Hermes
Hyper-personalize every message to each user
What it does
Every email tool — Loops, Customer.io, Braze — needs setup: instrument events, build segments, write templates. Weeks of setup. Everyone still gets the same email. Hermes uses data you already have. Connect your Postgres (read-only, no schema changes), and Hermes generates a unique email for every user based on real behavior — exactly when it matters. No segments. No templates. No setup. Your data already knows who’s about to churn. Hermes turns that into insight and acts on it.
Does the same job
all alternatives →
- IMI made a MailChimp alternative that connects to your database2023 · cc.dev · ▲302
Hi all! Excited to share cc.dev after months of work and refinement. The idea for this product came from trying to do email marketing for my side project, CubeDesk, a site where Rubik's Cube enthusiasts can time themselves, race with one another, train algorithms — it's a fun niche! With over 40k users, sending even a single campaign was becoming expensive with MailChimp. I knew AWS SES would be much cheaper, but it’s just an API with none of the other necessities you need for a robust email marketing platform. Beyond cost, I was also frustrated with having to make sure my database was…
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
Launched alongside, April 2026
the whole month →
- AG
Thought the resources for GPU arch were lacking, so here we are
Life & fun · Apr 2026 · jaso1024.com
- IB
Built a ~9M param LLM from scratch to understand how they actually work. Vanilla transformer, 60K synthetic conversations, ~130 lines of PyTorch. Trains in 5 min on a free Colab T4. The fish thinks the meaning of life is food. Fork it and swap the personality for your own character.
AI · Apr 2026 · github.com
- BC
Life & fun · Apr 2026 · sam-burns.com
- IB
With social media and now AI, its important to keep the indie web alive. There are many people who write frequently. Blogosphere tries to highlight them by fetching the recent posts from personal blogs across many categories. There are two versions: Minimal (HN-inspired, fast, static): https://text.blogosphere.app/ Non-minimal: https://blogosphere.app/ If you don't find your blog (or your favorite ones), please add them. I will review and approve it.
AI · Apr 2026 · text.blogosphere.app