Skip to main content

Getting started

Each npx langwatch command 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. Cursor has no wrapper command: point it at the LangWatch AI Gateway as above, and its telemetry comes from the gateway. Check out the quickstart for next steps.

Set up your agent

Claude Code

One command, or CLAUDE_CODE_ENABLE_TELEMETRY and the OpenTelemetry variables by hand.

Codex

Sessions, cost and traces from the OpenAI Codex CLI.

GitHub Copilot

Usage and cost from the Copilot CLI and Copilot Chat.

Gemini CLI

Sessions, cost and traces from the Gemini CLI.

OpenCode

Sessions, cost and traces from opencode.

Grok CLI

Sessions, cost and prompts from xAI’s Grok CLI.

pi

Sessions, cost and traces from the pi coding agent.

Cursor and Aider

Through the LangWatch AI Gateway: point their OpenAI base URL at https://gateway.langwatch.ai/v1 with a virtual key.

See your usage

Sessions

Context carried, compactions, cost, and a terminal replay of the whole conversation.

Pull requests

What each change cost, across every session and contributor.

Usage analytics

Spend and activity on your personal page, the CLI and the API.

Repository and PR attribution

How sessions get joined to repositories, branches and pull requests.

Teams, fleets and privacy

Team projects

Point agents at a shared project.

Headless machines and CI

Servers, build agents and fleets, with no login.

Privacy

Where your data lands and who can read it, stated exactly.

Secrets redaction

Credentials become a typed marker before storage. On by default.

Investigate with your agent

Explore your usage

Your agent answers “where did my tokens go”.

Find your context sweet spot

Where fat context stops paying for itself.

Compare provider costs

Price your real usage mix against other providers.
Last modified on November 4, 2026