GoldenRetriever.ai Public Beta

In plain words

GoldenRetriever.ai is a Mac-based search tool that finds specific moments in videos, audio files, PDFs, and images using multimodal AI, going beyond transcripts alone. Users ask questions in plain English and receive answers with exact timestamps and sources, even for content in foreign languages. The tool indexes files locally on the user's Mac while using their own Google Gemini API key for processing, keeping originals on disk. It's designed for anyone with recordings, documents, or media archives who struggle to locate specific information within them. The first 100 files are free to search.

written from the facts on this page · September 2026

From the sources

Search for stuff that's not in the transcripts! Your videos, recordings and documents are full of moments you can't find. GoldenRetriever.ai runs on your Mac and searches folders by what's shown as well as transcribed. Ask a question, land on the exact moment – with sources and timestamps. Find a scene from a recording. Pull up photos by theme. Check whether your insurance policy covers something, even when it's in German and you're searching in English. Free for your first 100 files.

AI search that watches your videos and hears your audio — not just transcripts. Ask questions in plain English, get sourced answers with timestamps. Free to start. Privacy-first.

Index files on your Mac. Videos, audio, PDFs, slides, screenshots, scans — understood by multimodal AI and searchable by meaning, in plain English (even if the file is in Japanese). Your originals stay on disk; AI traffic uses your own Gemini API key, billed by Google directly. You've recorded years of meetings, podcasts, lectures, demos, decisions . Saved decks, scans, screenshots, contracts. They sit as opaque blobs that search can't see into. The next time you need that one moment — you can't find it. All that knowledge is locked inside files that search can't reach. Other tools convert your video to text, then search the text. GoldenRetriever uses multimodal AI to understand the…from goldenretriever.ai

• 
  Memories.ai2025 · memories.ai · ▲446

  ChatGPT for your video library, with unlimited video context

• 
  Gemini can now natively embed video, so I built sub-second video searchMar 2026 · github.com · ▲438

  Gemini Embedding 2 can project raw video directly into a 768-dimensional vector space alongside text. No transcription, no frame captioning, no intermediate text. A query like "green car cutting me off" is directly comparable to a 30-second video clip at the vector level. I used this to build a CLI that indexes hours of footage into ChromaDB, then searches it with natural language and auto-trims the matching clip. Demo video on the GitHub README. Indexing costs ~$2.50/hr of footage. Still-frame detection skips idle chunks, so security camera / sentry mode footage is much cheaper.

• 
  AI Search Visibility Monitor2025 · writesonic.com · ▲400

  Your AI search ranking tool—for ChatGPT, Gemini, & Claude.

• 
  AI Toolbox 3.0Jul 2026 · ai-toolbox.co · ▲434

  AI Toolbox (formerly ChatGPT Toolbox): folders, search, bulk export, and prompt chaining for ChatGPT, Claude, Gemini, and Grok. 40,000+ users. Start free.

• 
  NeuraVid2025 · neuravid.io · ▲142

  Find & analyze videos instantly with AI-powered search

• 
  MomentClipJan 2026 · momentclip.com · ▲7

  Hey HN, I wanted a way to search across multiple YouTube videos at once, find every time someone discusses a topic, compare how different creators explain the same concept, or pull all mentions of a keyword across a channel's archive. The interesting part: it uses Gemini's multimodal capabilities to search visually, not just transcripts. So you can find "the whiteboard diagram" or "when he shows the demo", things transcript-based tools completely miss. Stack: Next.js, Convex, Clerk, Gemini 3 Flash Would love feedback from anyone who works with video content. https://momentclip.com

Questions this answers

• creator vetting based on transcript

• 
  Spira Maxima▲578

  Video model that turns script into viral social media videos

  AI · 17d ago · spira.ai

• 
  Rill Browser▲540

  The browser where Claude Code and Codex work beside you

  AI · 17d ago · rill.love

• 
  Germany's new sovereign AI model Kolibri▲424

  Kolibri is Aleph Alpha

  AI · 19d ago · tej.as

• 
  Giving Opus 5.5 a simulated paint canvas▲392

  Paintings by AI models: programs run through a simulation of oil paint.

  AI · 20d ago · stillwet.art

• 
  PixVerse R2▲381

  A real-time world model you can explore and change

  AI · 29d ago · world.pixverse.video

• 
  Hemory▲381

  Keep listening. Searchable memory for your AI agents.

  AI · 30d ago · hemory.com

• 
  Brew ▲900

  Like Claude design for email marketing

  AI · May 2026 · brew.new

• 
  Kilo Code for VS Code▲896

  Parallel agents, diff reviewer, and multi-model comparisons

  Dev tools · May 2026 · kilo.ai

• 
  StoreClaw▲806

  Grow your store profits with agents that know how to sell

  AI · May 2026 · storeclaw.ai

• 
  PollyReach▲795

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

  AI · May 2026 · pollyreach.ai

• 
  Needle: We Distilled Gemini Tool Calling into a 26M Model▲776

  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

• 
  Files.md – Open-source alternative to Obsidian▲730

  🌱 Private, quiet space for thinking. Simple app for .md files. - zakirullin/files.md

  Dev tools · May 2026 · github.com