I am grateful for Indian summer 🌞⛱️💦

ROFL 🤣

How the hell do you read comments in a post in @YakiHonne? #asknostr

Hello #noste devs. What's your favorite harness for your agents? What do you use and happy with? #asknostr

I forgot how much I used to love this Bulgarian band as a teenager - Gravity Co. - loved listening to them on road trips with my boyfriend. #nostalgic

#snl #dailyaffirmation 🤓

Reels I come across on friends' stories...

The alternate reality my psyche lives in...

...an IG post with the soundtrack of one of my favorite Bulgarian songs, “Двама,” from when I was somewhere around 6–8 years old, sent me deep into the #nostalgic #feels. A song from one of Bulgaria’s biggest film classics, The Goat Horn (#thegoatshorn). A sweet favorite memory: walking to school midday and crossing paths with my much older, then-teenage second cousin, with whom I share a name - her coming back from school with her boyfriend, him playing guitar, and the two of them singing this song.

GM 🌞 Curious what you think: What's one task AI can do better than humans and one task that humans can do better than AI? #asknostr

I’m kinda struggling with knowing how to proceed here and would love suggestions from experienced devs and heavy AI users, ideally people working with more private/sovereign setups. I want to build what I’m calling a Life OS / Personal Signal Observatory: a system that can draw from thousands of datasets, documents, and AI conversations from the last three years, identify patterns across them, and help me organize my projects, areas of life, decision processes, and day-to-day functioning. I already have the markdown/spec for a first iteration. It could eventually become an app, but initially I’m imagining a local or self-hosted setup with multiple agents that can retrieve context, execute tasks, keep track of ongoing projects, and help me run my day-to-day. The part I’m stuck on is where/how to build the underlying system. I considered Berd, but I don’t have an Apple Silicon machine. I’m also looking at Buzz, but I’m unsure where to start and have heard mixed reports about reliability. Ideally I’d like the canonical memory/data layer to belong to me, not OpenAI or Anthropic. I want to be able to export my existing histories, eventually delete most or all of the cloud-side chat history, and still use models from OpenAI, Anthropic, Google, etc. through my own harness while maintaining continuity locally. So I’m especially curious what people would recommend for: local/self-hosted memory + retrieval → agent orchestration → model APIs → tools/actions without becoming unnecessarily complicated or fragile. What stack would you build this on today? #asknostr

#collage #throwback GM 🌞 Hola... pieces of my life.... #introductions

Been seeing a lot of ivermectin posts/ads pop up in my feed. What's your guys take on using it and the protocol? Have you used it and in what circumstances? #asknostr

🤣

Demonic... I am getting angry... Fire🔥 in my veins boiling... 🤬 I must be dehydrated.

Честит празник, мила моя, София! 🧡

PINK 🩷 is NOT really my color... But I came across this video of me from 14 years ago yesterday 👀 when I used to hussle on the internet teaching entrepreneurs how to build a business online + use social media marketing (and platform like fb etc.) This may have been the one and only time I've worn pink... It's kinda cute, what do you think? I am 25 yo here I think. #throwback

🪿🐸🪽

Seeing this makes me feel happy and grateful. A tiny victory in the right direction.

Don't be an immature parent. GN 🌠