This product was not featured by Product Hunt yet. It will not be visible on their landing page and won't be ranked (cannot win product of the day regardless of upvotes).
Product upvotes vs the next 3
Waiting for data. Loading
Product comments vs the next 3
Waiting for data. Loading
Product upvote speed vs the next 3
Waiting for data. Loading
Product upvotes and comments
Waiting for data. Loading
Product vs the next 3
Loading
Splat — graph chat
Chat an infinite canvas instead of in a scrolling transcript
Chat with an LLM on an infinite canvas instead of in a scrolling transcript. Every prompt/response pair is a card, and cards link into a directed graph. When you write a new prompt you pick exactly which ancestor cards get sent as context. A linear thread makes you choose between polluting your context with a tangent and losing the tangent entirely; on a graph you just branch, and pull context from whichever branches turned out to be relevant.
Hey gang! 👋
I built Splat because I got frustrated with the linear nature of LLM chat.
When I'm researching something, I want to explore multiple threads in parallel without polluting my context with unrelated prompts. Traditional chat forces you to either keep every tangent in context or lose it entirely.
This is a very rough v0 that I originally hacked together for friends. It's definitely rough around the edges, but I wanted to put it in front of people early and find out whether this interaction model actually resonates.
Open to any and all feedback and feel free to contribute.
About Splat — graph chat on Product Hunt
“Chat an infinite canvas instead of in a scrolling transcript”
Splat — graph chat was submitted on Product Hunt and earned 0 upvotes and 1 comments, placing #105 on the daily leaderboard. Chat with an LLM on an infinite canvas instead of in a scrolling transcript. Every prompt/response pair is a card, and cards link into a directed graph. When you write a new prompt you pick exactly which ancestor cards get sent as context. A linear thread makes you choose between polluting your context with a tangent and losing the tangent entirely; on a graph you just branch, and pull context from whichever branches turned out to be relevant.
On the analytics side, Splat — graph chat competes within Productivity and GitHub — topics that collectively have 699.5k followers on Product Hunt. The dashboard above tracks how Splat — graph chat performed against the three products that launched closest to it on the same day.
Who hunted Splat — graph chat?
Splat — graph chat was hunted by Alex Korman. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
For a complete overview of Splat — graph chat including community comment highlights and product details, visit the product overview.
Alex Korman