Live data from Hacker News

Rate my startup: KeyTweet, a Twitter client that learns what you like

keytweet.com

1–10 of 31 posts

Rate my startup: KeyTweet, a Twitter client that learns what you like

#1
We developed KeyTweet to deal with the overwhelming number of tweets in the average user’s feed What KeyTweet does: We find keywords distinct to who you follow then sort your timeline based on those keywords. We drop tweets over 24 hours old and ones without links. You're left with what we think you'll like best.

My business partner and I have been following hackernews since we’ve started on this project. We’ve both seen some great advice given to new startups here. Please feel free to say anything that comes to your mind, small or large. Thank you for your help.

Rate my startup: KeyTweet, a Twitter client that learns what you like
keytweet.com

Re: Rate my startup: KeyTweet, a Twitter client that learns what you like

#9
post #8

Definitely agree with rjurney that you need to eventually update the homepage, but sweet idea for an app. I've signed up, but I'm still waiting to see how it actually works out my tweetstream

try hitting this url again http://keytweet.com/search/ twitter name here>

Re: Rate my startup: KeyTweet, a Twitter client that learns what you like

#10
This actually seems like a usable concept. Too often similar software tries to magically predict stuff in a not-so-transparent way.

Your decision to focus on links is, I believe, right on. Because you're not trying to replace my twitter stream with your useless predictions, but you're trying to help me notice the most important links, I think this could work.

However, you're doing something wrong with your encoding. You seem to strip out the Icelandic characters from the stream. (A very common pitfall amongst english-speaking developers.)

ps. You need a designer.

Post reply on HN