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).
Tosly
AI that reads the Terms of Service so you don't have to
Tosly is a free, open-source Chrome extension that scans Terms of Service pages, flags clauses written against you (data selling, forced arbitration, auto-renewals) in plain English with red/yellow/green severity, and highlights the exact quote on the live page before you click Accept. Only the visible text and URL leave the browser. No account, no login.
Most launch posts hide their weakest spot, so here is Tosly's up front: it trusts an LLM's category rubric. If the rubric is wrong, the flags are wrong, and nothing in the architecture fixes that. Signal for personal decisions, not legal advice.
What I could fix was how much you have to trust the model's prose.
Asking an LLM to "summarize this ToS" gives you a confident paragraph that says nothing. So the prompt is a scaffold instead: a fixed category rubric (data selling, forced arbitration, auto-renewal), severity rules, a JSON schema, and one hard constraint, every flag must carry the verbatim quote that triggered it, copied not paraphrased, max 200 chars. The quote is then highlighted on the live page.
If it cannot cite the clause, it cannot flag it. That bounds the bluffing without pretending to remove it.
Two real questions: - Where should a tool like this refuse to render a verdict at all? - Which clause types do you most distrust an LLM to read correctly?
Repo, store listing and demo are below if you want to poke at the rubric.
No comment highlights available yet. Please check back later!
About Tosly on Product Hunt
“AI that reads the Terms of Service so you don't have to”
Tosly was submitted on Product Hunt and earned 4 upvotes and 1 comments, placing #146 on the daily leaderboard. Tosly is a free, open-source Chrome extension that scans Terms of Service pages, flags clauses written against you (data selling, forced arbitration, auto-renewals) in plain English with red/yellow/green severity, and highlights the exact quote on the live page before you click Accept. Only the visible text and URL leave the browser. No account, no login.
Tosly was featured in Chrome Extensions (52.7k followers), Open Source (68.5k followers), GitHub (41.3k followers) and YouTube (16.9k followers) on Product Hunt. Together, these topics include over 52.9k products, making this a competitive space to launch in.
Who hunted Tosly?
Tosly was hunted by Preston Mayieka. 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 Tosly stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Preston Mayieka
Most launch posts hide their weakest spot, so here is Tosly's up front: it trusts an LLM's category rubric. If the rubric is wrong, the flags are wrong, and nothing in the architecture fixes that. Signal for personal decisions, not legal advice.
What I could fix was how much you have to trust the model's prose.
Asking an LLM to "summarize this ToS" gives you a confident paragraph that says nothing. So the prompt is a scaffold instead: a fixed category rubric (data selling, forced arbitration, auto-renewal), severity rules, a JSON schema, and one hard constraint, every flag must carry the verbatim quote that triggered it, copied not paraphrased, max 200 chars. The quote is then highlighted on the live page.
If it cannot cite the clause, it cannot flag it. That bounds the bluffing without pretending to remove it.
Two real questions:
- Where should a tool like this refuse to render a verdict at all?
- Which clause types do you most distrust an LLM to read correctly?
Repo, store listing and demo are below if you want to poke at the rubric.
https://github.com/preston176/to...
https://tosly.online
https://youtu.be/ivAgRwcxAH4