tt-a1i/archify

★ 63,945⑂ 4,240

Agent skill for beautiful, verifiable architecture, workflow, sequence, data-flow, and lifecycle diagrams—self-contained HTML with motion and crisp export.

About tt-a1i/archify

tt-a1i/archify is an open-source project on GitHub, mainly written in JavaScript. Agent skill for beautiful, verifiable architecture, workflow, sequence, data-flow, and lifecycle diagrams—self-contained HTML with motion and crisp export. It currently holds 63,945 stars and 4,240 forks with 176 open issues, and was last pushed on 2026-09-16 (repository created 2026-04-15).

Project Overview

AI Homed tracks it on the AI Models & LLM Tools board, currently at rank #42 with 0 new stars today.

GitHub Repository Details

Repository tt-a1i/archify · default branch main · size 159491 KB · watchers 193 · source: GitHub REST API and repository README

README

https://github.com/tt-a1i/archify/blob/HEAD/Archify

Turn anything you want to understand, plan, or share into an interactive visual.

https://github.com/tt-a1i/archify/blob/HEAD/Archify — interactive diagrams

Official channels: archify.si · GitHub
Archify is free and open source. Third-party online services and paid plans are operated by their respective providers and do not represent Archify. Service details →

Start with an idea, a question, or a plan. Describe it to your AI agent, and Archify turns it into an interactive HTML you can explore, customize, and share. From travel itineraries and learning maps to complex systems—make it your own.

See what the community is creating—and imagine what you could make next.

Live demos  ·  Get started  ·  Scenario guide  ·  Community  ·  简体中文  ·  日本語  ·  한국어

https://github.com/tt-a1i/archify/blob/HEAD/tt-a1i/archify | Trendshift

https://github.com/tt-a1i/archify/blob/HEAD/GitHub stars https://github.com/tt-a1i/archify/blob/HEAD/130K+ installs on skills.sh https://github.com/tt-a1i/archify/blob/HEAD/MIT License https://github.com/tt-a1i/archify/blob/HEAD/Works with Claude Code, Codex, Cursor, and OpenCode https://github.com/tt-a1i/archify/blob/HEAD/Stable version 3.1.0

https://github.com/tt-a1i/archify/blob/HEAD/Archify website https://github.com/tt-a1i/archify/blob/HEAD/Join Archify on Discord https://github.com/tt-a1i/archify/blob/HEAD/Archify WeChat group https://github.com/tt-a1i/archify/blob/HEAD/Archify QQ group https://github.com/tt-a1i/archify/blob/HEAD/Follow the creator on X

❤️ Partners & sponsors: Kimi Work · Supercode · OpenLux

See Archify in action

https://github.com/user-attachments/assets/78570807-ba1d-4737-953f-55504a378a87

One sentence. Your repo, mapped. Watch the 35-second demo: explore the diagram, follow source links, and trace a path. Try the interactive examples ↗

Install, then describe your idea

Works with Cursor, Claude Code, Codex CLI, and OpenCode. See installation options below for additional integrations.

npx skills add tt-a1i/archify -g

Send this to your agent:

Use Archify to diagram a web request: Browser calls the API,
the API checks Redis, and a cache miss queries PostgreSQL and fills the cache.

Then continue: “Add authentication”, “Highlight the cache-miss path”, or “Switch to the light theme”.

No repository is required: start with a description, or ask your agent to read a repository for a source-backed architecture diagram.

Choose your agent · Installation details and update checks · Create and check diagrams with your agent

❤️ Sponsors

https://github.com/tt-a1i/archify/blob/HEAD/Archify × Kimi Work collaboration banner

Archify × Kimi Work. Find Archify in the Kimi Work plugin store as Interactive Architecture Diagram. Describe your system in one sentence to create an interactive diagram. Try it in Kimi Work →

https://github.com/tt-a1i/archify/blob/HEAD/Supercode
supercode.sh
Supercode sponsors Archify and enhances Codex and Cursor with token optimization, curated Skills, and spec-driven development. Archify is featured as a Supercode Editor’s Choice skill.

https://github.com/tt-a1i/archify/blob/HEAD/Supercode Editor’s Choice — Archify
https://github.com/tt-a1i/archify/blob/HEAD/OpenLux
OpenLux
Thank you to OpenLux for sponsoring this project! OpenLux is an all-in-one AI platform for businesses, bringing together leading AI models from major providers worldwide. With fast, reliable service and responsive technical support, OpenLux offers base pricing for Claude, OpenAI, and Gemini models as low as 8.82%, 4%, and 8% of official rates, respectively.

Exclusive offer for Archify users: Sign up through our referral link and enjoy up to 7.5% off credit top-ups!

Get started with OpenLux →
https://github.com/tt-a1i/archify/blob/HEAD/PackyCode
PackyCode
Access leading AI models through PackyCode with one API endpoint and one API key. Enjoy automatic failover and dedicated high-speed routes for Codex and Claude Code.

Get started with $1 in free credits, a discount on your first top-up, and savings of up to 80% on eligible routes. Pay in RMB with no currency conversion markups or extra top-up fees.

Get started with PackyCode →
https://github.com/tt-a1i/archify/blob/HEAD/AICodeMirror
AICodeMirror
Thank you to AICodeMirror for sponsoring Archify! AICodeMirror provides API relay services for Claude, Codex, and Gemini, with enterprise-grade concurrency, invoice issuance, and 24/7 technical support. Codex pricing starts at 7% of standard rates, with additional top-up discounts.

Exclusive offer for Archify users: Register through our referral link to receive 20% off your first top-up.

Try AICodeMirror →
https://github.com/tt-a1i/archify/blob/HEAD/Infistar.cc
Infistar.cc
Thank you to Infistar.cc for sponsoring Archify! One API key covers text, image, and video creation with GPT, Claude, Gemini, DeepSeek, Qwen, Kling, and other models, without switching groups. Model API pricing starts at 1% of official rates, and AI images start at ¥0.06 each.

Exclusive offer for Archify users: Sign up through our referral link for $5 in trial credits and a special offer on your first top-up.

Try Infistar →
https://github.com/tt-a1i/archify/blob/HEAD/Archify × Raven
EverMind · Raven
EverMind sponsors Archify and builds memory infrastructure for agents. Its Raven harness supports Archify as a Skill for verified, interactive system maps.
Want to sponsor Archify? Contact us by email.

Show what matters

| Explain an agent workflow | Follow a cache miss | Explore service relationships | |---|---|---| | Agent workflow tracing everything the planner drives | Cache-miss sequence showing the Web App to Postgres route | Production architecture comparing backend and database roles | | Trace everything downstream of one step. | Highlight the path from web app to database. | Focus on authored backend and database connections. |

The Proof Lab contains all 11 checked-in scenarios, their JSON sources, and validation receipts.

Understand a real repository

CODE → DIAGRAM · A source-backed system map

MCO runtime architecture generated from the public mco-org/mco repository

Archify traced mco-org/mco at 9f1a1cf and produced this checked map. Open it ↗ · trace reach ↗ · typed source

Easy to extend. More ways to make it yours.

COMMUNITY STORIES · Selected examples shared by users

Keep building after the diagram is generated. Archify is open source and its output is standalone HTML. Ask your agent to adapt it, connect useful links, or add interactions for your own workflow. Community creations already span team collaboration, travel planning, legal citation checks, contract review, and incident retrospectives. These are just a few examples.

One user started with a hand-drawn multi-agent architecture, turned it into an interactive diagram, then added a Kimi execution pool through conversation. Others asked their agent to read a project and brought the resulting architecture into Feishu or DingTalk for team discussion.

Another user turned a Shanghai CityWalk guide into a four-day itinerary: switch between days, inspect a stop, and jump to Amap, Xiaohongshu, or Dianping. The author also added arrival check-ins and stop notes, turning the itinerary into a small tool to use during the trip. These extensions were added by the community author for this particular artifact.

▶ Explore the interactive Shanghai CityWalk

A community-created four-day Shanghai CityWalk itinerary

▶ Try the interactive version · Switch between D1–D4 and click a place to explore.

Community artifact · Shanghai CityWalk · Four days of routes and place links

Download it. Open it. Explore it.

The output is a self-contained HTML file. Download it and open it in your browser to use the node details and path exploration included in that artifact. No Archify installation is needed to view it. Send the HTML to someone else and the interactions go with it; external websites and map links need a network connection.

Explore the Shanghai CityWalk ↗ · Download HTML ↓

Try switching between D1–D4, opening a place card, or following a map link. Times and place information reflect the author's original itinerary.

Community and recognition

A selection of public coverage, community shares, and historical milestones. Follow the links for dates and sources.

Preview

Themes, exports, and share cards

Same diagram, two themes, one click to switch:

| Dark | Light | |---|---| | Dark theme | Light theme |

The Export menu copies PNG to the clipboard and downloads static or motion formats:

Export menu

After tracing a route, Export → Route Share Card downloads that authored path as a 1200×630 PNG with the full diagram retained for context.

Route Share Card showing the exact Users to API Server path with the full architecture retained as context

After tracing authored Upstream or Downstream reach, Export → Reach Share Card captures that exact reading without claiming runtime impact.

MCO downstream Reach Share Card showing authored relationships from Command Router

Open examples/web-app.html locally to try the complete viewer.

Quick start

Current stable version: v3.1.0. See Changelog.

1. Install

npx skills add tt-a1i/archify -g
More installation options and update-check details

For an explicit, non-interactive Cursor install:

npx -y skills add tt-a1i/archify --skill archify --agent cursor --global --copy --yes

To try without installing:

npx skills use tt-a1i/archify@archify --agent codex

DSH community opt-in: dsh plugin --profile web add @tt-a1i/archify-dsh@1.0.0

The agent switcher covers cursor, codex, claude-code, and opencode.

Archify may GET the fixed stable manifest solely to show an optional reminder; it never downloads or installs updates. Successful checks wait about 24 hours (±20%); active use retries failures after 6, then 24 hours. The server sees normal HTTP metadata (IP and time), but receives no version, Agent, project data, prompts, account/device ID, or ETag. You decide whether and when to update. Set ARCHIFY_UPDATE_CHECK_DISABLED=1 to disable networking and reminder-state writes.

Stay updated

Installations with the update checker also check for newer stable releases during diagram delivery and can show a reminder. Older installations without the checker need a manual update to gain this feature. You choose whether and when to upgrade; Archify never installs updates automatically.

2. Start from a description — no repository required

Use Archify to draw: Browser -> API -> Redis cache -> PostgreSQL fallback.

For source evidence, open a repository and ask:

Analyze this repository, then use archify to create a high-level runtime architecture diagram.
Show 8–12 core components, one primary path, external dependencies, and trust boundaries.
Put supporting detail in cards instead of adding more edges.

3. Refine in chat

Continue with focused requests such as add Redis, move auth to the left, or highlight the rollback path. Archify keeps the typed source available for targeted iteration.

Choose the right diagram

Ten diagram types, architecture comparisons, and examples

| Type | Best for | Include in your prompt | |---|---|---| | Architecture | Components, services, storage, boundaries | Scope, core components, primary path | | Workflow | CI/CD, approvals, tool calls, runbooks | Participants, order, branches, exceptions | | Sequence | API calls, cache fallback, auth, async traces | Callers, callees, returns, timing | | Data Flow | Pipelines, lineage, PII, consumers | Sources, transforms, stores, boundaries | | Lifecycle | States, retries, waits, terminal outcomes | States, events, retry and cancellation paths | | ERD | Database schemas: tables, columns, keys, cardinality | Tables, every column with its type, primary/foreign/unique keys, relationship cardinality | | Class | Classes, interfaces, selected members, type relationships | Types, key members, inheritance and implementations, composition, dependencies | | Tree | Single-parent hierarchies: repositories, modules, capability breakdowns | Root, levels, what each branch contains | | Timeline | When things happened: incident reviews, release histories | Timestamps with time zone, events, source lanes, whether times are observed or illustrative | | Waterfall | Where the time went in one request or agent run | Spans, start times and durations, nesting, whether timings are measured or illustrative |

Architecture's optional deployment-ownership profile fails closed when authored owners, region placement, private database scope, or named crossings are missing; it is never implicit and does not inspect live infrastructure. See the checked deployment proof.

For design or PR review, Architecture Delta compares validated Before / Delta / After snapshots with a machine receipt. Select an authored change or play one finite, viewer-only Review; it infers no impact, risk, or merge safety.

node archify/bin/archify.mjs compare architecture base.json head.json architecture-delta.html --json

Architecture Delta showing added, removed, changed, and moved authored facts

Not sure which one fits? Use the interactive scenario guide, or ask the zero-dependency CLI:

node archify/bin/archify.mjs guide "Show an API request with Redis cache miss"
node archify/bin/archify.mjs guide "Map Kafka topics, consumer groups, replay, and DLQ" --json

Workflow keeps the happy path clear across lanes:

Workflow example

Sequence explains one interaction over time:

Sequence example

Data Flow makes movement and sensitivity boundaries explicit:

Data Flow example

Lifecycle separates progress, waits, retries, and terminal outcomes:

Lifecycle example

New in 3.1: ERD, Class, Tree, Timeline and Waterfall.

ERD keeps tables, every column and key, and relationship cardinality together:

ERD example: an order management schema with customer, order, payment, inventory, product and order item tables grouped by domain

Class shows contracts, selected members, and which types depend on or implement them:

Class example: OrderService depends on the PaymentGateway interface, implemented by card and wallet gateways

Tree shows single-parent containment, such as a capability breakdown:

Tree example: a payment platform broken down into orders, payments and operations capabilities

Timeline places events on one proportional clock, with a lane per source:

Timeline example: an illustrative payment incident with release, monitoring and response events on one clock

Waterfall shows where the time went across nested and overlapping spans:

Waterfall example: illustrative timing of a checkout request where inventory lookup and discount calculation run concurrently

Explore these examples: ERD · Class · Tree · Timeline · Waterfall. The Timeline and Waterfall examples use illustrative data; treat timestamps or durations as real only when they come from logs or traces.

Architecture examples: web-app · Archify pipeline · grid placement · desktop agent

Why Archify

| Understand the structure | Walk through the story | |---|---| | Map components, workflows, and relationships from code or a description. | Explore nodes, follow paths, and share any view as a link. | | Extend it your way | Share the result | | Keep an editable source and build on the open-s

GitHub Stars & Activity

63,945Stars
4,240Forks
176Open issues
JavaScriptLanguage

GitHub Popularity

GitHub stars63,945
Forks4,240
Open issues176
Primary languageJavaScript
LicenseMIT
Stars gained today0
Created2026-04-15
Last pushed2026-09-16

Trending History

Daily boardrank #42 · ▲ 0 stars
Weekly boardrank #42 · ▲ 0 stars
Monthly boardrank #42 · ▲ 0 stars

Related AI Projects

1

affaan-m / ECC

JavaScript★ 283,160⑂ 0
→
2

DietrichGebert / ponytail

JavaScript★ 166,923⑂ 0
→
3

Mintplex-Labs / anything-llm

JavaScript★ 67,281⑂ 0
→
4

SillyTavern / SillyTavern

JavaScript★ 34,647⑂ 0
→
5

morluto / rea

TypeScript★ 320,235⑂ 0
→
6

NousResearch / hermes-agent

Python★ 254,906⑂ 0
→
7

firecrawl / firecrawl

TypeScript★ 192,727⑂ 0
→
8

Significant-Gravitas / AutoGPT

Python★ 187,642⑂ 0
→

More AI Rankings