Whirl
AI chat app with memory, multiple models, and living documents
Visit whirl.chat ↗What is Whirl?
Whirl is a full-stack AI chat application built on Next.js and Convex that lets you chat with multiple AI models in one conversation, routed through OpenRouter. It features long-term memory that persists across chats, living documents and interactive visualizations that stay editable, web search capabilities, and tool integrations via MCP. The app includes locked chats with device-side encryption, voice input, image generation, and file attachments. Whirl is open-source under MIT license and available for self-hosting.
Designed for users who want persistent context across conversations and access to multiple AI models without switching between apps. Features include incognito mode, message queueing, sharing, folders, and customizable themes.
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 Whirl automatically. Evidence: Trending on git-trends.github.io: agent files (claude-code) in whirlchat/whirl. 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