rebuild per file.

Press Ctrl+C to stop.

For agentic workflows: run --watch in a background terminal. Code changes from agent waves are picked up automatically between waves. If agents are also writing docs or notes, you'll need a manual /graphify --update after those waves.

---

For git commit hook

Install a post-commit hook that auto-rebuilds the graph after every commit. No background process needed - triggers once per commit, works with any editor.

graphify hook install    # install
graphify hook uninstall  # remove
graphify hook status     # check

After every git commit, the hook detects which code files changed (via git diff HEAD~1), re-runs AST extraction on those files, and rebuilds graph.json and GRAPH_REPORT.md. Doc/image changes are ignored by the hook - run /graphify --update manually for those.

If a post-commit hook already exists, graphify appends to it rather than replacing it.

---

For native CLAUDE.md integration

Run once per project to make graphify always-on in Claude Code sessions:

graphify claude install

This writes a ## graphify section to the local CLAUDE.md that instructs Claude to check the graph before answering codebase questions and rebuild it after code changes. No manual /graphify needed in future sessions.

graphify claude uninstall  # remove the section

---

Honesty Rules

• Never invent an edge. If unsure, use AMBIGUOUS.
• Never skip the corpus check warning.
• Always show token cost in the report.
• Never hide cohesion scores behind symbols - show the raw number.
• Never run HTML viz on a graph with more than 5,000 nodes without warning the user.