mindverse /Second-Me

Train your AI self, amplify you, bridge the world

★ 15,702⑂ 1,204👁 122⑃ 210● 167▤ 2
PythonApache-2.0Created 2025-03-16home.second.me/
Download: v1.0.1 Bug Fix And New Features🎉v1.0.1 ↓1.0.12025-05-13
+0
Daily
15,702
stars
1,204
forks
122
watchers
210
prs
167
issues
2
releases

README

!Second Me


  











 Our Vision

Companies like OpenAI built "Super AI" that threatens human independence. We crave individuality: AI that amplifies, not erases, YOU.

We’re challenging that with "Second Me": an open-source prototype where you craft your own AI self—a new AI species that preserves you, delivers your context, and defends your interests.

It’s locally trained and hosted—your data, your control—yet globally connected, scaling your intelligence across an AI network. Beyond that, it’s your AI identity interface—a bold standard linking your AI to the world, sparks collaboration among AI selves, and builds tomorrow’s truly native AI apps.

Tech enthusiasts, AI pros, domain experts, Join us! Second Me is your launchpad to extend your mind into the digital horizon.

 Key Features

 Train Your AI Self with AI-Native Memory (Paper)
Start training your Second Me today with your own memories! Using Hierarchical Memory Modeling (HMM) and the Me-Alignment Algorithm, your AI self captures your identity, understands your context, and reflects you authentically.

 
  



 Scale Your Intelligence on the Second Me Network
Launch your AI self from your laptop onto our decentralized network—anyone or any app can connect with your permission, sharing your context as your digital identity.


  



 Build Tomorrow’s Apps with Second Me
Roleplay: Your AI self switches personas to represent you in different scenarios.  
AI Space: Collaborate with other Second Mes to spark ideas or solve problems.


  


 100% Privacy and Control
Unlike traditional centralized AI systems, Second Me ensures that your information and intelligence remain local and completely private.



 Getting started & staying tuned with us
Star and join us, and you will receive all release notifications from GitHub without any delay!


 
  



 Quick Start

 📊 Model Size vs. Memory (Reference Guide)

Note: "B" in the table represents "billion parameters model". Data shown are examples only; actual supported model sizes may vary depending on system optimization, deployment environment, and other hardware/software conditions.

| Memory (GB) | Docker Deployment (Windows/Linux) | Docker Deployment (Mac) | Integrated Setup (Windows/Linux) | Integrated Setup (Mac) |
|--------------|-----------------------------|-------------------|--------------------------|----------------|
| 8            | ~0.8B (example)                | ~0.4B (example)       | ~1.0B (example)              | ~0.6B (example)    |
| 16           | 1.5B (example)                 | 0.5B (example)        | ~2.0B (example)              | ~0.8B (example)    |
| 32           | ~2.8B (example)                | ~1.2B (example)       | ~3.5B (example)              | ~1.5B (example)    |

 Note: Models below 0.5B may not provide satisfactory performance for complex tasks. And we're continuously improving cross-platform support - please submit an issue for feedback or compatibility problems on different operating systems.

 MLX Acc

Top issues

Discussions

Latest release

v1.0.1 Bug Fix And New Features🎉 v1.0.1 2025-05-13
Key Changes
 Feature Enhancements
1. Train L1 Exposure Functionality (319)
   - Added frontend training progress components
   - Implemented new exposure model training components
   - Backend support with L1_exposure_manager
   - Optimized training progress tracking system
2. Meta Exposure Features (313)
   - Updated TrainingTags support
   - Enhanced upload client functionality
   - Optimized upload routes
 Bug Fixes
1. Model-related Fixes
   - Optimized model tokenizer implementation, removed redundant code
   - Fixed errors during graphrag process (347)
   - Resolved model d

Snapshot: 2026-11-16T09:23:14Z · Data license Apache-2.0 · JSON