AnythingLLM for local doc Q&A and Buzz for offline transcription
alex_verem · x · 2026-11-01
Two local-first tools: AnythingLLM lets you drop in PDFs, Word and text files and ask questions about them, with desktop apps for Mac/Windows/Linux and models running on your own machine (67.8k GitHub stars). Buzz replaces Otter for audio you already have — interviews, lectures and voice memos get transcribed and translated fully offline, keeping sensitive recordings on your device.
More from Infra
- Where the money goes per token: a diagram of LLM API cost anatomy — cneuralnetwork · 2026-11-01
- FreeToken brings datacenter-scale MoE model serving to desktops, hits 15k stars — FlashML-org · 2026-11-01
- Musk claims xAI's capex efficiency is greatly underestimated — RachelVT42 · 2026-11-01
- AI bubble pops globally: China wipes out ¥23.5T, Nasdaq drops 3.46% in a day — Grady_Booch · 2026-11-01
- Strata engine underwhelms on 2× R9700: loses to llama.cpp despite higher t/s — Don_Reuter · 2026-11-01
- exo clusters your Macs into one AI machine to run frontier models locally — alex_verem · 2026-11-01