Get started | Scenarios | Instrument with MCP | Documentation
Welcome to LangWatch, an open-source platform for building and shipping reliable LLM-powered agents.
LangWatch combines observability, evaluation, and scenario-based testing to help teams understand agent behavior across real workflows — from production traces to simulated failures.
It empowers domain experts to review and score conversations, developers to debug and evaluate agents end-to-end, and business teams to track quality, usage, and cost with custom analytics.
lwp_og.webm
You can sign up and already start the integration on our free tier by following the guides bellow:
Ship safer agents in minutes. Create a free account, then dive into these guides:
- Run your first agent simulation - Test agents against realistic scenarios before production
- Set up evaluations - Measure quality, performance, and reliability
- Send your first traces - Integrate LangWatch with your stack
- Get started with LangWatch MCP - Use LangWatch in Claude Desktop and other MCP clients
-
LangWatch The core open-source platform for observing, evaluating, and testing LLM-powered agents.
-
Scenarios End-to-end simulations for multi-step, tool-using agents across real workflows.
-
Better Agents A standard and tooling ecosystem for building production-grade AI agents.
-
Docs Source for LangWatch documentation.
Open-source is at the heart of LangWatch. We welcome issues, pull requests, and discussions of new ideas.
Please read our Contribution Guidelines for details on our code of conduct and contribution process.
Need help or want to get involved?