Harvest – Structure live web data using AI chat
Hey HN! We’re excited to share Harvest- AI chat that structures live web data. https://www.goharvest.ai/ Harvest takes plain English chat and structures live data from any public webpages. Harvest pulls content from exactly the sources you specify; or if you don’t, it searches for sources. ChatGPT and Perplexity only serve you the parts of webpages they’ve indexed; Harvest gives you complete webpage data that’s fresh. For example: you can compile cloud GPU prices from many sites in a minute with one sentence of English:…
What it does
In the maker’s words, at launch
Hey HN! We’re excited to share Harvest- AI chat that structures live web data. https://www.goharvest.ai/ Harvest takes plain English chat and structures live data from any public webpages. Harvest pulls content from exactly the sources you specify; or if you don’t, it searches for sources. ChatGPT and Perplexity only serve you the parts of webpages they’ve indexed; Harvest gives you complete webpage data that’s fresh. For example: you can compile cloud GPU prices from many sites in a minute with one sentence of English: https://www.youtube.com/watch?v=ayBM0rm39Rw Harvest intelligently opens subpages to get more info. You can prompt Harvest to guide it to even better results. The results it gives are beautiful, iterable, and exportable. Coming soon is AI browser automation that interacts with pages 3x faster than OpenAI’s Operator or Computer Use; scheduled scrapes to run automatically and repeatedly; and whatever enough people tell us they want. If you currently have challenges structuring web data, we’d love to chat. https://discord.gg/gpJCTqqZ
Does the same job
all alternatives →
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, March 2025
the whole month →
Mimic Human Research & Save Findings in AI Knowledge Base
AI · 2025 · sider.ai
