Skip to main content
Run your agent through the LangWatch wrapper. This will open LangWatch for you to sign in, then start your agent with all telemetry already set up, tracking your token cost per PR, cache hit ratio, and much more.
Each agent’s page covers the first-run setup in full, for example Claude Code.

​
What you see now

Work with the agent for a minute, then open /me:
Sessions list

The sessions list on /me. Each row is one session, with its cost, the context it carried, and the pull requests it created.

  • Your session is on the sessions list, with its cost, the context it carried, and a terminal replay of the conversation.
  • Your spend for the month is on the usage cards. See Usage analytics.
  • Once the session works on a branch with a pull request, it shows under Pull requests.

​
Expand from here

  • Run plain commands with reporting on. langwatch instrument <tool> writes the connection and exits, so claude without the wrapper reports too. Each agent’s page covers it, for example Claude Code.
  • Send a machine to a team project with --project, or wire servers and CI with no login. See Team projects and Headless machines and CI.
  • Route the model calls through the LangWatch AI Gateway for budgets, model policies and provider fallback. See the coding CLI gateway integrations.
  • Control what gets stored. Privacy states who can read your sessions, and you can drop the conversation content while keeping the cost and token counts.
Last modified on August 27, 2026