LIAM
Email drafts in your voice + inbox organising + scheduling
What it does
You are wasting hours on emails and managing your calendar. LIAM is an executive assistant that connects to your Gmail and generates ready-to-send drafts in your voice, prioritises important emails, and helps with scheduling. LIAM never sends emails without your approval. No new app or software to install. Takes 1 minute to connect and it lives in your mailbox.
Does the same job
all alternatives →- LELIAM – email and calendar assistant that drafts replies and schedulesFeb 2026 · doitliam.com · ▲6
Hi HN, yesterday I missed a meeting and spent most of the day sending ~35 emails. That kind of inbox + calendar admin has been draining my time for a long while, so I built LIAM to fix it. It helps with: - Drafting replies in your tone (honestly a bit scary how close it gets) - Scheduling meetings and handling the back and forth - Prioritising important threads and organising the inbox Important: LIAM doesn’t send anything without approval. I’d love feedback on what you’d actually trust an email agent to do, and which email workflows you’d automate first. You are more than welcome to roast…
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 · 16d 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
