Release 6.2

What's Changed:

• Create requirements-macos.txt by @yukiarimo in #51
• Modified: requirements.txt by @0xGingi in #50
• Add Metal support fully by @0xGingi in #52
• set to use CPU by default + add ctransformers to req by @0xGingi in #54
• Remove hardcoded names by @0xGingi in #55
• merge main into dev by @yukiarimo in #56
• Fix the wrong file name (it wasn't matching with huggingface) by @robonxt-ai in #58
• Config update by @yukiarimo in #59
• Final steps for a new library. v6.1.1 by @yukiarimo in #60
• llama-cpp-python GPU installation fixed + Added Donate by @0xGingi in #62
• v6.1.2 by @yukiarimo in #63
• v6.1.3 - Optimization performance by @yukiarimo in #67
• v6.2 by @yukiarimo in #71

New Features:

• First Kanojo implementation
• Prompt Templates are part of the Kanojo Connect
• Double speed due to the enhanced server stability
• Rewritten UI chat logic from scratch
• Fixed Bootstrap bugs
• Removed unnecessary dependencies
• Optimized images
• Complete PWA support for all platforms
• Auth system 2.0
• Offline mode (beta 1.0)
• Project directory refactor
• Vital configuration tweaks
• Easy installation via updated CLI and TUI
• Updated documentation

Not working:

• Both Himitsu and Himitsu Copilot
• Prompts without history
• Google Search
• Audio and Video calls
• Offline PWA load if using a server-side approach
• Bootstrap bug with toggles
• Light mode

New Contributors

• @robonxt-ai made their first contribution at #58

Full Changelog: v6.1...v6.2

Release 6.1.3

Enhenced:

• New Settings Popup
• Updated Profile Page
• Faster Load by Minifying Scripts
• Improved HTML structure

What's Changed

• v6.1.3 - Optimization performance by @yukiarimo in #67

Full Changelog: v6.1.2...v6.1.3

Release 6.1.2

Improved:

• Auth system finally works well
• Improved security system -> impossible to bypass
• Users have separate folders
• Final library switch to llama-cpp-python
• Cleared unnecessary dependencies
• Stability improvements and bug fixes

Not working:

• User-generated and uploaded images still in the shared folder
• Some minor features can not work

What's Also Changed:

• llama-cpp-python GPU installation fixed + Added Donate by @0xGingi in #62
• v6.1.2 by @yukiarimo in #63

Full Changelog: v6.1.1...v6.1.2

Release 6.1.1

Enhancements:

The fnal steps for a new library

• Moved to another library implementation.
  ctransformers -> llama-cpp-python
• Improved stability in generation
• Final steps towards Auth System
• Removed unnecessary dependencies
• Prompt templates are disabled temporary
• Tweaked config.json for consumer hardware

What's Changed

• Create requirements-macos.txt by @yukiarimo in #51
• Modified: requirements.txt by @0xGingi in #50
• Add Metal support fully by @0xGingi in #52
• set to use CPU by default + add ctransformers to req by @0xGingi in #54
• Remove hardcoded names by @0xGingi in #55
• merge main into dev by @yukiarimo in #56
• Fix the wrong file name (it wasn't matching with huggingface) by @robonxt-ai in #58
• Config update by @yukiarimo in #59
• Final steps for a new library. v6.1.1 by @yukiarimo in #60

New Contributors

• @robonxt-ai made their first contribution in #58

Full Changelog: v6.1...v6.1.1

Release 6.1

• Implemented Himitsu Copilot v0.1
• Stable Prompt templates
• Final Bootstrap Rewrite
• No bugs
• Improved requirements.txt
• Added setup shell script
• Yuna AI moved to server-based implementation
• Dark Mode is default now
• New Call UI
• Added templates for Yuna and AGI models folder
• New History Manager
• Added collections v0.1

Release v6.0.3 ~beta

• Himitsu copilot implementation
• Bootstrap web UI improvements
• requirements.txt update
• Module not found error fix
• General optimization

Release v6.0.2

• Stable UI
• Mobile adaptation
• Better prompt handling
• New Desktop app v1.0
• Intro page added
• Yuna AI moved to the yuna.html file
• General improvements and bug fixes

Beta v.6.0.1

• Empty message error fixed

Release v6.0

Updates:

• Fully rewritten UI
• Added auto-scaling
• Mobile Optimization
• Scaling optimization
• Full dark mode support
• New sending message logic
• Implemented prompt templates
• Himitsu implemented in the as prompt template manager (for now)
• Workaround single-page application
• Full PWA support
• The sidebar was returned
• Sidebar mobile optimization
• Select elements now are shown as a scrollable lists
• Message history elements are now showing correctly in full-screen
• Server loading delay was decreased

New

• Parameters on client configuration
• Server side in file configuration
• Image generation
• Image recognition
• Follow-up copilot for prompt templates
• Icons instead of text buttons
• Yuna logo
• Call UI
• Loading animation
• Auto fix option for server deploy
• Helpful automation configuration shell script

Fixed:

• Sounds error
• Wrong windows of popup elements
• Full-page freeze

Not working:

• Speech recognition
• Speech synthesis

Not implemented

• Web search
• Long-term memory embeddings

Full Changelog: v5.2...v6.0

Release v5.2

Full Changelog: v5.1...v5.2

What's new:

• New mobile-optimized UI
• Rewritten UI for single-page application
• Implemented Yuna's vision, one more step towards AGI
• Image captioning and image generation were moved to the separate vision module
• Project file structure logic was refactored
• Better generation with native Python libraries
• First stable workaround for custom configs
• All C++ dependencies were removed
• New sounds
• Improved server request logic
• Implemented full video call support
• Images now integrated into message bubbles
• Easier installation
• Memory efficient generation

Still not working:

• TTS response with audio
• PWA is not working offline but working in general
• Speech recognition causes error: "can't recognize the text."
• Speech recognition not working on mobile
• Config not loading from external URLs