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).
DeepTutor Mobile
An open-source phone client for HKUDS's DeepTutor AI tutor
DeepTutor is an open-source AI tutor from HKUDS at the University of Hong Kong. It explains, answers and creates practice. I built DeepTutor Mobile, an unofficial open-source phone client for it. Build from source; bring your own server.
HKUDS at the University of Hong Kong open-sourced DeepTutor, an AI tutor that explains study materials, answers questions and creates practice exercises.
I built DeepTutor Mobile as an independent, open-source mobile client for this project. Connect to the DeepTutor running on your own computer or VPS, then chat, review mistakes and manage study materials from your phone.
My goal is to make an existing self-hosted learning setup more convenient to use day to day. DeepTutor provides the AI learning capabilities; my contribution is the mobile interface.
The client has a Simplified Chinese UI and targets Android and iOS. This is a source preview: build it yourself and bring your own DeepTutor 1.7.1 server. There is no installable release yet.
Android interaction flows have been tested against mock services. iOS has passed a simulator build, with interaction testing pending. Real-model and OCR workflows still need validation.
The client is Apache-2.0; hosting and model-service costs are separate. Thanks to the HKUDS team for the upstream project.
Which mobile workflow would you improve first: chat, adding materials or reviewing mistakes? Feedback, issues and PRs are welcome.
No comment highlights available yet. Please check back later!
About DeepTutor Mobile on Product Hunt
“An open-source phone client for HKUDS's DeepTutor AI tutor”
DeepTutor Mobile was submitted on Product Hunt and earned 0 upvotes and 1 comments, placing #210 on the daily leaderboard. DeepTutor is an open-source AI tutor from HKUDS at the University of Hong Kong. It explains, answers and creates practice. I built DeepTutor Mobile, an unofficial open-source phone client for it. Build from source; bring your own server.
DeepTutor Mobile was featured in Open Source (69k followers), Artificial Intelligence (483.1k followers), GitHub (41.5k followers) and Online Learning (3.8k followers) on Product Hunt. Together, these topics include over 193.3k products, making this a competitive space to launch in.
Who hunted DeepTutor Mobile?
DeepTutor Mobile was hunted by Panda. 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 DeepTutor Mobile stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Panda
Hi Product Hunt!
HKUDS at the University of Hong Kong open-sourced DeepTutor, an AI tutor that explains study materials, answers questions and creates practice exercises.
I built DeepTutor Mobile as an independent, open-source mobile client for this project. Connect to the DeepTutor running on your own computer or VPS, then chat, review mistakes and manage study materials from your phone.
My goal is to make an existing self-hosted learning setup more convenient to use day to day. DeepTutor provides the AI learning capabilities; my contribution is the mobile interface.
The client has a Simplified Chinese UI and targets Android and iOS. This is a source preview: build it yourself and bring your own DeepTutor 1.7.1 server. There is no installable release yet.
Android interaction flows have been tested against mock services. iOS has passed a simulator build, with interaction testing pending. Real-model and OCR workflows still need validation.
The client is Apache-2.0; hosting and model-service costs are separate. Thanks to the HKUDS team for the upstream project.
Which mobile workflow would you improve first: chat, adding materials or reviewing mistakes? Feedback, issues and PRs are welcome.
Client: https://github.com/TinyPandaGame/deeptutor-mobile
Upstream: https://github.com/HKUDS/DeepTutor