snyvi is a free, open-source desktop app for people building several passion projects at once with coding agents. Each project gets a desk: its folder, up to four agents side by side (Claude Code, Codex, Gemini, any shell), and its own notes. Every plan or review an agent writes lands on that desk as a clean page, versioned. Home shows where each project was left. Local only, no account, MIT. Mac tester needed: the Mac build is signed and notarized, but we don't own a Mac. Try it and tell us.
Hi Product Hunt 👋 I'm Sunny. I have more passion projects than hours, and once coding agents made it possible to build them all at once, the work started scattering: plans in scrollback, to-dos in my head, every project pulling me away from the last.
snyvi is what I built for that. One desk per project, the agents side by side, and everything they write kept as a page you can read, version and search. It's one small app on your machine: no account, nothing leaves it, MIT.
One honest ask: we need a Mac tester. The Mac build is signed and notarized by CI, but neither of us owns a Mac. If you do, brew install --cask snymrova/snyvi/snyvi and tell me what the first minute was like. I'll fix what you hit today.
And for everyone: how do you keep several agent-built projects straight today? That answer shapes what I build next.
Does the agent automatically retrieve the latest approved plan when I start a new agent session, or should I tell it which page to go to?
Congrats on the launch! Quick question: does snyvi only work with agents that run in a terminal? I do most of my work in the Claude and ChatGPT desktop apps. Is there a way to get plans from those onto a desk, or is that something you’re thinking about?
About snyvi on Product Hunt
“All your passion projects, in one calm place”
snyvi launched on Product Hunt on October 20th, 2026 and earned 83 upvotes and 3 comments, placing #19 on the daily leaderboard. snyvi is a free, open-source desktop app for people building several passion projects at once with coding agents. Each project gets a desk: its folder, up to four agents side by side (Claude Code, Codex, Gemini, any shell), and its own notes. Every plan or review an agent writes lands on that desk as a clean page, versioned. Home shows where each project was left. Local only, no account, MIT. Mac tester needed: the Mac build is signed and notarized, but we don't own a Mac. Try it and tell us.
snyvi was featured in Productivity (663.5k followers), Open Source (69k followers) and GitHub (41.4k followers) on Product Hunt. Together, these topics include over 219.5k products, making this a competitive space to launch in.
Who hunted snyvi?
snyvi was hunted by Sunny Luthra. 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.
Want to see how snyvi stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Hi Product Hunt 👋 I'm Sunny. I have more passion projects than hours, and once coding agents made it possible to build them all at once, the work started scattering: plans in scrollback, to-dos in my head, every project pulling me away from the last.
snyvi is what I built for that. One desk per project, the agents side by side, and everything they write kept as a page you can read, version and search. It's one small app on your machine: no account, nothing leaves it, MIT.
One honest ask: we need a Mac tester. The Mac build is signed and notarized by CI, but neither of us owns a Mac. If you do, brew install --cask snymrova/snyvi/snyvi and tell me what the first minute was like. I'll fix what you hit today.
And for everyone: how do you keep several agent-built projects straight today? That answer shapes what I build next.