Snapdeck – Build slides with open-source LLMs and agent routing
I’m a student founder, and Snapdeck has been a 6-month sprint from idea to product. In March I hacked together a minimal version and launched it on Product Hunt just to see if anyone else had the same frustration with slides — and people did. A couple of months later I tried a Figma plugin version, which brought in more feedback but still felt limited. Yesterday we launched the first full standalone version on Product Hunt and reached #2 of the day. About 1,000 people have signed up so far, with ~30% retention among the main target users. Under the hood, Snapdeck runs on an orchestration…
What it does
In the maker’s words, at launch
I’m a student founder, and Snapdeck has been a 6-month sprint from idea to product. In March I hacked together a minimal version and launched it on Product Hunt just to see if anyone else had the same frustration with slides — and people did. A couple of months later I tried a Figma plugin version, which brought in more feedback but still felt limited. Yesterday we launched the first full standalone version on Product Hunt and reached #2 of the day. About 1,000 people have signed up so far, with ~30% retention among the main target users. Under the hood, Snapdeck runs on an orchestration layer we built that routes tasks across multiple open-source language models and commercial APIs, acting as an “agent” to generate structured slides and editable charts. Unlike most AI slide tools, everything stays fully editable — layouts, visuals, and content can be dragged, modified, or updated via natural-language commands. Current output is PDF, with PPTX coming soon. Demo screenshots: https://youtu.be/fmlQ6cccj1w . We’re considering open-sourcing parts of the orchestration layer, and I’d love feedback from HN: is this genuinely useful for real workflows, and what’s still missing? https://snapdeck.site
Does the same job
all alternatives →
- MAMarkdeck – author cool slides, text-only, offline-ready, collaborative2019 · github.com · ▲235


- CLCraft.ly2011 · craft.ly · ▲10
We hatched this idea of a Kickstarter + Groupon + Etsy model last week, threw up a super simple landing page that day, then launched a more detailed landing page last night. What do you think of the idea as a whole? The landing page itself? Since the Etsy / crafting world is so large and diverse, we're really trying to focus on the sharing of our site to get the word out. We are doing some minimal google ads and will be doing various tests to see what brings in the best traffic and converts the best. Interestingly enough, good old fashioned twitter searching with hand authored tweets has had…
- IMI Made an AI Software Engineer with Google Gemini 1.5 Flash2024 · saas-quick.com · ▲6
Hey HN! Thank you for all the support and feedback on my original submission 2 months ago. I've been improving the backend using a MCTS/AlphaZero approach and it's currently producing much better results. My long term goal is to allow users to manage multiple projects, deployed autonomously, both from scratch and by making continual updates all prompted with natural language. The cost of each project has been lowered to $9 as performance with smaller models has improved (I migrated from Claude-3-Opus to gemini-1.5-flash). Thanks for checking it out!
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, September 2025
the whole month →
- AS
Commerce · Sep 2025 · anycrap.shop
- TE
I made a built-from scratch Wayland Compositor to display any GUI app* in the terminal! I think there is a lot of unexplored potential in custom Wayland compositors, a lot of really cool things you can embed existing applications into! So, I started with embedding apps into the terminal because that is the easiest input/output (output is just utf-8 and I use the great `chafa` library for that, and I just read from stdin for the input). If you have any other ideas for cool Wayland compositors, let me know. I purposedly wrote 80% the app in Typescript to appeal to the most developers and…
Dev tools · Sep 2025 · github.com
- IR
Years ago I stumbled across a basic version of this concept and it stuck with me. I knew if I was ever going to take on such a project, it would need to be flawless, but without coding experience it was just another idea that would never happen. By the end of 2024, as AI coding tools exploded everywhere, I finally had a way to make it real. I started from zero knowledge and spent months collaborating with AI agents as a learning experience. Every pixel and every function went through me. The AI translated what I asked for into code, but every decision was human. I didn't use existing OS…
AI · Sep 2025 · mitchivin.com

