Odin
Find any file. Ask any document. 100% local AI.
What it does
Odin indexes millions of files in seconds using NTFS MFT parsing, then lets you search instantly and ask questions about any document (PDF, Word, Excel, HWP, etc.) using a fully local AI. No cloud, no account, no data ever leaves your machine.
Does a similar job
all alternatives →- OAOSS AI agent that indexes and searches the Epstein filesJan 2026 · epstein.trynia.ai · ▲211
Hi HN, I built an open-source AI agent that has already indexed and can search the entire Epstein files, roughly 100M words of publicly released documents. The goal was simple: make a large, messy corpus of PDFs and text files immediately searchable in a precise way, without relying on keyword search or bloated prompts. What it does: - The full dataset is already indexed - You can ask natural language questions - Answers are grounded and include direct references to source documents - Supports both exact text lookup and semantic search Discussion around these files is often fragmented. This…
Locally AI Chat with your documentsNov 2025 · ▲12Analyze, extract, summarize files locally, just by asking.
Insight - AI Document AgentJun 2026 · apps.apple.com · ▲4Your documents, understood. Chat with any file— all offline
- IAIndex and search *all* your documents2024 · github.com · ▲21
Hey HN! I've build a simple tool to index and search your documents. This uses two great open source libraries: apache tika (for extracting content from docs) and apache lucene (for searching). It's been built with kotlin ktor as a web framework. You can index all kind of files (i.e doc, docx, xls, ppt, pdf, txt, html even ORC pdfs) and then search them using very advanced queries like "always contain X", "never contain X", "X near Y", wildcard search, proper stemming support etc. We're using it on my work where we have hundreds of thousands of doc/docx/pdf files and it works…
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 · 19d 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, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
