Antu (案图): turn structured JSON into one offline HTML legal diagram: fact timelines, procedure flowcharts, relationship diagrams and justification trees. Made for AI agents (MCP server, command line, agent skill) and legal professionals.
- ✓Open-source license (AGPL-3.0)
- ✓Actively maintained (<30d)
- ✓Clear description
- ✓Topics declared
- ✓Documented (README)
claude mcp add antu -- npx -y skills{
"mcpServers": {
"antu": {
"command": "npx",
"args": ["-y", "skills"]
}
}
}Resumen de MCP Servers
# Antu 案图
[](https://github.com/zh-xx/Antu/actions/workflows/verify.yml)
[](https://github.com/zh-xx/Antu/actions/workflows/codeql.yml)
[](https://github.com/zh-xx/Antu/releases)
[](https://www.npmjs.com/package/@zh-xx/antu)
[](LICENSE)
[](package.json)
[](CHANGELOG.md)
[](https://zh-xx.github.io/Antu/)
[](CONTRIBUTING.md)
[中文](README.zh-CN.md) | **English**
Antu turns one JSON document into one self-contained HTML legal diagram. The page is one file of about 2.3 MB that makes no network request and needs no server; it opens offline and can be archived,
printed or sent as an attachment. An AI Agent can read the case materials and write the JSON; the engine then draws the
diagram from it, and the same JSON gives the same diagram. Antu is at version 0.x, and the formats of the relationship
and justification diagrams are still drafts.
## Diagram Types
Four types of legal content, each drawn in several ways. A selector in the page switches between the ways; nothing in the JSON chooses one.
<table>
<tr><th rowspan="2" align="left" valign="middle">Relationship</th><td align="center"><a href="examples/relationship/marketplace-parties.en.json"><img src="assets/kinds/graph.svg" width="88" alt="graph"><br>graph</a></td><td align="center"><a href="examples/relationship/marketplace-parties.en.json"><img src="assets/kinds/focus.svg" width="88" alt="focus view"><br>focus view</a></td><td align="center"><a href="examples/relationship/marketplace-parties.en.json"><img src="assets/kinds/chain.svg" width="88" alt="guarantee chain"><br>guarantee chain</a></td><td align="center"><a href="examples/relationship/marketplace-parties.en.json"><img src="assets/kinds/matrix.svg" width="88" alt="relation matrix"><br>relation matrix</a></td><td align="center"><a href="examples/relationship/marketplace-parties.en.json"><img src="assets/kinds/equity.svg" width="88" alt="equity tree"><br>equity tree</a></td></tr>
<tr><td align="center"><a href="examples/relationship/marketplace-parties.en.json"><img src="assets/kinds/authority.svg" width="88" alt="authority chart"><br>authority chart</a></td><td align="center"><a href="examples/relationship/marketplace-parties.en.json"><img src="assets/kinds/related.svg" width="88" alt="related-party list"><br>related-party list</a></td><td align="center"><a href="examples/relationship/marketplace-parties.en.json"><img src="assets/kinds/path.svg" width="88" alt="relation path"><br>relation path</a></td><td align="center"><a href="examples/relationship/marketplace-parties.en.json"><img src="assets/kinds/summary.svg" width="88" alt="camp summary"><br>camp summary</a></td></tr>
<tr><th rowspan="1" align="left" valign="middle">Fact</th><td align="center"><a href="examples/fact/neighbour-corridor-charging.en.json"><img src="assets/kinds/timeline.svg" width="88" alt="timeline"><br>timeline</a></td><td align="center"><a href="examples/fact/neighbour-corridor-charging.en.json"><img src="assets/kinds/chronicle.svg" width="88" alt="chronicle"><br>chronicle</a></td><td align="center"><a href="examples/fact/neighbour-corridor-charging.en.json"><img src="assets/kinds/scale.svg" width="88" alt="time scale"><br>time scale</a></td></tr>
<tr><th rowspan="1" align="left" valign="middle">Procedure</th><td align="center"><a href="examples/procedure/05-premises-lease.en.json"><img src="assets/kinds/flow.svg" width="88" alt="flowchart"><br>flowchart</a></td><td align="center"><a href="examples/procedure/05-premises-lease.en.json"><img src="assets/kinds/route.svg" width="88" alt="route map"><br>route map</a></td></tr>
<tr><th rowspan="1" align="left" valign="middle">Justification</th><td align="center"><a href="examples/justification/fang-yuan-defense-excess.en.json"><img src="assets/kinds/tree.svg" width="88" alt="reasoning tree"><br>reasoning tree</a></td></tr>
</table>
Relationship diagrams show parties, roles and legal relationships; fact diagrams the time, the participants and how events went;
procedure diagrams a procedural path and its branches; justification diagrams a conclusion drawn from norms and facts. The
relationship and justification schemas are still drafts.
Three looks, called **themes**: `document` (black and white and square, for print and filing; the default), `modern`
(rounded, pale) and `legal` (navy). The reader switches in the page, or a call fixes a page to one. Only the diagram is
themed. See [spec/theme.md](spec/theme.md).
## Usage
```bash
npm install
npm run diagram -- examples/fact/neighbour-corridor-charging.en.json
```
The page is written beside the JSON file. The interface language of a page is set with `?lang=en` or `?lang=zh`; the case content is never translated.
## Principle
```
Agent ──> key information ──> one JSON ──> engine ──> diagram
```
| Role | Does | Determinism |
|---|---|---|
| Model | reads documents, extracts facts, understands meaning | the result may differ from run to run |
| Engine | draws the diagram according to the specification | the same JSON gives the same diagram, whichever model wrote it |
| JSON specification | the only interface between the two | versioned (see [spec/versioning.md](spec/versioning.md)) |
The engine does not write JSON, and the Agent does not draw. The model puts information into JSON; the engine draws. The JSON specification is a specification of its own, for four reasons:
1. General-purpose charting syntax is built on nodes, edges and state machines, and has no place for procedural standing or the source of a piece of evidence.
2. The diagram does not depend on which model extracted the information.
3. The same JSON gives the same diagram at any time and in any environment, so a diagram handed to a court or to the other side can be reproduced.
4. The source is recorded when the facts are extracted: each fact states the document, the page and the provision it rests on, and the diagram shows them. The materials themselves are neither bundled nor linked.
## Agent Integration
The reference material for an Agent, for the fact diagram, is a field table of about 3.4k characters and a mechanism note of about 6.3k characters.
### Skill
```
npx skills add zh-xx/Antu -g
```
The Skill is in [`skills/antu/`](skills/antu/); each [release](https://github.com/zh-xx/Antu/releases) also carries it as `antu-skill-<version>.zip`.
The command line asks the npm registry once a day whether a newer Antu is out (one GET request, nothing of any diagram) and, if so, ends its output with a notice. `ANTU_NO_UPDATE_NOTIFIER=1` turns it off.
### MCP
The MCP server is the npm package [`@zh-xx/antu`](https://www.npmjs.com/package/@zh-xx/antu), registered as `io.github.zh-xx/antu` in the [MCP registry](https://registry.modelcontextprotocol.io).
```json
{
"mcpServers": {
"antu": {
"command": "npx",
"args": ["-y", "-p", "@zh-xx/antu@latest", "antu-mcp"]
}
}
}
```
Tools: `antu_schema`, `antu_guide`, `antu_examples`, `antu_validate`, `antu_layout`, `antu_render`, `antu_preview`, `antu_versions`.
## In an Application
The same package has three entries for an application's own code ([spec/embed.md](spec/embed.md)):
```js
import { mount } from '@zh-xx/antu/embed' // draw a diagram inside your page, in a shadow root
import { validate } from '@zh-xx/antu/validate' // check the JSON your model wrote; each error names its field
import { renderHtml } from '@zh-xx/antu/html' // the self-contained page as a string (Node)
const diagram = mount(element, spec, { lang: 'en', onEvent: (e) => console.log(e) })
```
## Documentation
- Design documents for people, under [`spec/`](spec/): [architecture](spec/v0-architecture.md), [the source types](spec/source-schema-draft.md), [themes](spec/theme.md), [the MCP server](spec/mcp-server.md), [embedding in an application](spec/embed.md), and the diagrams ([fact](spec/fact/), [procedure](spec/procedure/schema-draft.md), [relationship](spec/relationship/schema-draft.md), [justification](spec/justification/schema-draft.md)). The notes for Agents are under [`spec/agent/`](spec/agent/).
- [CHANGELOG.md](CHANGELOG.md) and the versioning rules in [spec/versioning.md](spec/versioning.md).
- Known problems and requests are tracked as [GitHub issues](https://github.com/zh-xx/Antu/issues). Working rules for contributors are in [CONTRIBUTING.md](CONTRIBUTING.md).
## License
Copyright (C) 2026 Ji Cheng.
Antu is free software, licensed under the **GNU Affero General Public License, version 3 or any later version** ([`LICENSE`](LICENSE), SPDX `AGPL-3.0-or-later`). In short: you may use, study, change and share it, including for commercial purposes. If you distribute a changed version, or let others use it over a network (for example as a hosted service), you must release your changes under the same licence, keep the copyright and licence notices, and make the source available. There is no warranty. This summary is not the licence; the licence text is.
- **Additional permission (AGPL section 7).** A page made with Antu contains Antu's code together with the diagram data you gave it. The diagram data, and the content of the diagram you drew from your material, are not part of Antu and are not covered by this licence: you may keep them private, publish them, or sell them on any terms you like. The licence covers Antu's code in the page, and the notices in the page must stay with it. The same text is in Lo que la gente pregunta sobre Antu
¿Qué es zh-xx/Antu?
+
zh-xx/Antu es mcp servers para el ecosistema de Claude AI. Antu (案图): turn structured JSON into one offline HTML legal diagram: fact timelines, procedure flowcharts, relationship diagrams and justification trees. Made for AI agents (MCP server, command line, agent skill) and legal professionals. Tiene 2 estrellas en GitHub y su última actualización registrada es del 2026-10-09.
¿Cómo se instala Antu?
+
Puedes instalar Antu clonando el repositorio (https://github.com/zh-xx/Antu) o siguiendo las instrucciones del README en GitHub. ClaudeWave también te ofrece bloques de instalación rápida en esta misma página.
¿Es seguro usar zh-xx/Antu?
+
Nuestro agente de seguridad ha analizado zh-xx/Antu y le ha asignado un Trust Score de 95/100 (tier: Verified). Revisa el desglose completo de comprobaciones superadas y flags en esta página.
¿Quién mantiene zh-xx/Antu?
+
zh-xx/Antu es mantenido por zh-xx. La última actividad registrada en GitHub es del 2026-10-09, con 24 issues abiertos.
¿Hay alternativas a Antu?
+
Sí. En ClaudeWave puedes explorar mcp servers similares en /categories/mcp, ordenados por popularidad o actividad reciente.
Despliega Antu en tu cloud
Lleva este repo a producción en minutos. Cada plataforma genera su propio entorno con variables de entorno editables.
¿Mantienes este repo? Añade un badge a tu README
Pega el badge en tu README de GitHub para mostrar que está auditado por ClaudeWave. Cada badge enlaza de vuelta a esta página y muestra el Trust Score actual.
Más MCP Servers
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
An open-source AI agent that brings the power of Gemini directly into your terminal.
Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl! Don't be shy, join here: https://discord.gg/EMgGbDceNQ and follow here for daily tips and tricks: https://x.com/Scrapling_dev
The fastest path to AI-powered full stack observability, even for lean teams.