Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
China Travel Kit
Source-aware China inbound travel data, CLI, HTTP API, and MCP server
Install: git clone https://github.com/tczyliu/china-travel-kit
Install
$
git clone https://github.com/tczyliu/china-travel-kitInstall command taken from the project's README or registry entry. Always review code before running it.
README excerpt
Read full README on GitHub →Huaxingzhi · 华行志
A source-aware China travel planning Skill and open knowledge base for humans, apps, and AI agents.
简体中文 · Project analysis (中文) · Roadmap · Contributing
Current version: v0.5.0 Alpha
Author contact: WeChat Changzhanzhang
Huaxingzhi (technical project name: China Travel Kit) is an open, bilingual Agent Skill and travel knowledge base with an explainable requirement matcher, visual Chinese travel finder, zero-runtime-dependency Python query engine, CLI, HTTP API, and MCP server. It focuses on the parts of China travel that are difficult for international visitors to verify: visitor areas, reservations, passport-specific instructions, seasonal risks, accessibility, emergency context, transport context, official city tourism portals, and data freshness.
This is an alpha dataset and developer preview, not a booking service or a live navigation system. It currently covers 56 places across Beijing, Shanghai, Guangzhou, Shenzhen, Chengdu, Xi'an, Hangzhou, and Lijiang. The first expansion prioritizes officially sourced 5A/4A attractions in major gateway and tourism cities; none is a complete city guide.
Why this project exists
Travel articles are plentiful. Reusable, source-linked, reviewable China travel data is not. This repository makes each fact easy to inspect and update through pull requests, while letting one data layer power several interfaces:
JSON city records
├── CLI search and itinerary drafts
├── local HTTP API
└── MCP tools for AI clients
Every attraction record includes sources and last_verified. Prices and reservation rules are deliberately nullable: an unknown value is safer than a confident but outdated answer.
Try it in 60 seconds
Requires Python 3.10 or newer. No runtime packages are required.
git clone https://github.com/tczyliu/china-travel-kit.git
cd china-travel-kit
python3 -m china_travel_kit search museum --city Beijing
python3 -m china_travel_kit recommend 'First visit: pandas, food, relaxed pace' --travelers 2 --start-date 2026-07-10 --end-date 2026-07-12
python3 -m china_travel_kit areas --city Beijing
python3 -m china_travel_kit prepare 成都 --month 7
python3 -m china_travel_kit plan 丽江 --days 2 --interests mountain photography
python3 -m china_travel_kit emergency 丽江
python3 -m china_travel_kit freshness
python3 -m china_travel_kit integrity
Agent Skill
The repository root is an installable Agent Skill. SKILL.md defines when to use the toolkit, how to preserve Chinese and English place names, and when live facts must be rechecked. Conditional safety and itinerary guidance lives in references/ so ordinary destination searches stay lightweight.
Point an Agent Skills-compatible client at this repository, or clone it into that client's skills directory. The Skill uses the bundled read-only Python engine and does not require an API key for the included data.
Start the visual travel finder:
python3 -m china_travel_kit serve
Then open http://127.0.0.1:8765/ to search attractions and generate itinerary cards in a responsive Chinese interface.
Validate the data and run tests:
python3 -m china_travel_kit validate
python3 -m unittest discover -s tests -v
MCP server
The server uses MCP over stdio and exposes eight read-only tools:
Similar plugs
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…
Open-source web crawler and scraper for LLMs and AI agents: any website into clean, LLM-ready Markdown. Run it yourself, or use Crawl4AI Cloud with one key.
The fastest path to AI-powered full stack observability, even for lean teams.
⭐AI-driven public opinion & trend monitor with multi-platform aggregation, RSS, and smart alerts. 告别信息过载，你的 AI 舆情监控助手与热点筛选工具！聚合多平台热点 + RSS 订阅，支持关键词精准筛选。AI 智能筛选新闻 + AI 翻译 + AI…