What makes graphify notable?

3.2K downloads. Trust evidence available

How should graphify be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

graphify

AI coding assistant skill for building and querying knowledge graphs from codebases, docs, and media. Use for: understanding complex codebases, architectural... Skill: graphify Owner: fantox Summary: AI coding assistant skill for building and querying knowledge graphs from codebases, docs, and media. Use for: understanding complex codebases, architectural... Tags: latest:2.1.0 Version history: v2.1.0 | 2026-04-19T07:52:21.195Z | user **Credential requirements for semantic extraction now clearly specified in environment metadata.** - Added ANTHROPIC_API_KEY and OPENAI_API_KEY

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

3.2k

Updated

Oct 9, 2026

Version

2.1.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 3.2K downloads reported by the source. Last updated 10/9/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 9, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 9, 2026
Adoption signal: 3.2K downloadsadoption · observed Oct 9, 2026
Latest release: 2.1.0release · observed Apr 19, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17951783tfh7a7znjpezgbe1s84naav:graphify

Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-fantox-graphify/snapshot"

Documentation

CLAWHUB

75,204 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: graphify-skill
description: "AI coding assistant skill for building and querying knowledge graphs from codebases, docs, and media. Use for: understanding complex codebases, architectural analysis, context sharing with OpenClaw/Claude Code, and extracting design rationale from multimodal sources. Always check graphify-out/GRAPH_REPORT.md before grepping or globbing to find relevant files."
metadata:
  openclaw:
    requires:
      bins:
        - python3
        - pip
      env:
        - name: ANTHROPIC_API_KEY
          description: "Required for semantic extraction (docs, PDFs, images). Not needed for AST-only code extraction."
          required: false
        - name: OPENAI_API_KEY
          description: "Alternative LLM backend for semantic extraction."
          required: false
    install:
      - kind: uv
        package: graphify
        bins: [graphify]
    primaryEnv: ""
    emoji: "🕸️"
    homepage: https://github.com/safishamsi/graphify
    os:
      - linux
      - macos
      - windows
---

# Graphify Skill

Graphify turns a folder of code, docs, images, and videos into a **queryable knowledge graph**. After running `graphify .`, the generated `GRAPH_REPORT.md` is referenced by the assistant when you ask it to explore the codebase. Use it to navigate unfamiliar codebases, trace architectural intent, and share context efficiently.

**Credential note:** Semantic extraction (docs, PDFs, images) calls an external LLM using your own API key (`ANTHROPIC_API_KEY` or `OPENAI_API_KEY`). AST code extraction and Whisper transcription run fully locally with no API key required.

> **Token efficiency:** Reading `GRAPH_REPORT.md` is ~71.5× cheaper than reading raw source files. Always check it first.

---

## Installation

### Minimum install
```bash
pip install graphify
```

### Recommended install with all extras
```bash
pip install "graphify[pdf,video,watch,svg]"
```

| Extra | Adds support for |
|-------|-----------------|
| `pdf` | PDF papers and documents |
| `video` | Video/audio transcription via faster-whisper |
| `watch` | `--watch` file monitoring |
| `svg` | `--svg` export |
| `mcp` | Model Context Protocol server |
| `neo4j` | Neo4j graph database integration |
| `office` | Word/Excel/PowerPoint documents |

### Register with OpenClaw
```bash
graphify claw install
```

This copies the skill into OpenClaw's global skill directory and writes an `AGENTS.md` to the project root so the graph is consulted on every tool call.

### Register with other platforms
```bash
graphify claude install     # Claude Code (CLAUDE.md + PreToolUse hook)
graphify cursor install     # Cursor (.cursorrules)
graphify codex install      # Codex (AGENTS.md)
graphify copilot install    # GitHub Copilot CLI
graphify gemini install     # Gemini CLI
graphify aider install      # Aider
```

### Git post-commit hook (optional, local project only)
Installs a hook in the current project's `.git/hooks/` — no global changes.
```bash
graphify hook install
```

_meta.json

{
  "ownerId": "kn71dktm0ht90f72ja215th2bx84mxs8",
  "slug": "graphify",
  "version": "2.1.0",
  "publishedAt": 1776585141195
}

references/api_reference.md

# Graphify API Reference

Complete reference for the `graphify` CLI (package `graphify`, v0.4.23+).

---

## Command Overview

```
graphify <target> [options]       Build or update a knowledge graph
graphify query "<question>"       Semantic search on the graph
graphify path "NodeA" "NodeB"     Shortest path between two nodes
graphify explain "NodeName"       Plain-language node explanation
graphify add <url>                Add external content to the graph
graphify <platform> install       Register with an AI assistant platform
graphify hook install             Install git post-commit rebuild hook
```

---

## Build Commands

### `graphify <target>`

Build a knowledge graph from a directory.

```bash
graphify .                    # current directory
graphify ./src                # specific subdirectory
graphify /absolute/path       # absolute path
```

**Flags:**

| Flag | Description |
|------|-------------|
| `--mode deep` | Aggressive INFERRED edge extraction with confidence scores |
| `--update` | Reprocess only files changed since last run (uses SHA-256 cache) |
| `--directed` | Preserve edge directionality in the output graph |
| `--cluster-only` | Re-run Leiden community detection without re-extracting nodes/edges |
| `--no-viz` | Skip generating `graph.html` (faster; useful in CI) |
| `--watch` | Auto-sync graph as files change (requires `graphify[watch]`) |
| `--wiki` | Generate Wikipedia-style article per node |
| `--svg` | Export SVG visualization (requires `graphify[svg]`) |
| `--graphml` | Export GraphML file for Gephi / yEd |

**Extraction pipeline (in order):**
1. **AST extraction** — tree-sitter deterministic parsing; no LLM calls; produces `EXTRACTED` edges
2. **Transcription** — faster-whisper local audio/video processing; domain-aware prompts
3. **Semantic extraction** — parallel LLM subagents for docs, PDFs, images; produces `EXTRACTED` and `INFERRED` edges

---

## Query Commands

### `graphify query "<question>"`

Semantic natural-language search across the knowledge graph.

```bash
graphify query "where is rate limiting enforced?"
graphify query "what calls the payment processor?" --dfs
```

| Flag | Description |
|------|-------------|
| `--dfs` | Depth-first traversal; traces a specific execution path instead of ranking |

**Returns:** Ranked list of matching nodes with relationship context and source file references.

---

### `graphify path "NodeA" "NodeB"`

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

```bash
graphify path "AuthMiddleware" "PostgresAdapter"
graphify path "UserController" "EmailService"
```

**Use for:** Impact analysis before editing a module, tracing coupling chains, verifying isolation.

---

### `graphify explain "NodeName"`

Generate a plain-language explanation of a node and its relationships.

```bash
graphify explain "UserSessionManager"
graphify explain "RateLimiter"
```

**Returns:** What the node does, what it connects to, and which community it belongs to.

---

## Content

skill-card.md

## Description:

AI coding assistant skill for building and querying knowledge graphs from codebases, docs, and media.

This skill is ready for commercial/non-commercial use.

## Publisher:

[fantox](https://clawhub.ai/user/fantox)

### License/Terms of Use:

MIT-0

## Use Case:

Developers and engineers use Graphify to generate and query knowledge graphs for unfamiliar codebases, architecture analysis, impact tracing, and context sharing with AI coding assistants.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Semantic extraction can send selected documents, PDFs, or images to an external LLM provider when an API key is configured.

Mitigation: Use only intended API keys and review inputs before semantic extraction; AST code extraction and Whisper transcription can run without those API keys.

Risk: Generated knowledge graphs may include sensitive files if the project is indexed without exclusions.

Mitigation: Create a .graphifyignore that excludes secrets, credentials, caches, build output, dependency directories, and other high-noise or sensitive paths before indexing.

Risk: URL ingestion and assistant or git hook installation can add external content or project-local automation.

Mitigation: Run URL ingestion and assistant or git hook setup only when those project-scoped changes are intended.

Risk: The installed graphify package is external to the skill artifact.

Mitigation: Install in a virtual environment and review the graphify package provenance and version before use.

## Reference(s):

- [Graphify API Reference](artifact/references/api_reference.md)
- [ClawHub skill page](https://clawhub.ai/fantox/skills/graphify)
- [Graphify project homepage](https://github.com/safishamsi/graphify)

## Skill Output:

**Output Type(s):** [text, markdown, JSON, shell commands, configuration, guidance]

**Output Format:** [Markdown guidance with inline shell commands and references to generated graph artifacts]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [May reference graphify-out/GRAPH_REPORT.md, graphify-out/graph.json, graph.html, and optional export files produced by the graphify CLI.]

## Skill Version(s):

2.1.0 (source: server release metadata)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

templates/graphifyignore.txt

# .graphifyignore — copy this to your project root and rename to .graphifyignore
# Uses .gitignore syntax. Paths are relative to the project root.
# Graphify will skip any file or directory matched below.

# ── Package managers / dependency trees ──────────────────────────────────────
node_modules/
vendor/
.venv/
venv/
env/
.env/
__pycache__/
*.pyc
*.pyo
.tox/
.nox/
bower_components/
jspm_packages/
.yarn/
.pnp.*

# ── Build and distribution outputs ───────────────────────────────────────────
dist/
build/
out/
.next/
.nuxt/
.output/
.svelte-kit/
target/
bin/
obj/
*.egg-info/
*.dist-info/
site/

# ── Generated / compiled files ────────────────────────────────────────────────
*.min.js
*.min.css
*.bundle.js
*.chunk.js
*.generated.*
*.pb.go
*_pb2.py
*_pb2_grpc.py
*.g.dart

# ── Lock files (high noise, low signal) ──────────────────────────────────────
package-lock.json
yarn.lock
pnpm-lock.yaml
poetry.lock
Cargo.lock
Gemfile.lock
composer.lock
go.sum

# ── Test fixtures, snapshots, and large datasets ─────────────────────────────
__snapshots__/
testdata/
fixtures/
*.snap
*.golden

# ── IDE and editor artifacts ──────────────────────────────────────────────────
.idea/
.vscode/
*.swp
*.swo
.DS_Store
Thumbs.db

# ── Version control internals ─────────────────────────────────────────────────
.git/
.svn/
.hg/

# ── CI and infrastructure ─────────────────────────────────────────────────────
.github/
.circleci/
.gitlab/
.terraform/
*.tfstate
*.tfstate.backup

# ── Logs, coverage, and profiling ─────────────────────────────────────────────
*.log
logs/
coverage/
.nyc_output/
htmlcov/
*.prof
*.trace

# ── Secrets and credentials (never index) ─────────────────────────────────────
.env
.env.*
*.pem
*.key
*.p12
*.pfx
secrets/
credentials/

# ── Graphify cache (never commit) ─────────────────────────────────────────────
graphify-out/cache/

# ── Large binary assets (index if you want vision analysis; exclude otherwise) ─
# *.png
# *.jpg
# *.gif
# *.mp4
# *.mov

Github ReposUpdated 7h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.