LMRing
Compare and evaluate AI models side-by-side with real-time streaming responses
Visit lmring.com ↗What is LMRing?
LMRing is an open-source platform for comparing multiple AI models simultaneously across 50+ providers including OpenAI, Anthropic, Google, and Meta. Users write a prompt once and send it to up to four selected models, viewing real-time streaming responses in a unified interface. The platform supports text, image, and video inputs for multimodal evaluation.
Features include an ELO-based leaderboard, voting system for crowdsourced quality assessment, conversation history with sharing capabilities, and support for custom OpenAI-compatible endpoints and local models. LMRing is self-hostable with full data ownership, supporting flexible authentication via GitHub, Google, and email OTP. The project was built using Claude and Gemini AI coding tools.
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 LMRing automatically. Evidence: GitHub llm-ring/lmring; repo has AGENTS.md, CLAUDE.md, GEMINI.md. View source.
Similar vibe-coded apps
Open-source AI job search agent that runs locally in your CLI
A second brain for the AI era. Markdown notes with Git and AI agents.
Sovereign agent operating system for enterprises to own their AI knowledge
Open-source workplace AI platform connecting enterprise knowledge to AI agents
Local MCP server connecting AI assistants to Adobe Premiere Pro with preview and
Open-source control plane for coordinating multiple AI coding agents
Coordinate specialist AI agents around shared goals with review and reuse
