nowfound

Life & fun · May 28, 2026

Reqiem

Remember those you've lost — from anywhere in the world

What it does

I built Reqiem after losing someone dear — and being unable to visit their grave because of the war in Ukraine. For everyone separated from the places where their loved ones rest. Create memory pages with photos, biography, candles and flowers — start free, share with family anywhere in the world.

Does the same job

all alternatives →
  • Rebuilt from Memories2020 · ▲74

    A view into the collective memory of Aleppo before the war.

  • Remem AIFeb 2026 · ▲112

    AI that remembers what matters for you

  • Yume Journal2025 · ▲158

    Never forget your dreams again

  • wander2022 · ▲71

    Your personal memory travel guide.

  • Bring Hope With a Donation Popup2023 · ▲96

    Help earthquake victims in Türkiye, it’s time to unite

  • BA
    Build a personal knowledge graph from the content you consume online2023 · recall.wiki · ▲79

    I've been working on this tool that lets you build a personal knowledge graph from articles, blog posts, podcasts, YouTube videos, and other content you find interesting online. You can safely forget everything and trust that Recall will resurface it when something new that is related comes up. Looking forward to your thoughts and feedback on how it could be improved! The original version of Recall was posted last year nov on HN: https://news.ycombinator.com/item?id=33425947 Since then I have pivoted to a browser extension.

More life & fun this month

the category →

Launched alongside, May 2026

the whole month →
  • Brew 905

    Like Claude design for email marketing

    AI · May 2026 · brew.new

  • Parallel agents, diff reviewer, and multi-model comparisons

    Dev tools · May 2026 · kilo.ai

  • StoreClaw805

    Grow your store profits with agents that know how to sell

    AI · May 2026 · storeclaw.ai

  • Give your agent a real number and voice to make calls.

    AI · May 2026 · pollyreach.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