Graphify

Active
GitHub Python Apache-2.0

Description

AI coding assistant skill that turns any folder of code, docs, papers, images, or videos into a queryable knowledge graph. Works with Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot CLI, and more.

Key Features

  • Knowledge graph generation — automatically converts code, docs, PDFs, images, and videos into queryable knowledge graphs
  • Multi-platform AI assistant integration — supports Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot and 20+ platforms
  • Interactive visualization — generates browsable graph.html with node clicking, filtering, and search
  • Architecture diagram export — exports readable architecture pages with Mermaid call-flow diagrams
  • Project-scoped skill installation — install skills into .claude/skills or .agents/skills directories
  • Git hooks integration — auto-updates knowledge graphs on code commits via post-commit hooks

Use Cases

💡 Large codebase understanding: quickly generate project architecture graphs to help newcomers understand code structure
💡 Document smart retrieval: build indexes over PDF papers and docs for semantic search instead of manual browsing
💡 Code review assistance: discover hidden dependencies and potential impact scopes through knowledge graphs
💡 Multi-modal content management: extract information from images and videos into a unified queryable knowledge base
💡 Project documentation maintenance: auto-update architecture docs after code changes to keep docs in sync

Strengths & Limitations

Strengths

  • Actively maintained, recent updates
  • High community interest (114.0k stars)
  • Permissive open-source license (Apache-2.0)

Quick Start

# Install Graphify (uv recommended)
uv tool install graphifyy

# Register the AI assistant skill
graphify install

# Use in your AI assistant
# Type /graphify . to convert your project into a knowledge graph

# Or use CLI directly
graphify .

Related Projects

MineContext

5.5k · Python
Stale B

A proactive context-aware AI partner from ByteDance Volcengine that uses context engineering to provide AI agents with precise project understanding and code context management.

agentcodingmemory +2
  • · Proactive context engineering delivering daily/weekly summaries, tips, and todos to your homepage
  • · Screenshot-based digital world comprehension via visual language models
  • · Intelligent resurfacing of relevant context during creation without information overload

Nocturne Memory

1.3k · Python
Active A

A lightweight, rollbackable, and visual long-term memory server for MCP agents, replacing traditional vector RAG with reliable context retention.

pythonmcpmemory +2
  • · MCP-based long-term memory server enabling AI to remember identity and history across sessions and models
  • · One soul, any engine — memory stored in independent MCP Server, not bound to any LLM, AI retains full memory when switching models
  • · Namespace isolation support — multiple AI personalities can have completely independent memory spaces without interference

Claude Mem

93.0k · JavaScript
Active A+

A Claude Code plugin that automatically captures coding session context, compresses it with AI, and injects relevant context back into future sessions for persistent memory.

codingmemoryagent +2
  • · Cross-session persistent memory - Automatically captures tool observations and generates semantic summaries, injecting relevant context into new sessions
  • · Progressive disclosure - Layered memory retrieval with token cost visibility for precise control over injected context volume
  • · Skill-based search - Query project history via mem-search skill with semantic project context retrieval