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
Mentar
Open-source AI tutor that runs on your PC, not the cloud!
A free, open-source AI tutor for kids that runs entirely on your own computer. No accounts, no subscription, nothing leaves the device. The model only explains - a deterministic checker marks every answer, so it can't tell your child a wrong answer is right. Github: avps82/mentar
I'm a parent and a developer. I wanted an AI tutor for my kids that didn't need an account, a subscription, or their homework questions going to someone's cloud. I couldn't find a free one, so I built it — and I'm open-sourcing it because other parents shouldn't have to.
The bit I care about most: the AI never grades anything.
Every question comes from generators I can actually read - 934 topics across Years 1–12, for Australian, Indian, Singaporean and US curricula. A deterministic checker marks the answers. The model's only job is explaining: analogies, worked examples, "have another look at step 2" nudges. Worst case, a hallucination gives my daughter a clumsy explanation. It can't tell her a wrong answer is right.
It runs fully local on Ollama or llama.cpp - my test machines are a base M1 MacBook and an old gaming rig with a 3080. There's also an optional cloud mode if you'd rather use an OpenAI or Anthropic account; it's off by default and asks for explicit consent first, because that's your child's conversation leaving your house.
Being straight with you, because it's a kids' product: this is a research preview for supervised use — a grown-up in the room. Most of the code is AI-written under my direction and review (the README says so on the first screen), and the safety layer has not had a professional safeguarding audit. I'm an unfunded side project, and I'm looking for that review pro bono. There's a ready-made packet in the repo for anyone qualified who's willing to look.
It's AGPL, on purpose: if someone ships kids a modified version, the safety changes have to be inspectable.
No startup, nothing to sell, just a parent with a repo. My kids are the first users, so ask me the hard questions.
About Mentar on Product Hunt
“Open-source AI tutor that runs on your PC, not the cloud!”
Mentar was submitted on Product Hunt and earned 0 upvotes and 1 comments, placing #107 on the daily leaderboard. A free, open-source AI tutor for kids that runs entirely on your own computer. No accounts, no subscription, nothing leaves the device. The model only explains - a deterministic checker marks every answer, so it can't tell your child a wrong answer is right. Github: avps82/mentar
On the analytics side, Mentar competes within Open Source, Education, Artificial Intelligence and GitHub — topics that collectively have 667.4k followers on Product Hunt. The dashboard above tracks how Mentar performed against the three products that launched closest to it on the same day.
Who hunted Mentar?
Mentar was hunted by Pradeep. 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 Mentar including community comment highlights and product details, visit the product overview.
Pradeep