Herald – Local-first terminal email client
Hi folks, Some time ago I tried to find a way to clean up my 10k emails inbox and could find anything which worked for me. So I built built my own tool which evolved into a client. More that out of necessity but for fun add semantic search, LLM based tagging, and clean up rules through Ollama. It has a demo mode to try without configuring anything. On Mac: brew tap herald-email/herald brew install herald herald --demo With Go: go install github.com/herald-email/herald-mail-app/cmd/herald@latest herald --demo The DEMO uses pre-populated synthetic data so no risk for…
What it does
In the maker’s words, at launch
Hi folks, Some time ago I tried to find a way to clean up my 10k emails inbox and could find anything which worked for me. So I built built my own tool which evolved into a client. More that out of necessity but for fun add semantic search, LLM based tagging, and clean up rules through Ollama. It has a demo mode to try without configuring anything. On Mac: brew tap herald-email/herald brew install herald herald --demo With Go: go install github.com/herald-email/herald-mail-app/cmd/herald@latest herald --demo The DEMO uses pre-populated synthetic data so no risk for your inboxes. Any feedback will be highly appreciated.
Does the same job
all alternatives →
- OOOmnia OS, the Most Efficient Email Client Without AIOct 2025 · omniaos.co · ▲7
I just shipped something I’ve needed for years - a more efficient email client. I finally built Omnia OS because my inbox turned into a landfill of AI-generated noise. If you're going to email me going forward, I suggest including a more compelling subject and opening line, otherwise all emails from unknown people will not make it to my inbox. AI draft-suggestion tools never solved the real problem: finding the messages, files, or company I actually need to follow up with. After securing AI systems for a living, I know how easy it is to weaponize prompt injection, so bolting AI onto email…
- OSOpen-source email helpdesk2013 · github.com · ▲42
We've tried systems like OSTicket, OTRS etc, but never found anything to our liking. Most systems were cluttered, slow or too advanced. Brimir is simple but usefull.
- OSOpen sourcing my email sending startup2019 · ▲38
Hi all, I've posted a few times here about Maildown, a startup that I've been trying to validate lately. Due to lack of time to focus on this, I've taken the decision to abandon the project as a startup, but to make it available as an open source solution instead. The (still very basic) github repository is here: https://github.com/chris104957/maildown Maildown now exists as a simple CLI wrapper for Amazon SES which bakes in Markdown and styling support, making it much easier to get transactional mails up and running in any project Thanks for looking, Chris
- KFKeyboard First Email ClientApr 2026 · tallyman.io · ▲7
My email clients/inbox really fu*ing annoyed me. Tallyman is what happened next: a keyboard driven email client on top of Gmail and Outlook. Your vim muscle memory works (j/k, gg, relative line numbers, counts, ...) 39 rebindable shortcuts, command palette, email templates, themes ... No migration. OAuth only. Verified by Microsoft and live now. Google verification is under review. 30 day free trial, $9/mo per inbox after that. Write me an email if you need an extended trial: [email protected]
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 · 26d ago · cactuscompute.com
Launched alongside, May 2026
the whole month →
Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai
- NW
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com
- FM
Dev tools · May 2026 · github.com