Filorag — Search Inside Any Video
Skip the Replay. Just Ask.
What it does
Filorag is an AI-powered semantic search engine for videos and images. Upload content, ask questions in natural language, and instantly find the exact moment, scene, screen, or visual you need. Unlike transcript-only tools, Filorag understands context, visuals, conversations, and concepts together. Think of it as Ctrl+F for visual content. Don’t watch again. Just ask.
Does the same job
all alternatives →
- OSOpen-source AI video editor2025 · github.com · ▲268
Hey HN community! I'm one of the lead devs of this project at fal.ai and we created an open source lightweight video editor powered by the latest media AI models. The main goal was to tackle some challenges when dealing with complex media handling and encoding on the browser. It all started as an internal experiment but as we tackled some of the issues it was clear there could be some value sharing it with the open source community. Some of the key points and tech stack details: - It uses IndexedDb, so all data is local (i.e. no auth, no cloud db) - Multiple AI models for video, image, music…
- SSSisi – Semantic Image Search CLI tool, locally without third party APIs2024 · github.com · ▲128
I wrote this tool to get familiar with CLIP model, I know many people have written similar tools with CLIP before, but I'm new to machine learning and writing a classic tool helps my study. The unusual thing with my version is, it is in pure Node.js, with the power of node-mlx, a Node.js machine learning framework. The repo in the link is mostly about implementing indexing and CLI, the code of the model implementation lives as a Node.js module: https://github.com/frost-beta/clip . Hope this helps other learners!
- SVSemantic Video Search2022 · ramanlabs.in · ▲62
Hi HN, I am Anubhav from Ramanlabs. We have been working on a native gui application to allow users to search any video data( mp4, mkv) or video streams (http/rtsp) using computer vision. Application is supposed to work like a video player which displays decoded frames and recognizes objects concurrently, making it an interactive experience. It works in super real-time and only expects a quad-core CPU with AVX2 instructions at minimum. Application is free to download (without any signup/account). We are only supporting WINDOWS for now [0]. Even though this is a binary application,…
- SSSemantic search for video2023 · semanticvideosearch.com · ▲77
Hello HN Over the New Year's break, I created semanticvideosearch.com. This can search any video based on meaning and context. I would love to get your feedback on it. What should I change and what can be improved? The preprocessed videos can be search very quickly, while the youtube video links take some time (yt videos also have a upper duration limit due to compute issues). I intend to add search based on the frames of the video soon. I would love to know your thoughts on the demo and any suggestions for improvements. Thanks! PS: the inspiration to create this was to get the 2 mins of…
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 · 27d ago · cactuscompute.com
Launched alongside, May 2026
the whole month →
Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.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