Sankofa – Browser extension to semantically search your history
Hey there HN! I lead Product at Vectara. Some of us read a lot of articles on the web (like those on HN) and we were desperately trying to recall the text we read -- using semantic search because we might not have remembered the exact text we read. (Or ask questions about the content -- ChatGPT style.) Sankofa is a new browser extension that can automatically index web pages you visit and let you search / ask questions about that content. We built it using Vectara's retrieval-augmented-generation (RAG) platform and hope this is useful to folks. This is an initial release: we would love…
In plain words
Sankofa is a browser extension that automatically indexes web pages as users visit them, enabling semantic search and question-answering about previously read content. Built on Vectara's retrieval-augmented-generation platform, it helps users recall articles and information without needing to remember exact wording. The extension is designed for people who read extensively online and need to quickly retrieve and query specific information from their browsing history.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hey there HN! I lead Product at Vectara. Some of us read a lot of articles on the web (like those on HN) and we were desperately trying to recall the text we read -- using semantic search because we might not have remembered the exact text we read. (Or ask questions about the content -- ChatGPT style.) Sankofa is a new browser extension that can automatically index web pages you visit and let you search / ask questions about that content. We built it using Vectara's retrieval-augmented-generation (RAG) platform and hope this is useful to folks. This is an initial release: we would love to hear any feedback and suggestions!
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, January 2024
the whole month →
- IM
Life & fun · 2024 · sitinshade.com
