FloatTrip — security grade SAFE, quality 57/100

Security audit verdict: SAFE · quality 57/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by shouzhuoshouzhuo · Agent Tool · ★ 76

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is FloatTrip safe to install? View the security audit →

About FloatTrip

✈️ AI 旅游规划助手 一句话描述需求,自动生成带时刻表的多日旅游计划 📖 简介 AI 旅游规划助手是一个基于 LangGraph 多 Agent 流水线 的旅游行程生成工具。只需输入一句话的出行需求(目的地、日期、偏好),系统即可自动完成: 🔍 意图识别(快速失败) — 从自然语言抽取目的地、日期、偏好;支持"明天开始3日游"等相对时间 + 天数表达式;缺目的地/日期时立即返回,不触发后续 LLM 调用 🌤️ 天气感知 — 自动拉取出行日期天气预报,雨雪天优先安排室内景点,超出预报范围时降级提示 🗺️ 景点搜索 — 调用高德地图 API 获取真实景点候选池,按评分过滤 🧭 智能规划 — Planner/Reviewer 多轮循环优化,共享对话记忆确保紧急问题优先修复 🍜 餐饮推荐 — 基于每天动线搜索周边餐厅,按天并行调用 LLM 推荐午晚餐 🗺️ 地图可视化 — 前端接入高德 JS API,在半屏地图上逐天绘制行程动线与景点标注 ✍️ 手动编辑 — 对生成的行程可拖拽换序、搜索换点/换餐厅、改时段,带撤销/重做栈;保存时服务端重算逐段距离 🔌 多 LLM 提供商 — 通过 一键切换 DeepSeek / 豆包,统一工厂函数封装,缺 Key 时给出明确报错 所有景点与餐厅数据均来自高德真实 POI,不会凭空捏造地点。 🧪 这个项目有Agent评测体系:基于 Anthropic《Demystifying Evals for AI Agents》方法论,对核心 Agent(Planner / Reviewer)建立了可复现的定量评估框架,包括代码打分器 G1–G7 + LLM 评委 + Reviewer 可靠性指标,指标覆盖 pass@k、pass^k、收敛轮次、误放行率、planner 反驳率。详见 。 🎬 演示 新建规划页 <p al

ai-travel-planneramapitinerary-plannerlangchainlanggraphllm-agentpoiroute-optimizationtravel-agent

Quick Facts

Stars76
Forks15
LanguagePython
CategoryAgent Tool
Quality Score57.4445378066453/100
Last Updated2026-09-19
Created2026-05-21
Platformspython
Est. Tokens~16k

Compatible Skills

These tools work well together with FloatTrip for enhanced workflows:

  • Fast-LLM-Agent-MCP — semantic(0.20)+complementary+same_lang+similar_pop+shared_platform (52%)

FloatTrip alternative? Top 6 similar tools

Looking for a FloatTrip alternative? If you're comparing FloatTrip with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • Upwork-AI-jobs-applier by kaymen99 · ⭐ 156

    AI tool for automating Upwork job applications using AI agents to find and qualify jobs, write personalized co

  • palico-ai by palico-ai · ⭐ 343

    Build, Improve Performance, and Productionize your LLM Application with an Integrated Framework

  • ai-playground by rokbenko · ⭐ 320

    Code from tutorials presented on the "Code AI with Rok" YouTube channel

  • oreilly-ai-agents by sinanuozdemir · ⭐ 299

    An introduction to the world of AI Agents

  • gpt-all-star by kyaukyuai · ⭐ 238

    🤖 AI-powered code generation tool for scratch development of web applications with a team collaboration of au

  • langchain_data_agent by eosho · ⭐ 234

    NL2SQL - Ask questions in plain English, get SQL queries and results. Powered by LangGraph.

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Python Agent Tools

Frequently Asked Questions

What is FloatTrip?

FloatTrip is A travel planning Agent powered by LangGraph, Amap POI, route clustering and LLM-based itinerary generation.. It is categorized as a Agent Tool with 76 GitHub stars.

What programming language is FloatTrip written in?

FloatTrip is primarily written in Python. It covers topics such as ai-travel-planner, amap, itinerary-planner.

How do I install or use FloatTrip?

You can find installation instructions and usage details in the FloatTrip GitHub repository at github.com/shouzhuoshouzhuo/FloatTrip. The project has 76 stars and 15 forks, indicating an active community.

What are the best alternatives to FloatTrip?

The top alternatives to FloatTrip on Agent Skills Hub include Upwork-AI-jobs-applier, palico-ai, ai-playground. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Agent Tool tools