Skip to main content
Lantern is a live demo of Infino as the retrieval layer for an AI agent. Pick a repository, ask a question in plain English, and Claude answers by searching the code through Infino. Every answer cites the exact lines it used and shows what it took: search in milliseconds, thinking in seconds, tokens spent.

Open Lantern

Runs in the browser, no login. Each visitor gets a handful of questions a day.

​
What to try

  • Ask the pre-indexed infino-ai/infino repo something conceptual, like why does a table need an append before it can be reopened?
  • When the benchmark bar appears, open it. The same question also ran through plain file tools (grep and read), so you can compare tool calls, tokens, and time side by side.
  • Open under the hood to see what the index actually stores: the schema, sample chunks, and the files Infino wrote on disk.
  • Paste any public GitHub repo to index it live. Large repos start answering while indexing is still in progress.

​
How Infino powers it

The agent talks to Infino through the same tool names the Infino MCP server exposes, so what you see is what any MCP-connected agent gets.
Last modified on July 7, 2026