Perund.io
Work with your data together with AI.
What it does
Perund.io is private AI storage that keeps you in control of your data. Upload TXT, MD, or PDF files and chat with an AI that uses only your documents as context - your content isn't trained on or shared. For external LLMs, generate a shareable link and instruction snippet for any file. Paste them into an LLM that can access URLs, and it will query your file via vector search, using results in its answers. Your file stays in Perund, and you can revoke access anytime.
Does a similar job
all alternatives →
- GYGet your unstructured data AI-ready in minutes2024 · tonic.ai · ▲38
Hey HN! We're excited to announce the launch of Tonic Textual, the secure data lakehouse for LLMs. Simply stated, Tonic Textual allows you to build generative AI systems on your own unstructured data without having to spend time extracting and standardizing your data. In minutes you can build automated, scalable unstructured data pipelines that extract, centralize, standardize, and enrich data from your documents into an AI-optimized format ready for embedding, fine-tuning, and ingesting into a vector database. While in-flight, we also scan for sensitive information and protect it via…
- IBI built a Python script uses AI to organize files, runs 100% locally2024 · github.com · ▲11
I wanted a file management tool that actually understands what my files are about. Previous projects like LlamaFS (https://github.com/iyaja/llama-fs) aren't 100% local and require an AI API. So, I created a Python script that leverages AI to organize local files, running entirely on your device for complete privacy. It uses Google Gemma2 2B and llava-v1.6-vicuna-7b models for processing. Note: You won't need any API key and internet connection to run this project, it runs models entirely on your device. What it does: - Scans a specified input directory for files -…
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
