Sorana

Inspiration We got tired of re-explaining ourselves to AI every single day. Our notes were in Obsidian, our tasks scattered across folders, and every time we opened a new chat, the AI had forgotten everything. We wanted a workspace that thinks the way we do: through connections, context, and accumulated knowledge. So we built Sorana, a personal AI that learns your projects, remembers your preferences, and makes your knowledge actually work for you.

What is Sorana? Sorana is your personal AI knowledge workspace, a second brain that actually acts. Unlike chatbots that forget you the moment you close the window, Sorana builds a lasting memory of your projects, files, and thinking style. Open it tomorrow and it already knows where you left off. Visualise your entire knowledge base on a spatial 2D canvas (like Obsidian Canvas, but AI-powered), chat with any document in plain language, and let your AI handle repetitive tasks, organising files, researching topics, managing emails, all without leaving your workspace. Everything runs on your machine. Your data stays yours.

Core Capabilities

• AI memory: Think of Sorana's memory as a personal knowledge profile that grows with every conversation. It captures what matters, your projects, your writing style, your preferences, so your AI gets sharper over time, not blunter. Like a second brain that never forgets, even after months away
• MCP servers: Your AI should do, not just advise. Tools like Obsidian and Notion help you organise knowledge, but they can't act on it. Sorana's built-in automation lets you give plain-language instructions and watch them execute: move that file, summarise this folder, fetch that article, archive those emails. No app switching. No copy-pasting. Just results.
• Obsidian export: Already using Obsidian? Sorana is the AI layer your vault has been missing. Export your Sorana workspace directly into Obsidian, your spatial file groupings, topic relationships, and knowledge structure, in formats Obsidian natively understands. Use Sorana as your intelligent AI workspace, and keep your Obsidian vault as your permanent knowledge archive. The best of both worlds.
• Document Processing and OCR: OCR extracts text from scanned documents, images, and PDFs. Once processed, documents become searchable and indexed via adaptive retrieval (semantic search ? keywords ? full-text fallback) so the agent finds precise answers from your documents. Process documents via the context menu ('Document Overview' and 'Process Documents'), particularly valuable for PDFs and image-based documents.