paper

Instead of treating each agent run as a temporary terminal interaction, paper records the session as structured data: prompts, turns, tool calls, token usage, cost, duration, status, and metadata.

paper CLI captures the work as it happens locally. paper console turns that captured work into durable session history your team can view, search, inspect, and learn from over time.

How paper works

paper sits between supported agents and model providers so agent sessions can be captured as structured history.

1. Run an agent through the paper CLI.
2. The paper CLI captures the session as structured data.
3. The session is saved to paper console.
4. Your team can inspect session history and learn from agent work across runs.

Start here

Which docs should I use?

• Use the quickstart if you want to capture your first session.
• Use the paper CLI docs if you need to install paper, authenticate, check the daemon, run supported agents, or troubleshoot local capture.
• Use the paper console docs if you want to understand captured sessions, search session history, review team activity, or inspect usage and cost.

Going further

Once you’re capturing sessions, these are the next steps from everyday use to getting the most out of paper:

• Custom backends — customize routing, set model allowlists, or share one team-managed key.
• Skills — turn a captured session into a reusable skill your team can apply again.
• Team workspace — switch orgs and gateways, filter the team’s sessions, and read the aggregate dashboard.