Adity Kushawaha

Adity Kushawaha

Founder of MemoryOS

About

Building MemoryOS and exploring how AI systems can keep reliable context as they learn, change, and work across multiple agents. Interested in AI infrastructure, agents, developer tools, and startups. Currently getting MemoryOS ready for launch and always happy to connect with other builders.

Badges

Gone streaking
Gone streaking

Forums

LinkedIn or X ?

Hello Product Hunt!

I've been testing distribution across LinkedIn and X for a few launches now, mostly just to see what's the best channel.

Do AI Products Need Better Control over the Memory

I've been building MemoryOS,and i had an question: are we actually solving an AI memory problem ,or just building another place to store conversations?

many developers I speak with already use vector databases,Conversation history,Claude skills,files or other tools. They don't necessary feel that memory storage is broken.

The problem I keep seeing appears later.

A user changes their preference. Two agents receive conflicting information. An older fact continues influencing answers. A team needs to know where a memory came from, why it is currently trusted, or whether an agent is still allowed to use it.

Hey Product Hunt - I’m Adity, building MemoryOS

I m building MemoryOS around a problem that became obvious once I went deeper into AI memory:

Remembering is becoming easy. Governing what gets remembered is not.

Once an AI application has multiple agents, models, sessions, and data sources, memory starts behaving like shared state.

Then harder questions appear:

View more