Local PDF question-answering assistant
Keep large PDFs out of an AI context window by searching them locally and sending only relevant passages with page citations.
From Github Awesome — GitHub Trending Weekly #43: Cloudflare Computer, waku-agent, querysplat, findphone, Soup, morphicons at 11:08
Problem: Sending an entire large PDF into a model consumes context unnecessarily and can make relevant passages harder to retrieve.
For: Users who ask questions about PDFs large enough to make full-document context inefficient.
Products from this video
anydoc Backchannel Bindwidth Can I Vibecode It? Capptivo cargo-frisk chapter-tgz Claude Code Claude Desktop Cloudflare Computer ComfyUI-Spectrum-MiniMax-H3 CommerceAgentBench creakwork12 da-cli Desko diri doc7 Falco findphone Finger Frame AI GenOffice Gmail Jungle Trail King's Gambit — Medieval 3D Chess MAGI-2 Preview Microsoft Outlook morphicons Node.js OpenAI Codex OpenEdit Outreachr Python QuerySplat Rust Shitty Soup SQLite Stickman Video Director Swiftlet Token Saver Virtual Mac on iPad vPhone Workstation Waku Agent whisper.cpp
Examples
- Token-Saver is described as a Claude Desktop extension that uses local hybrid search and sends selected passages with page citations.