devtools

Test AI with Langwatch

Evaluate LLMs and AI agents with Langwatch, a platform for founders working with AI technologies, backed by 3.3k+ GitHub stars

From the repo · “Open-Source Agent Observability & Evals for AI Platform teams. Trace, test, route and govern every agent & coding assistant in the company.”

4,988 stars+35★ this week417 forksTypeScriptGuide quality 9/10 · reviewed Jul 3Updated 10/22/2026100% free · open source
What it does

Langwatch evaluates and tests Large Language Models (LLMs) and AI agents to help founders assess their performance and capabilities.

When to use it
  • •When selecting an LLM for a specific task or project
  • •When comparing the performance of different LLMs or AI agents
  • •When testing and fine-tuning LLMs or AI agents for a particular use case
Ready-to-paste prompt
langwatch --llm gpt-3 --task text-classification --dataset my-dataset.json
Heads up: Langwatch requires a GitHub personal access token to fetch LLM models, which must be stored in a .env file at the root of the project
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/langwatch && curl -fsSL https://workflowstacks.com/api/skills/langwatch/claude-skill -o ~/.claude/skills/langwatch/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How Test AI with Langwatch works
Codeflow
Free to inspect

Test AI with Langwatch is a very large TypeScript project (~2M lines across 13180 code files, plus 5429 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, Apache-2.0 license, has a test suite.

Size
Very large codebase
~2M lines · 13180 code files · days to read — use, don't read
Setup
Developer setup
A real software project. Use it via its install path; don't expect to read it all.
Runs on
Node.js
No API keys detected
TypeScript 80%Gherkin 9%Go 7%Python 2%Jupyter Notebook 1%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    CLAUDE.md
    The instructions the AI actually follows
  3. 3
    cmd/haven/main.go
    Where the program starts running
  4. 4
    go.mod
    Dependencies and the commands it exposes
  5. 5
    skills/README.md
    Inside skills/ — an example of what the AI is told to do
What's in each folder
skills/Prompts, skills & agent definitions142 files
pkg/Core code — the actual logic119 files
services/Backend / API811 files
packages/Sub-packages / plugins493 files
plugins/Sub-packages / plugins16 files
cmd/Command-line entry points8 files
docs/Documentation1459 files
platform/Folder11538 files
READMEHas testsDocumentedCI checksApache-2.0 licenseUpdated this month
Quick Actions
Details
Creator
langwatch
Language
TypeScript
Category
devtools
Published
9/9/2023

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/langwatch.svg)](https://workflowstacks.com/skills/langwatch?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.