Ask your AI coding agent to map a repository's runtime architecture as a shareable diagram.
Turn a described login or API flow into an interactive sequence diagram.
Trace how data moves through a pipeline and where sensitive data is exposed.
Produce a presentation-ready architecture diagram for stakeholders without a design tool.
| tt-a1i/archify | jgraph/mxgraph | mailgun/transactional-email-templates | |
|---|---|---|---|
| Stars | 6,925 | 6,923 | 6,937 |
| Language | HTML | HTML | HTML |
| Setup difficulty | easy | moderate | easy |
| Complexity | 2/5 | 3/5 | 1/5 |
| Audience | developer | developer | developer |
Figures from each repo's GitHub metadata at analysis time.
Installed via a single npx command as a skill for an existing AI coding agent.
Archify is a skill that an AI coding agent, such as Claude, Codex CLI, or opencode, can use to turn a plain-English description of a system into a polished diagram. Instead of drawing a rough sketch, it produces a single, self-contained HTML file that you can open in a browser, click around in, and share. You describe what you want, for example a login flow that goes from a browser through a web app, an API, token checking, a cache lookup, and a database fallback, and the agent uses Archify to lay it out. It supports five kinds of technical diagrams: architecture diagrams for showing components and services, workflow diagrams for processes like approvals or CI/CD pipelines, sequence diagrams for showing calls and responses over time, data flow diagrams for tracing how information moves and where it is sensitive, and lifecycle diagrams for showing states, retries, and outcomes. The finished diagrams are interactive rather than static pictures. A viewer can search for a specific part of the system, trace a particular path through it, compare how busy different parts are, or watch a short guided walkthrough, all without the tool inventing connections that were not actually described. Diagrams come in light or dark themes and can include gentle animation. They can be exported as PNG, SVG, animated WebM video, or a ready-to-share image sized for social posts. Under the hood, each diagram is generated from a structured, typed data format with a schema, and the tool runs automatic checks on layout, formatting, and routing before it will replace a working diagram with a new one, so a broken save does not overwrite something that already works. The project describes itself as a way to turn a technical idea into something you can present, not as a general drawing editor or a themed version of existing diagramming tools. It installs as an add-on for supported AI coding agents with a single command line install, and once installed you simply ask your agent in plain language to use Archify on your repository or on a description you give it. The project is released under the MIT license, so it can be used, modified, and redistributed freely, including for commercial purposes, as long as the copyright notice is kept.
An AI agent skill that turns a plain-English system description into an interactive, shareable architecture, workflow, sequence, data-flow, or lifecycle diagram.
Mainly HTML. The stack also includes HTML, JSON, Node.js.
Use freely for any purpose, including commercial use, as long as you keep the copyright notice.
Setup difficulty is rated easy, with roughly 5min to a first successful run.
Mainly developer.
This repo across BitVibe Labs
Verify against the repo before relying on details.