Skip to content

v2.2.0

Choose a tag to compare

View all tags
@github-actions github-actions released this 31 May 18:21
· 8 commits to master since this release
v2.2.0
32912f0

🚀 eVera v2.2.0

What's Changed

  • feat(v2.2.0): full self-contained install + LM Studio/Jan/llama.cpp support

✨ Highlights

  • 🎭 3D Holographic Avatar with Three.js WebGL
  • 🤖 8 gesture animations auto-triggered by expression
  • 🛡️ Production hardened with WebGL fallback, CSP, FPS monitoring
  • 🔒 Content Security Policy, SRI CDN loading, local fallback

📥 Download & Install

Platform Download Install
Windows Vera-Setup-*.exe Run the installer
macOS Vera-*.dmg Open DMG → drag to Applications
Linux Vera-*.AppImage chmod +x Vera-*.AppImage && ./Vera-*.AppImage
Android Vera-*.apk Enable unknown sources → install APK
Android Auto Vera-Auto-*.apk Install on phone → connect to car
Wear OS Vera-Wear-*.apk Install on watch via Play Store or sideload

🚀 One-Command Install (Linux / macOS)

curl -fsSL https://raw.githubusercontent.com/embeddedos-org/eVera/main/install.sh | bash

🪟 Windows One-Command Install

irm https://raw.githubusercontent.com/embeddedos-org/eVera/main/setup.ps1 | iex

🐍 From Source (manual)

git clone https://github.com/embeddedos-org/eVera.git && cd eVera
bash setup.sh          # installs Python, Ollama, Playwright, all deps
source .venv/bin/activate
python main.py --mode server
# Open http://localhost:8000

🤖 Offline LLMs (no internet needed)

ollama pull qwen3:8b          # 5 GB — recommended
ollama pull llama3.2:3b       # 2 GB — fast
ollama pull deepseek-r1:7b    # 5 GB — best reasoning

Or use LM Studio, Jan AI, or llama.cpp — eVera auto-detects all of them.

Full Changelog: v2.1.0...v2.2.0

Assets 2
Loading