by safishamsi · Codex Skill · ★ 14.6k
graphify An AI coding assistant skill. Type in Claude Code, Codex, OpenCode, or OpenClaw - it reads your files, builds a knowledge graph, and gives you back structure you didn't know was there. Understand a codebase faster. Find the "why" behind architectural decisions. Fully multimodal. Drop in code, PDFs, markdown, screenshots, diagrams, whiteboard photos, even images in other languages - graphify uses Claude vision to extract concepts and relationships from all of it and connects them into one graph. Andrej Karpathy keeps a folder where he drops papers, tweets, screenshots, and notes. graphify is the answer to that problem - 71.5x fewer tokens per query vs reading the raw files, persistent across sessions, honest about what it found vs guessed. How it works graphify ru
| Stars | 14,565 |
| Forks | 1,490 |
| Language | Python |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 57.062/100 |
| Open Issues | 23 |
| Last Updated | 2026-04-09 |
| Created | 2026-04-03 |
| Platforms | claude-code, codex, python |
| Est. Tokens | ~24k |
Explore other popular codex skill tools:
graphify is AI coding assistant skill (Claude Code, Codex, OpenCode, OpenClaw, Factory Droid, Trae). Turn any folder of code, docs, papers, or images into a queryable knowledge graph. It is categorized as a Codex Skill with 14.6k GitHub stars.
graphify is primarily written in Python. It covers topics such as claude-code, codex, graphrag.
You can find installation instructions and usage details in the graphify GitHub repository at github.com/safishamsi/graphify. The project has 14.6k stars and 1490 forks, indicating an active community.
graphify is released under the MIT license, making it free to use and modify according to the license terms.