ZhuofanWu

ZhuofanWu / TaxiAgent

Public

一个面向网约车场景的多 Agent + Spring Boot & Spring AI 项目，从底层搓一个ReAct框架

18
2
100% credibility
Found Apr 03, 2026 at 17 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Java
AI Summary

TaxiAgent is an AI-powered demo for ride-hailing customer service, featuring specialized agents for booking trips, daily queries like weather and locations, and support tasks with integrated real-world data sources.

How It Works

1
🔍 Discover TaxiAgent

You hear about this smart helper for taxi rides and customer service on GitHub.

2
📥 Get the project

Download the ready-to-use files to your computer.

3
🔗 Link everyday services

Connect map info for locations and weather updates so it knows real-world details.

4
▶️ Launch with one click

Start your personal taxi assistant right on your machine.

5
Start chatting
🚕
Book a ride

Tell it where to go and confirm details for a smooth trip.

☀️
Daily info

Ask about weather, nearby spots, or travel times.

❓
Get support

Check past rides, cancel, or create help requests.

6
🧠 Watch it think and act

Your assistant uses smart tools to find answers and handle requests step by step.

🎉 Perfect taxi companion

Enjoy booking rides, getting info, and support all in natural conversation.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 17 to 18 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is TaxiAgent?

TaxiAgent is a Java-based Spring Boot app using Spring AI to power a multi-agent chatbot for ride-hailing scenarios, like booking taxis or checking weather en route. It routes user queries to specialized agents for orders, daily info (POI search, estimates), support tickets, or fallbacks, with built-in safeguards like human-in-the-loop order confirmations before finalizing. Developers get a ready-to-run chat API at endpoints like /chat/v2/c/{chatId} for starting sessions and /chat/v2/r/{chatId} for resuming, complete with multi-layer memory across heap, Redis, and MySQL.

Why is it gaining traction?

Unlike basic prompt demos, it engineers a full ReAct loop with intent routing, tool calls to maps/weather APIs, RAG for knowledge, and event streams for visible agent actions—making agents feel production-stable. The multi-agent Spring AI setup shines for agent spring boot skills, blending agent github copilot-style tools with spring agent framework patterns, while pointerized tool results keep contexts lean. It's a practical agent github repo for seeing how agent spring ai handles real flows without hallucinated bookings.

Who should use this?

Java backend devs prototyping vertical agent apps, like e-commerce order agents or customer support bots in Spring ecosystems. Teams evaluating multi agent spring ai for taxi agent-like services, needing HITL for high-stakes actions. Spring Boot shops wanting agent github action inspiration beyond copilot vscode/intellij plugins.

Verdict

Grab it as a reference for agent spring boot—solid docs and quick-start make it easy to fork, despite 12 stars and 1.0% credibility signaling early maturity. Worth a weekend spin if you're building spring agent jar prototypes, but expect tweaks for prod.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.