andrewnguonly/Lumos

Health v2 · maintenance only

Adoption not part of the score

1516 stars · 112 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Lumos is a Chrome extension that acts as a RAG-powered LLM co-pilot for browsing the web, letting users summarize pages and ask questions about on-screen content. It runs entirely on local LLMs via a locally hosted Ollama server, so no data is sent to remote inference services.

Use cases

• summarize long threads on forums and social media
• summarize news articles while browsing
• ask questions about product and business reviews
• ask questions about long technical documentation
• run an LLM assistant in the browser without cloud APIs
• chat with web page content using local models

When to choose

• you want an in-browser LLM assistant with full privacy using local inference
• you already run Ollama and want a browsing co-pilot on top of it
• you need RAG-style Q&A over the page you're viewing

When to avoid

• you want cloud-hosted model quality without managing a local Ollama server
• you need a browser other than Chrome
• you cannot run or configure a local LLM server with CORS settings

Facets

application · maturity active

rag llm-inference chatbot browser-extension large-language-models browser-extensions privacy browser-extension self-hosted ollama langchain-js local-llm chrome-extension web-copilot privacy-first retrieval-augmented-generation docker

Member repositories

For agents

markdown · JSON · MCP: product_card(name="andrewnguonly/Lumos")