Overview
Understanding RA-H's approach to knowledge management
What is RA-H?
RA-H is an AI-powered knowledge management system designed for researchers, thinkers, and anyone who works with ideas. It learns how you think and helps connect ideas across your entire knowledge base.
The Problem
Knowledge workers struggle with scattered information across tools like Notion, Obsidian, bookmarks, and notes apps. You know you read something important, but can't find it. Traditional tools don't learn from your workflow or adapt to how you think.
RA-H's Solution
- Automatically organizes diverse content — Papers, videos, notes, tweets all in one place
- Learns from every interaction — Gets smarter about your knowledge over time
- Makes your knowledge conversationally searchable — Ask questions, get answers from your own content
- Runs locally on your Mac — You own your data completely, no vendor lock-in
- Structure emerges naturally — No forced folders or categories, organization emerges from your usage patterns
Two Ways to Use RA-H
| Version | Best For | Get It |
|---|---|---|
| Mac App | Most users. One-click install, auto-updates | Download |
| Open Source (RA-OS) | Developers, self-hosters, contributors. BYO API keys | GitHub |
Both versions use the same core codebase. The Mac app adds packaging, auth, and optional subscription features. The open source version is fully functional with your own API keys.
Design Philosophy
Non-prescriptive & Emergent
The system doesn't force you into folders or predefined categories. Organization emerges naturally from your actual content. The structure adapts to how you think, not the other way around.
Everything is Connected
Every piece of knowledge can potentially connect to any other. Connections aren't just links — they carry context, explanation, and meaning. RA-H helps you discover these connections automatically.
Local-First
Your knowledge network belongs to you, not a platform. Your thinking, research, and connections all live on your machine in a portable format you control. No cloud dependencies, no data mining, no vendor lock-in.
Human + AI
You guide, AI assists. Create custom guides to share context with AI agents. Always in control of your knowledge.
Tech Stack
- Frontend: Next.js 15, TypeScript, Tailwind CSS
- Database: SQLite + sqlite-vec (vector search)
- AI Models: Anthropic Claude + OpenAI GPT via Vercel AI SDK
- Desktop: Tauri (Mac app)
- MCP Server: Local connector for Claude Code and external agents
Current Status
- Version: v0.1.27 (February 2026)
- Platform: Mac (Apple Silicon + Intel), macOS 12+
- Database:
~/Library/Application Support/RA-H/db/rah.sqlite - License: MIT (open source version)
Key Features
- Flexible Pane System — Feed view, Focus panel, collapsible Chat
- Normal/Agent Mode — Toggle between fast (GPT-5 Mini) and deep reasoning (Claude Opus 4.5)
- Smart Organization — Multi-tag dimensions instead of folders
- Agent Memory — Persistent memory across sessions in Agent mode
- Guides — Markdown documents that help AI agents understand your knowledge base
- Content Extraction — YouTube videos, websites, PDFs automatically processed
- MCP Server — Connect Claude Code and other external agents to your knowledge base