What it does
LangWatch is a platform for teams running AI in their products or workplace. It records every request sent to an AI model, so teams can see what happened, how much it cost and where things went wrong.
It can run simulated tests to check how well an AI agent (a program that carries out tasks on its own) behaves, including voice agents. It also helps manage prompts, the written instructions given to AI models.
Other parts include a single gateway for sending requests to AI providers like OpenAI and Anthropic, with spending budgets and shared keys, plus a view of which AI tools people in the company actually use. You can use the hosted cloud version or run it on your own machine.
Who it's for
Engineering and platform teams who build AI agents or manage AI tools like Claude Code and Copilot across a company.
Can I use it without coding?
With some setup. You can sign up for the hosted version, or self-host it with a single command if Node.js is installed. New to this? Start here.
Can I run it?
- Cost
- Free, with optional paid extrasThe open-source version is free; the makers also sell a hosted or pro version.
- Runs on
- Mac, Linux, Cloud, Server
- Privacy
- Your choice: run it on your device or use an online service
Try it
- Sign up for LangWatch Cloud on the project's website, or install Node.js 24 or newer to host it yourself.
- Start the self-hosted server using the command shown in the README.
- Connect your coding assistant or AI app using the integration guides in the docs.
Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?
Before you install
- Only download from the official GitHub page. Copies with similar names exist for many popular projects.
- Plain-AyI is an independent guide and doesn't host or review the software it lists. Please check each project's official page before installing.
- License (Apache-2.0): Permissive: free to use, change and share, including for business.
- More on staying safe