I built a mental health app to fix mine
Hi HN, I’m still in college and new to the startup world, but here is my first shot at a side project: Milburn, an integrated therapy+journal tool(https://milburn.vercel.app/). I built Milburn bc every mental health tool I could find was missing something: the therapy apps didn’t have voice/memory/too expensive, and the journal apps were always a PITA to sync with therapy. We trained the chatbot’s model on specific therapy modalities(I personally need CBT sessions, but we also have others like DBT), and then created a prompted journal, added a feedback loop, voice…
What it does
In the maker’s words, at launch
Hi HN, I’m still in college and new to the startup world, but here is my first shot at a side project: Milburn, an integrated therapy+journal tool(https://milburn.vercel.app/). I built Milburn bc every mental health tool I could find was missing something: the therapy apps didn’t have voice/memory/too expensive, and the journal apps were always a PITA to sync with therapy. We trained the chatbot’s model on specific therapy modalities(I personally need CBT sessions, but we also have others like DBT), and then created a prompted journal, added a feedback loop, voice capabilities, and a triage questionnaire. We’re clearly still at a super early stage and new to this lol, so we would appreciate any feedback on the tool/idea: What resonates? What’s missing? Is this different enough to the myriad other mental health apps on the market? I’d especially appreciate insights from those who’ve worked in mental health tech or have experience with similar tools. We’re also looking for beta users so drop me an email at [[email protected]](mailto:[email protected]) if you’d like some free access!
Does the same job
all alternatives →
- MMMy midweek project - karmurl2011 · ▲26
Inspired by the following post by photon_off... http://news.ycombinator.com/item?id=1683309 I made karmurl last night. It's a simple app where you submit a URL for feedback, then for every piece of feedback you give to someone else's, you get to read one piece of feedback for yours. http://karmurl.com
- IBI built a mockup/prototype/wireframe editor in ten weeks2012 · ▲42
Hi HN, After watching a lot of Show HN's here, it's finally my turn to show something. This is the first real project I have shipped, so it is extra special to me. For those who will inevitably ask why I made yet another mockup editor I covered it on our blog (http://blog.mocktailsapp.in/why-build-yet-another-mockup-editor-tm). Not all the features mentioned in that post have been implemented yet. As such Mocktails is pre-beta software and very minimal. It does not even have user accounts or any actual server side component at all for that matter (yet)! Our intention is to build Mocktails…
- ETEchologue – the private AI voice journal I built for myselfJul 2026 · echologue.com · ▲29
I have tried journaling many times but nothing stuck. So I decided to make my own app for myself with these features: * Voice first * Private first * AI chat * Automatic tagging, meaning extraction, and semantic retrieval using embeddings stored locally * Export to LLM the AI angle is especially interesting for me. It allows me to ask questions like: * "remind me highlights and crazy nights in the last 3 months" * "How was I feeling during my trip in Spain and how big of a problem was my breakup" * "How would you judge my overall interactions with Marc after I told him about my problems" the…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
