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
DeepDeck
Open-source AI apps you can use, modify, and share
DeepDeck is an MIT-licensed macOS desktop built on DeepSeek Harness. It turns Cordis plugins into apps with their own windows, settings, Workspaces, and Agent Sessions. Use Hacker News Reader or Video Sherlock, ask the agent to modify local source, rebuild and hot-reload the result, then contribute useful changes through Git and PRs. Bring your own Codex or DeepSeek connection. No included model credits. Not an official DeepSeek product.
Maker update: I published a new open-source DeepDeck App called Strudel Studio.
It is a visual song sequencer with multi-section arrangements, up to eight tracks, independent 16-step patterns, 31 instruments, full-song preview, and deterministic Strudel source generation.
The experiment is about more than AI-generated music. The visual App owns the authoritative project state, while the main Agent can propose bounded, structured edits through a registered action. Every result is validated, tied to the revision it started from, and applied as a reversible change. Stale Agent output is rejected instead of silently overwriting newer human work.
I’m testing whether some agent skills should come with an optional human-facing App—not replacing their agent-readable instructions, but giving people a better place to start, observe, steer, and verify the work.
Would you rather use an Agent inside creative software as a chat overlay, or through narrow actions that modify validated project state?
Disclosure: I build DeepDeck and Strudel Studio. DeepDeck is based on DeepSeek Harness and is not an official DeepSeek product.
About DeepDeck on Product Hunt
“Open-source AI apps you can use, modify, and share”
DeepDeck was submitted on Product Hunt and earned 3 upvotes and 1 comments, placing #57 on the daily leaderboard. DeepDeck is an MIT-licensed macOS desktop built on DeepSeek Harness. It turns Cordis plugins into apps with their own windows, settings, Workspaces, and Agent Sessions. Use Hacker News Reader or Video Sherlock, ask the agent to modify local source, rebuild and hot-reload the result, then contribute useful changes through Git and PRs. Bring your own Codex or DeepSeek connection. No included model credits. Not an official DeepSeek product.
On the analytics side, DeepDeck competes within Open Source, Developer Tools, Artificial Intelligence and GitHub — topics that collectively have 1.1M followers on Product Hunt. The dashboard above tracks how DeepDeck performed against the three products that launched closest to it on the same day.
Who hunted DeepDeck?
DeepDeck was hunted by Joe Jiang. 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 DeepDeck including community comment highlights and product details, visit the product overview.
Joe Jiang
Maker update: I published a new open-source DeepDeck App called Strudel Studio.
It is a visual song sequencer with multi-section arrangements, up to eight tracks, independent 16-step patterns, 31 instruments, full-song preview, and deterministic Strudel source generation.
The experiment is about more than AI-generated music. The visual App owns the authoritative project state, while the main Agent can propose bounded, structured edits through a registered action. Every result is validated, tied to the revision it started from, and applied as a reversible change. Stale Agent output is rejected instead of silently overwriting newer human work.
I’m testing whether some agent skills should come with an optional human-facing App—not replacing their agent-readable instructions, but giving people a better place to start, observe, steer, and verify the work.
Open source: https://github.com/jo32/dsh-strudel-studio
Would you rather use an Agent inside creative software as a chat overlay, or through narrow actions that modify validated project state?
Disclosure: I build DeepDeck and Strudel Studio. DeepDeck is based on DeepSeek Harness and is not an official DeepSeek product.