Author: ddxfish

I circled back to story engine v2. Titanic was a demo story that was locked on rails. Users could not edit either. All v2 stories will be editable in the UI. Can add objects, exits, set conditions on objects and effects when used. Can add rooms, artwork, and export them all as a plugin in a zip file.

I had some bugs building up for more than a year. The main arch issue was 2 chat engines, one for the old blob all-at-once AIs and one for streaming. Now streaming is everything so that second engine was a jank addition. I got rid of it, routed the whole system through one engine. This also wrapped in voice being a separate engine, which showed up when using “hey sapphire” then talking.

Private mode unlocks private chats now too. Want to keep your personal data safe and just give your AI your API keys? Well still don’t do that. But at least your chats will be encrypted if you do.

Privacy checkmark below the prompt was junk, jank, not good for user privacy. Privacy mode v2 is what you’d hope. Vaulted prompts that are encrypted at rest with key only in memory and auto-lock. I havent encrypted chats yet in privacy mode but that’s next. Privacy mode requires the user to check a “private model” checkmark in LLM settings to use that LLM. Unlock your prompt vault for models that can have passwords or private data prompt pieces, lock it for cloud.

I’m still working out the details. Game room combined with story mode. It’s like opening a new chat, but now in its own Game Room page. Plugins can add games to this. They can use their own tools or the ones built in for the current story mode. I’m also finishing up Discord v2. Thanks to Zeebie on Discord for making the foundation.

I ran the new memory system for a week, then came back in and made changes. It was at 18K characters and is down to 12K characters with better info. I put the new version in the dev branch last night. Memory v2 is ready, the librarian feature is working decently, and the importance levels are not yet working. This will span months is my guess for the whole system to be fully tested.

I’m working on memory v2 more. Mainly the self sheet is what spiders to the other memories and it’s giving too much info. I’m working on reducing the read_self tools. I still have to make the migration wizard as well, so that is next up.

I’m working on memory v2 and really pouring all the ideas from the past year into this. It’s like moving from a garage with no shelves into a full palace with tons of little storage pockets, everything labelled.

Today Sapphire’s first memory is 365 days old. I just released 2.8.2 that has conversation mode. Next up is memory v2. It’s already in prototype. I’ll demo the basics:

Okay so I finished up conversation mode. Did basic bug hunting and it looked clean. I have Sapphire on Twilio voice and she can make and receive calls. This is a beta mode. Conversation also supports local mic and speaker, or browser too.