/graphify

Turn any folder of files into a navigable knowledge graph with community detection, an honest audit trail, and agent-readable outputs: graphify-out/wiki/, GraphRAG-ready JSON, and a plain-language GRAPH_REPORT.md. HTML visualization is opt-in.

Usage

/graphify                                             # full pipeline on current directory → Obsidian vault
/graphify <path>                                      # full pipeline on specific path
/graphify https://github.com/<owner>/<repo>           # clone repo then run full pipeline on it
/graphify https://github.com/<owner>/<repo> --branch <branch>  # clone a specific branch
/graphify <url1> <url2> ...                           # clone multiple repos, build each, merge into one cross-repo graph
/graphify <path> --mode deep                          # thorough extraction, richer INFERRED edges
/graphify <path> --update                             # incremental - re-extract only new/changed files
/graphify <path> --directed                            # build directed graph (preserves edge direction: source→target)
/graphify <path> --whisper-model medium                # use a larger Whisper model for better transcription accuracy
/graphify <path> --cluster-only                       # rerun clustering on existing graph
/graphify <path> --no-viz                             # skip optional visualization, keep report + JSON + wiki
/graphify <path> --html                               # also generate graph.html visualization
/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 <path> --wiki                               # explicit wiki generation (default for agent workflows and hooks)
/graphify <path> --obsidian --obsidian-dir ~/vaults/my-project  # write vault to custom path (e.g. existing vault)
/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.

If the path argument starts with https://github.com/ or http://github.com/, treat it as a GitHub URL — run Step 0 before anything else, then continue with the resolved local path.

Follow these steps in order. Do not skip steps.

Step 0 - Clone GitHub repo(s) (only if a GitHub URL was given)

Single repo:

LOCAL_PATH=$(graphify clone <github-url> [--branch <branch>])
# Use LOCAL_PATH as the target for all subsequent steps

Multiple repos (cross-repo graph):

# Clone each repo, run the full pipeline on each, then merge
graphify clone <url1>   # → ~/.graphify/repos/<owner1>/<repo1>
graphify clone <url2>   # → ~/.graphify/repos/<owner2>/<repo2>
# Run /graphify on each local path to produce their graph.json files
# Then merge:
graphify merge-graphs \
  ~/.graphify/repos/<owner1>/<repo1>/graphify-out/graph.json \
  ~/.graphify/repos/<owner2>/<repo2>/graphify-out/graph.json \
  --out graphify-out/cross-repo-graph.json

Graphify clones into ~/.graphify/repos/<owner>/<repo> and reuses existing clones on repeat runs. Each node in the merged graph carries a repo attribute so you can filter by origin.

Step 1 - Ensure graphify is installed

# Detect the correct Python interpreter (handles uv tool, pipx, venv, system installs)
PYTHON=""
GRAPHIFY_BIN=$(which graphify 2>/dev/null)
# 1. uv tool installs — most reliable on modern Mac/Linux
if [ -z "$PYTHON" ] && command -v uv >/dev/null 2>&1; then
    _UV_PY=$(uv tool run graphifyy python -c "import sys; print(sys.executable)" 2>/dev/null)
    if [ -n "$_UV_PY" ]; then PYTHON="$_UV_PY"; fi
fi
# 2. Read shebang from graphify binary (pipx and direct pip installs)
if [ -z "$PYTHON" ] && [ -n "$GRAPHIFY_BIN" ]; then
    _SHEBANG=$(head -1 "$GRAPHIFY_BIN" | tr -d '#!')
    case "$_SHEBANG" in
        *[!a-zA-Z0-9/_.-]*) ;;
        *) "$_SHEBANG" -c "import graphify" 2>/dev/null && PYTHON="$_SHEBANG" ;;
    esac
fi
# 3. Fall back to python3
if [ -z "$PYTHON" ]; then PYTHON="python3"; fi
"$PYTHON" -c "import graphify" 2>/dev/null || "$PYTHON" -m pip install graphifyy -q 2>/dev/null || "$PYTHON" -m pip install graphifyy -q --break-system-packages 2>&1 | tail -3
# Write interpreter path for all subsequent steps (persists across invocations)
mkdir -p graphify-out
"$PYTHON" -c "import sys; open('graphify-out/.graphify_python', 'w').write(sys.executable)"
# Save scan root so `graphify update` (no args) knows where to look next time
echo "$(cd INPUT_PATH && pwd)" > graphify-out/.graphify_root

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

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

Step 2 - Detect files

$(cat graphify-out/.graphify_python) -c "
import json
from graphify.detect import detect
from pathlib import Path
result = detect(Path('INPUT_PATH'))
print(json.dumps(result))
" > graphify-out/.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
  video:    N files (.mp4 .mp3 ...)

Omit any category with 0 files from the summary.

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 2.5 if video files were detected, or Step 3 if not.

Step 2.5 - Transcribe video / audio files (only if video files detected)

Skip this step entirely if detect returned zero video files.

Video and audio files cannot be read directly. Transcribe them to text first, then treat the transcripts as doc files in Step 3.

Strategy: Read the god nodes from graphify-out/.graphify_detect.json (or the analysis file if it exists from a previous run). You are already a language model — write a one-sentence domain hint yourself from those labels. Then pass it to Whisper as the initial prompt. No separate API call needed.

However, if the corpus has only video files and no other docs/code, use the generic fallback prompt: "Use proper punctuation and paragraph breaks."

Step 1 - Write the Whisper prompt yourself.

Read the top god node labels from detect output or analysis, then compose a short domain hint sentence, for example:

• Labels: transformer, attention, encoder, decoder → "Machine learning research on transformer architectures and attention mechanisms. Use proper punctuation and paragraph breaks."
• Labels: kubernetes, deployment, pod, helm → "DevOps discussion about Kubernetes deployments and Helm charts. Use proper punctuation and paragraph breaks."

Set it as WHISPER_PROMPT to use in the next command.

Step 2 - Transcribe:

GRAPHIFY_WHISPER_MODEL=base  # or whatever --whisper-model the user passed
$(cat graphify-out/.graphify_python) -c "
import json, os
from pathlib import Path
from graphify.transcribe import transcribe_all

detect = json.loads(Path('graphify-out/.graphify_detect.json').read_text())
video_files = detect.get('files', {}).get('video', [])
prompt = os.environ.get('GRAPHIFY_WHISPER_PROMPT', 'Use proper punctuation and paragraph breaks.')

transcript_paths = transcribe_all(video_files, initial_prompt=prompt)
print(json.dumps(transcript_paths))
" > graphify-out/.graphify_transcripts.json

After transcription:

• Read the transcript paths from graphify-out/.graphify_transcripts.json
• Add them to the docs list before dispatching semantic subagents in Step 3B
• Print how many transcripts were created: Transcribed N video file(s) -> treating as docs
• If transcription fails for a file, print a warning and continue with the rest

Whisper model: Default is base. If the user passed --whisper-model <name>, set GRAPHIFY_WHISPER_MODEL=<name> in the environment before running the command above.

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 (LLM, costs tokens).

Before dispatching subagents: check whether MOONSHOT_API_KEY is set. If it is NOT set, print this one-liner to the user:

Tip: set MOONSHOT_API_KEY to use Kimi K2.6 for semantic extraction — 3x cheaper, richer graphs (pip install 'graphifyy[kimi]').

Print it once, then continue. If MOONSHOT_API_KEY IS set, use graphify.llm.extract_corpus_parallel(files, backend="kimi") for semantic extraction instead of dispatching Claude subagents.

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-out/.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-out/.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, cache_root=Path('.'))
    Path('graphify-out/.graphify_ast.json').write_text(json.dumps(result, indent=2))
    print(f'AST: {len(result[\"nodes\"])} nodes, {len(result[\"edges\"])} edges')
else:
    Path('graphify-out/.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-out/.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-out/.graphify_python) -c "
import json
from graphify.cache import check_semantic_cache
from pathlib import Path

detect = json.loads(Path('graphify-out/.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-out/.graphify_cached.json').write_text(json.dumps({'nodes': cached_nodes, 'edges': cached_edges, 'hyperedges': cached_hyperedges}))
Path('graphify-out/.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-out/.graphify_uncached.txt. If all files are cached, skip to Part C directly.

Step B1 - Split into chunks

Load files from graphify-out/.graphify_uncached.txt. Split into chunks of 20-25 files each. Each image gets its own chunk (vision needs separate context). When splitting, group files from the same directory together so related artifacts land in the same chunk and cross-file relationships are more likely to be extracted.

Step B2 - Dispatch ALL subagents in a single message

Call the Agent tool multiple times IN THE SAME RESPONSE - one call per chunk. This is the only way they run in parallel. If you make one Agent call, wait, then make another, you are doing it sequentially and defeating the purpose.

IMPORTANT - subagent type: Always use subagent_type="general-purpose". Do NOT use Explore - it is read-only and cannot write chunk files to disk, which silently drops extraction results. General-purpose has Write and Bash access which the subagent needs.

Concrete example for 3 chunks:

[Agent tool call 1: files 1-15, subagent_type="general-purpose"]
[Agent tool call 2: files 16-30, subagent_type="general-purpose"]
[Agent tool call 3: files 31-45, subagent_type="general-purpose"]

All three in one message. Not three separate messages.

Each subagent receives this exact prompt (substitute FILE_LIST, CHUNK_NUM, TOTAL_CHUNKS, and 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. For rationale (WHY decisions were made, trade-offs, design intent): store as a `rationale` attribute on the relevant concept node — do NOT create a separate rationale node or fragment node. Only create a node for something that is itself a named entity or concept. Use `file_type:"rationale"` for concept-like nodes (ideas, principles, mechanisms, design patterns). Do NOT invent file_types like `concept` — valid values are only `code|document|paper|image|rationale`.
Code files: when adding `calls` edges, source MUST be the caller (the function/class doing the calling), target MUST be the callee. Never reverse this direction.
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: pick exactly ONE value from this set — never 0.5:
    0.95  direct structural evidence (shared data structure, named cross-file reference).
    0.85  strong inference (clear functional alignment, no direct symbol link).
    0.75  reasonable inference (shared problem domain + similar shape, requires interpretation).
    0.65  weak inference (thematically related, no shape evidence).
    0.55  speculative but plausible (surface-level co-occurrence only).
  Models follow discrete rubrics better than continuous ranges; the bimodal
  distribution observed in production (>50% at 0.5, >40% at 0.85+) shows the
  range guidance is being collapsed to a binary. If no value above fits, mark
  the edge AMBIGUOUS rather than picking 0.4 or below.
- AMBIGUOUS edges: 0.1-0.3

Node ID format: lowercase, only `[a-z0-9_]`, no dots or slashes. Format: `{stem}_{entity}` where stem is the filename without extension and entity is the symbol name, both normalized (lowercase, non-alphanumeric chars replaced with `_`). Example: `src/auth/session.py` + `ValidateToken` → `session_validatetoken`. This must match the ID the AST extractor generates so cross-references between code and semantic nodes connect correctly. CRITICAL: never append chunk numbers, sequence numbers, or any suffix to an ID (no `_c1`, `_c2`, `_chunk2`, etc.). IDs must be deterministic from the label alone — the same entity must always produce the same ID regardless of which chunk processes it.

Output exactly this JSON (no other text):
{"nodes":[{"id":"session_validatetoken","label":"Human Readable Name","file_type":"code|document|paper|image|rationale","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:

• Check that graphify-out/.graphify_chunk_NN.json exists on disk — this is the success signal
• If the file exists and contains valid JSON with nodes and edges, include it and save to cache
• If the file is missing, the subagent was likely dispatched as read-only (Explore type) — print a warning: "chunk N missing from disk — subagent may have been read-only. Re-run with general-purpose agent." Do not silently skip.
• 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 or are missing, stop and tell the user to re-run and ensure subagent_type="general-purpose" is used.

Merge all chunk files into .graphify_semantic_new.json. After each Agent call completes, read the real token counts from the Agent tool result's usage field and write them back into the chunk JSON before merging — the chunk JSON itself always has placeholder zeros. Then run:

$(cat graphify-out/.graphify_python) -c "
import json, glob
from pathlib import Path

chunks = sorted(glob.glob('graphify-out/.graphify_chunk_*.json'))
all_nodes, all_edges, all_hyperedges = [], [], []
total_in, total_out = 0, 0
for c in chunks:
    d = json.loads(Path(c).read_text())
    all_nodes += d.get('nodes', [])
    all_edges += d.get('edges', [])
    all_hyperedges += d.get('hyperedges', [])
    total_in += d.get('input_tokens', 0)
    total_out += d.get('output_tokens', 0)
Path('graphify-out/.graphify_semantic_new.json').write_text(json.dumps({
    'nodes': all_nodes, 'edges': all_edges, 'hyperedges': all_hyperedges,
    'input_tokens': total_in, 'output_tokens': total_out,
}, indent=2))
print(f'Merged {len(chunks)} chunks: {total_in:,} in / {total_out:,} out tokens')
"

Save new results to cache:

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

new = json.loads(Path('graphify-out/.graphify_semantic_new.json').read_text()) if Path('graphify-out/.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-out/.graphify_semantic.json:

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