Apps

Explore TV series episode ratings with interactive charts

Model pricing table from the @armand-dev/llm registry

Parse a shell command into the agent-shell-subset IR — or see exactly why it's refused

Estimate a benchmark run's cost across models, with token-size sensitivity charts

Render markdown carried in the URL fragment — fully client-side

Visualize ChatReqV1 LLM trace files

LLM benchmark results

Start/stop time tracking with labels, calendar view, and JSON export

Put a model through a suite of capability tests; inspect traces, results, and notes per run

Randomly redirects to an AI chat platform