What did you do with Claude?

Open your Claude Code history, or try the sample. Everything stays in your browser.

Runs in your browser. Nothing is uploaded.

Open your Claude Code history and see your rhythm, what you built, the tools and skills you leaned on, what it cost and how well it ran. Built on a data catalog of every number a Claude usage dashboard can show.

Drop your projects folder here

Claude Code keeps one file per session in ~/.claude/projects. Drop the folder, or pick it.

The folder is hidden. In the picker, press ⌘ ⇧ . on a Mac or Ctrl H on Linux to show it.

01

Me

Active days, streaks, a weekday × hour heatmap, projects, languages, commits, edit acceptance, tools, skills, models, tokens and cost.

02

Capabilities

Every skill with its plugin, every MCP server down to each tool, every built-in tool, subagent and slash command, with how often and how well.

03

Team

Weekly active people against seats, stickiness, retention cohorts, depth of use and adoption by team, with groups under five people hidden.

04

Telemetry

Turn duration p50 and p95, API errors, tool success, permission decisions, connector health, compactions and agent runs.

05

Catalog

Every metric with its definition, source and chart, the unified event schema, and the Claude Code OpenTelemetry names.

Reads Claude Code transcripts (.jsonl) and events in the catalog's unified schema (.jsonl or .json). Prompt and response text is never read into the dashboard; session titles stay on your screen.

Export

Everything is written in your browser. Events use the unified schema, so a team lead can load everyone's files together for the Team view.

Used for events loaded from Claude Code, which carry no person or team. Never your email or name.