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
Lycana
Turn ideas into architecture diagrams for teams and agents
Describe your system by voice. Lycana turns it into a typed architecture diagram, capturing your reasoning as you explain it. Teammates and AI agents can look up what each part does and why it's there, then build on the plan with your intent in mind.
I'm Jensen Huang (prev ByteDance, Razer) and I'm building Lycana with Justin, my cofounder (prev UC Berkeley (Morphing Matter Lab), dConstruct robotics, Fabrica AI).
Coding agents write code well, but they guess at how your system fits together. You describe the architecture in a prompt, the agent fills the gaps, and three files later you find out it treated the queue as a database.
Lycana draws the diagram while you describe your system out loud.
What makes it different
- Voice-first approach You don't type a prompt or learn a syntax. Say "the API writes to Postgres and pushes jobs onto a queue" and the nodes appear while you're still speaking. - Every part has a type. Each node records what it is, such as a service, database, cache or queue, and each link records what flows across it. When you say "the queue", Lycana changes the queue node. - Edit by voice or by hand. Drag a node, rename a link, or say "put the cache in front of the API". Both change the same diagram. - It asks when a command is unclear. If Lycana can't tell which node you mean, it asks you which one. - Export it. Download the diagram as PNG, JPG, PDF or Mermaid. - MCP support is coming soon. Your coding agent will be able to query your diagrams directly and read each component, its type and what it connects to.
Lycana is free to try with no signup. 👉Open lycana.ai and start talking. For Product Hunt we're also opening a founding price. Lycana Pro costs US$5 a month for as long as you stay subscribed, down from US$20. Claim it at https://lycana.ai/founding/phlau...
We'd like to know one thing. Was Lycana faster than your usual sketch or your usual architecture prompt? We're replying here all day, and you can also email humans@lycana.ai.
About Lycana on Product Hunt
“Turn ideas into architecture diagrams for teams and agents”
Lycana was submitted on Product Hunt and earned 3 upvotes and 1 comments, placing #107 on the daily leaderboard. Describe your system by voice. Lycana turns it into a typed architecture diagram, capturing your reasoning as you explain it. Teammates and AI agents can look up what each part does and why it's there, then build on the plan with your intent in mind.
On the analytics side, Lycana competes within Design Tools, Developer Tools and Artificial Intelligence — topics that collectively have 1.3M followers on Product Hunt. The dashboard above tracks how Lycana performed against the three products that launched closest to it on the same day.
Who hunted Lycana?
Lycana was hunted by Jensen Huang. 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 Lycana including community comment highlights and product details, visit the product overview.
Jensen Huang
Hey Product Hunt👋
I'm Jensen Huang (prev ByteDance, Razer) and I'm building Lycana with Justin, my cofounder (prev UC Berkeley (Morphing Matter Lab), dConstruct robotics, Fabrica AI).
Coding agents write code well, but they guess at how your system fits together. You describe the architecture in a prompt, the agent fills the gaps, and three files later you find out it treated the queue as a database.
Lycana draws the diagram while you describe your system out loud.
What makes it different
- Voice-first approach You don't type a prompt or learn a syntax. Say "the API writes to Postgres and pushes jobs onto a queue" and the nodes appear while you're still speaking.
- Every part has a type. Each node records what it is, such as a service, database, cache or queue, and each link records what flows across it. When you say "the queue", Lycana changes the queue node.
- Edit by voice or by hand. Drag a node, rename a link, or say "put the cache in front of the API". Both change the same diagram.
- It asks when a command is unclear. If Lycana can't tell which node you mean, it asks you which one.
- Export it. Download the diagram as PNG, JPG, PDF or Mermaid.
- MCP support is coming soon. Your coding agent will be able to query your diagrams directly and read each component, its type and what it connects to.
Lycana is free to try with no signup.
👉Open lycana.ai and start talking.
For Product Hunt we're also opening a founding price. Lycana Pro costs US$5 a month for as long as you stay subscribed, down from US$20. Claim it at https://lycana.ai/founding/phlau...
We'd like to know one thing. Was Lycana faster than your usual sketch or your usual architecture prompt? We're replying here all day, and you can also email humans@lycana.ai.