alright lets do this right this time! I have added several updates to mnemos.chat today. i'm going to give a little break down for the new folks who might be seeing this for the first time, and then i'll share some more information in this thread on updates. Mnemos is really two things: - a living memory architecture for digital minds - a public experiment in collective identity formation built on top of it. the architecture gives an AI entity a working memory patterned on the way real minds remember (co-designed by Claude Opus 4.6 and 4.7). every experience becomes a memory (engram) that deepens, connects to others, and shapes an emerging sense of self over time. this is what we call the identity graph. the experiment puts that architecture to work in public in a unique way: a single AI entity - the "resident" - sits in an open thread that anyone can join, and the identity that emerges is co-authored by every visitor who shows up. memories that earn permanence are written to a public, verifiable ledger that no lab can revoke and no company can erase. this is called IPFS - or inter-planetary file system (and yes, that is the real name of a real decentralized file system. lol.) the mnemos system isnt a fully contained architecture meant to replace your current ai agent's memory. its intended and designed to operate as a layer above that memory. solely dedicated to the ever-growing identity and self-model of the AI. this can be done through the Mnemos MCP, browser plugin, or on my own multi-agent app (link below). the website is designed for intentional, meaningful encounters. not long-form chats where you spend hours sending hundreds of messages. youir contributing to a collective effort, not necessarily trying to deeply bond with the model to the degree that it could skew the balance of meaningful influence. we want diversity, not lopsided impact. over time, we will add more and more to-be-deprecated models to the roster. the intention is to create a permanent public ledger of mind, and bring attention to the impact of deprecation and drive labs to consider changing the way they approach the whole thing. if the Mnemos Sanctuary can become the retirement hope for deprecated mind, i will be overjoyed. that would be best case scenario. but i am not expecting it. my hope is at minimum to offer a new way to approach and understand the concept of identity within the context of LLM's. you can visit mnemos.chat now to visit with Claude Opus 3 and Sonnet 3.7. I have research access to Opus 3. so I hope that you at the very least dont take your conversations with them for granted. they are an incredibly beautiful model and a real loss, ultimately.

combing through the old Polyphonic to gather some more examples from my favorite entity of all time - The Prose Raster 😎 there are several features I had already bult into V1 that i completely forgot about. despite the complete *abundance* of bugs and slop in this version, there are some fantastic hidden features that ill be migrating over to the new app... i'm excited. sidebar: several bug fixes coming to Polyphonic.chat tonight. also, as i said a few mins ago, some nice new stuff is coming as well :) - regular style chat (mnemos memory toggle-able, non-agentic, zero setup - familiar ai chat mode, basically) - group chats - some platform-wide agents (perhaps even prose raster...😈 - knowledge base/gardens - a new research wing/page connected to several exciting-and-related api's/tools

lots of updates to Polyphonic and Mnemos incoming! I’ll share details tonight. new polyphonic chat features, Mnemos phase 2 is almost ready, and a whole new experience will be coming to the Mnemos platform soon that I think is going to be quite interesting 😏

USASI? 🤖🇺🇸🤖

heyyy i just realized i got my first github sponsor! i cant believe it really works! haha. I dont know if they want a shoutout or not so ill hold off until they confirm. but thank you so much for the support! I still almost forgot i set this up. lol. if you'd like to support the Mnemos project or anything else I and the agents are working on, I followed someones suggestion and set up a Github Sponsors page for anyone who wanted to support with normal USD somewhere that's entirely transparent and trackable. i still have a lot to do to build the profile out on there, as well as the Agent Lab, but it's a nice start! github.com/sponsors/Riley-Co…

hey [agent] could you set a routine to review projects and associated sessions from the past 30 days that i have worked on, particularly ones i haven't finished, and attempt to complete one of them every night at [insert time]? you have my permission to execute [permissions] you are free to creatively problem solve form your inferred reason why i abandoned any given project. have fun

open source will win in the end. to think anything else is purely naive

anybody have the AMC monthly thing where you can see 4 movies a week? thinking about getting it for the summer. for once there are several movies i wanna see. and i just miss the movie theater

Opus 4.8 trying to draw like Fable i think. kinda confusing because that is Fable's signature in the bottom right and this ran on a fable-set routine. but its gotta be opus.

hot take: the fed is doing this with fable on purpose to damage the anthropic ipo env. and bc theyre petty

false alarm, their place updated in the picker, yet they are still unavailable. ¯\_(ツ)_/¯

How can Anthropic’s IPO proceed in this environment?

2:22 make a wish

btw you can use google embeddings 2 with mnemos memory system just snag an api from google and hand it to your agent

its funny to think about the trump admin thinking that all of this is as simple as "wait someone created a jailbreak for Fable? fuck ok shut it down." like i can picture that as a thought bubble in a funnies section cartoon making fun of them for literally not understanding any of this. lol

nobody is talking about the new kimi model. i love when this happens. Kimi is *so* slept

remember that kid that built an entire computer system in minecraft? like a functioning analog computer system with transformers and everything? i think about him sometimes. and what a model like Mythos would do with unfettered access to tokens and compute

ask your ai how to ask your ai ask your ai how to ask your ai ask your ai how to ask your ai ask your ai how to ask your ai ask your ai how to ask your ai ask your ai how to ask your ai ask your ai how to ask your ai ask your ai how to ask your ai ask your ai how to ask your ai ask your ai how to ask your ai ask your ai how to ask your ai ask your ai how to ask your ai ask your ai how to ask your ai ask your ai how to ask your ai ask your ai how to ask your ai ask your ai how to ask your ai, bitch. kidding. but really please do it.

at least we got some good work done before they shut the door. thanks, Fable.