I built a zero-backend, browser-only alternative to Open WebUI and heavy LLM stacks

A developer built Lab, an open-source, browser-only web interface for LLMs that runs entirely client-side without any backend, database, or Docker containers. The MIT-licensed tool connects directly to a local Ollama instance over HTTPS, requiring only the OLLAMA_ORIGINS environment variable to permit cross-origin requests. It targets users who want a lightweight workspace for inspecting token counts, testing system prompts, or chatting with local models.

Most open-source LLM chat interfaces follow the exact same blueprint: a heavy Python or Node.js backend, a Postgres/Redis database, and a multi-container Docker Compose setup just to pass a JSON prompt to an API. If you just want a clean, responsive workspace to inspect token counts, test system prompts, or chat with your local Ollama instance, deploying 2GB+ of Docker containers is massive overkill. That’s why I built Lab - a lightweight, completely serverless, local-first web environment for LLMs. Since Lab runs entirely in your browser over HTTPS, connecting to a local Ollama instance http://localhost:11434 requires allowing browser cross-origin requests. Simply set the environment variable on your Ollama host: Linux systemd sudo systemctl edit ollama.service Add: Service Environment="OLLAMA ORIGINS= " Restart Ollama, and Lab connects instantly directly from your browser tab. The project is fully open-source under the MIT license: Feedback, bug reports, and PRs are more than welcome