agentskillexchange Simulate agent scenarios, trace failures, and watch production regressions with LangWatch
Run end-to-end agent simulations, review traces, and watch production regressions when reliability work spans pre-release testing and live monitoring.
Prerequisites
LangWatch platform, your agent application traces, optional Docker for self-hosting
Installation
Use the upstream install or setup path that matches your environment:
- npx @langwatch/server
- Prefer Docker? You can still use docker compose:
- git clone https://github.com/langwatch/langwatch.git
- docker compose up -d --wait --build
Requirements and caveats from upstream:
- <img src="https://img.shields.io/pypi/dm/langwatch?logo=python&logoColor=white&label=pypi%20langwatch&color=blue" alt="langwatch Python package on PyPi"...
- The fastest way to run LangWatch locally — only Node.js required:
- Docker Compose - Run LangWatch on your own machine.
Basic usage or getting-started notes:
Run realistic scenarios against your full stack (tools, state, user simulator, judge) and pinpoint where your agents break, and why? down to each decision.
Cloud ☁️
The easiest way to get started with LangWatch.
Extracted from upstream docs: https://raw.githubusercontent.com/langwatch/langwatch/HEAD/README.md