edisonwong520

edisonwong520 / wanny

Public

A real Jarvis, connecting your appliances, AI controls everything in realworld. Wanny = nanny in Wechat

edisonwong520.github.iowanny
46
2
69% credibility
Found Apr 03, 2026 at 46 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

Wanny is an open-source AI butler that lets you control smart home devices and vehicles like Mercedes via natural WeChat conversations, with memory for habits and proactive automations.

How It Works

1
🔍 Discover Wanny

You find Wanny on GitHub, an AI butler that chats via WeChat to control your smart home and car.

2
📧 Create your account

Sign up quickly with your email to get your personal AI helper ready.

3
💬 Connect WeChat

Link your WeChat so you can talk naturally to your butler anytime.

4
Add your devices
🏡
Smart home

Link lights, AC, fridge from Mijia or Midea.

🚗
Your car

Connect Mercedes for location and status checks.

5
🗣️ Chat and control

Tell your butler 'turn off bedroom lights' or 'check car fuel' right in WeChat.

6
🧠 Butler learns you

It remembers your favorite temperature or bedtime routine over time.

✨ Proactive home magic

Your butler turns on dinner before you arrive home, perfectly timed.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 46 to 46 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 wanny?

Wanny turns your WeChat into a real Jarvis AI, letting you control smart appliances from Mijia, Midea, Mercedes-Benz cars, and Home Assistant hubs using natural language commands. It handles device states in real time, learns your habits for proactive automations like preheating floors on your commute home, and stores long-term memory for context-aware responses. Built in Python with Django backend, Vue frontend, and Gemini AI, it offers a web console for monitoring real-world status alongside chat interactions.

Why is it gaining traction?

Unlike basic IoT bridges, Wanny acts like a real Jarvis program with manual approval gates for safety, escalating trusted actions to full autonomy—perfect for real-world reliability without constant babysitting. WeChat integration hooks Chinese developers tired of fragmented apps, while proactive care based on car location, weather, and routines delivers that "wow" real-time collaboration feel. Early adopters praise its vector memory for personalized suggestions, standing out in the GitHub real-world AI space.

Who should use this?

Home automation tinkerers with Mijia/Midea gear or Mercedes vehicles who want voice-like WeChat control without building from scratch. AI hobbyists experimenting with agentic flows for physical devices, or WeChat-heavy users seeking a real Jarvis app to manage daily rhythms like fuel checks or lighting scenes.

Verdict

Grab it for personal setups if you're okay deploying your own Django/Vue stack—46 stars and 0.7% credibility score signal early-stage experimentation with solid docs but unproven stability. Risks like unofficial APIs make it non-production ready, yet ideal for real-world prototyping.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.