Atomic
AI-native personal knowledge base with semantic search and wiki synthesis
Visit atomicapp.ai ↗What is Atomic?
Atomic is a self-hosted or cloud-hosted knowledge management tool that organizes notes as "atoms"—markdown entries automatically tagged, embedded, and linked by semantic similarity. It offers semantic search to find ideas by meaning rather than keywords, wiki synthesis to generate cited articles from tagged notes, and an agentic chat interface that queries your knowledge base without hallucination. The tool runs as a desktop app, iOS client, or self-hosted server synced across devices, with integrations for Claude and Cursor via MCP.
Designed for individuals managing personal knowledge, Atomic emphasizes end-to-end ownership: your data stays on your hardware or your own server. Features include a spatial canvas visualization of connected ideas, auto-tagging powered by LLMs, RSS feed ingestion, browser extension for web clipping, and scheduled reports. The project is open source and available on GitHub.
Momentum
Daily activity over the last 30 days: upvotes, unique visits, new GitHub stars and Hacker News points.
How do we know it's vibe coded?
vibetrend discovered Atomic automatically. Evidence: GitHub kenforthewin/atomic; repo has AGENTS.md, CLAUDE.md. View source.
Similar vibe-coded apps
#2 this week
Manage teams of AI agents to run your business from one dashboard

Agent development environment for running multiple coding agents in parallel

AI converts documents into natively editable PowerPoint presentations

Open-source video production system directed by AI agents

Open-source AI job search agent that runs locally in your CLI

Open-source desktop client for DeepSeek Harness with plugin architecture

Open-source Android agent that runs on-device with no root required