I’d like to share www.kuky.com, a peer support network that connects people through short, self-recorded videos and matches them using sentiment analysis powered by large language models (LLMs).

We’re building Kuky to help users find others who genuinely understand their emotional journey—not through swiping or likes, but through shared human stories. In this short Loom demo (link above), I walk through how:

Users create a profile by uploading 3 videos: an intro, their mental health journey, and their likes/dislikes

LLMs analyze each video for emotional tone, key themes, and psychological markers

Based on this, Kuky intelligently connects users with similar experiences and emotional alignment

We're passionate about creating a safe, empathetic space for authentic conversation—especially for people dealing with mental health challenges.

For more background, here’s a feature on Kuky in Women Love Tech: https://womenlovetech.com/kuky-the-mental-health-app-were-sw...

Would love your thoughts on the concept, the matching algorithm, and how you’d imagine using something like this.

Thanks, Armin

Comments URL: https://news.ycombinator.com/item?id=44112338

Points: 12

# Comments: 7

Whether it’s two people experiencing their first trimester or someone looking for a supportive mental health network, Kuky leverages technology to foster meaningful connections.

We’re excited about the potential of Kuky to help people find the support they need, and we’d love to hear your feedback:

What do you think about the demo? How can we improve Kuky to better meet user needs? Are there other applications or ideas you’d explore with this tech? Which community do you think needs this product most?

Comments URL: https://news.ycombinator.com/item?id=42269297

Points: 3

# Comments: 0

Microsoft recently announced they have generated 2Billion in ARR from Github Copilot. As part of corporate social responsibility, do you think Microsoft should give back to the open source community given that Copilot is technically trained by OSS maintainers??

We’re building PXL (https://pxlapp.com/), a psql client with support for copilot like features (inline code complete, query optimisation & sql assistant).

Here's the Github repo if anyone is interested https://github.com/pxlapp/postgres/tree/pxl

PXL helps in the following manner: 1- It has context of your DB schema so it can produce inline completion suggestions 2- The sql assistant can improve developer workflows so you don't need to keep going back to ChatGPT 3- It's can be integrated into other clients (check our Github for beekeeper-studio demo)

We’re still pretty early in development and we really want to improve the sql developer experience. Any feedback would be greatly appreciated!

Comments URL: https://news.ycombinator.com/item?id=41076143

Points: 2

# Comments: 2