---
title: "langwatch"
type: "tool"
slug: "langwatch-langwatch"
canonical_url: "https://www.graphcanon.com/tools/langwatch-langwatch"
github_url: "https://github.com/langwatch/langwatch"
homepage_url: "https://langwatch.ai"
stars: 3326
forks: 327
primary_language: "TypeScript"
license: "Apache-2.0"
categories: ["evaluation-observability", "llm-frameworks"]
tags: ["evaluation", "llm", "ai", "datasets", "observability", "gpt", "analytics", "prompt-engineering"]
updated_at: "2026-07-07T18:42:59.504732+00:00"
---

# langwatch

> The platform for LLM evaluations and AI agent testing

LangWatch provides tools to test, simulate, evaluate, and monitor language model-powered agents in end-to-end scenarios before release and during production. This includes features such as end-to-end agent simulations, real-time eval + observability, dataset creation, evaluation, and prompt optimization.

## Facts

- Repository: https://github.com/langwatch/langwatch
- Homepage: https://langwatch.ai
- Stars: 3,326 · Forks: 327 · Open issues: 668 · Watchers: 13
- Primary language: TypeScript
- License: Apache-2.0
- Last pushed: 2026-07-07T17:11:11+00:00

## Categories

- [Evaluation & Observability](/categories/evaluation-observability.md)
- [LLM Frameworks](/categories/llm-frameworks.md)

## Tags

evaluation, llm, ai, datasets, observability, gpt, analytics, prompt-engineering

## Related tools

- [ollama](/tools/ollama-ollama.md) - Get up and running with Kimi-K2.6, GLM-5.1, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models. (★ 175,659)
- [prompts.chat](/tools/f-prompts-chat.md) - The world's largest open-source prompt library for AI (★ 165,019)
- [transformers](/tools/huggingface-transformers.md) - 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models (★ 162,347)
- [langflow](/tools/langflow-ai-langflow.md) - Langflow is a powerful platform for building and deploying AI-powered agents and workflows. (★ 151,298)
- [open-webui](/tools/open-webui-open-webui.md) - User-friendly AI Interface (Supports Ollama, OpenAI API, ...) (★ 144,575)
- [awesome-llm-apps](/tools/shubhamsaboo-awesome-llm-apps.md) - 100+ AI Agent & RAG apps you can actually run — clone, customize, ship. (★ 116,702)
- [LLMs-from-scratch](/tools/rasbt-llms-from-scratch.md) - Implement a ChatGPT-like LLM in PyTorch from scratch (★ 98,711)
- [TradingAgents](/tools/tauricresearch-tradingagents.md) - TradingAgents: Multi-Agents LLM Financial Trading Framework (★ 91,610)

## README (excerpt)

```text
<img width="1212" height="395" alt="012d1688-24ae-4759-ae70-5f8f81a13c0e" src="https://github.com/user-attachments/assets/27b6e50e-efde-41cf-9f7c-94b829b25a8c" />


<h3 align="center">
    <a href="https://langwatch.ai">Website</a> · <a href="https://docs.langwatch.ai">Docs</a> · <a href="https://discord.gg/kT4PhDS2gH">Discord</a> · <a href="https://docs.langwatch.ai/self-hosting/overview">Self-hosting</a>
</h3>

<p align="center">
<a href="https://discord.gg/kT4PhDS2gH" target="_blank"><img src="https://img.shields.io/discord/1227886780536324106?logo=discord&labelColor=%20%235462eb&logoColor=%20%23f5f5f5&color=%20%235462eb" alt="chat on Discord"></a>
<a href="https://pypi.python.org/pypi/langwatch" target="_blank"><img src="https://img.shields.io/pypi/dm/langwatch?logo=python&logoColor=white&label=pypi%20langwatch&color=blue" alt="langwatch Python package on PyPi"></a>
<a href="https://www.npmjs.com/package/langwatch" target="_blank"><img src="https://img.shields.io/npm/dm/langwatch?logo=npm&logoColor=white&label=npm%20langwatch&color=blue" alt="langwatch npm package"></a>
<a href="https://twitter.com/intent/follow?screen_name=langwatchai" target="_blank">
   <img src="https://img.shields.io/twitter/follow/langwatchai?logo=X&color=%20%23f5f5f5"
      alt="follow on X"></a>
<img src="https://img.shields.io/badge/license-Apache%202.0%20%2B%20Enterprise-blue" alt="Open-core: Apache 2.0 floor + Enterprise extension">
</p>

<video src="https://github.com/user-attachments/assets/ff49882d-4e9d-4b7c-819b-be690fba9387" autoplay loop muted playsinline width="100%" style="display: block; aspect-ratio: 16 / 9;"></video>

## Why LangWatch?

The platform for LLM evaluations and AI agent testing.
We help teams test, simulate, evaluate, and monitor LLM-powered agents end-to-end — before release and in production.
Built for teams that need regression testing, simulations, and production observability without building custom tooling.

- [**End-to-end agent simulations**](https://langwatch.ai/scenario/)
  Run realistic scenarios against your **full stack** (tools, state, user simulator, judge) and pinpoint where your agents break, and why? down to each decision.

- **Eval + observability + prompts in one loop**
  [Trace](https://docs.langwatch.ai/integration/overview) → [dataset](https://docs.langwatch.ai/datasets/overview) → [evaluate](https://docs.langwatch.ai/llm-evaluation/offline-evaluation) → [optimize prompts/models](https://docs.langwatch.ai/optimization-studio/overview) → re-test. No glue code, no tool sprawl.

- [**Open standards, no lock-in**](https://docs.langwatch.ai/integration/opentelemetry/guide)
  OpenTelemetry/OTLP-native. Framework- and LLM-provider agnostic by design.

- [**AI Gateway for governance + cost control**](https://docs.langwatch.ai/ai-gateway/overview)
  OpenAI/Anthropic-compatible proxy with virtual keys, hierarchical budgets, inline guardrails, automatic fallback across providers, and Anthropic `cache_control` passthrough. ~700 ns hot-path overhead. Ships as a separate Go binary (`services/gateway/`) + Helm sub-chart (`charts/gateway/`).

- [**Collaboration that doesn't slow shipping**](https://docs.langwatch.ai/features/annotations)
  Review runs, annotate failures, and ship fixes faster. Let domain experts label edge cases with [annotations & queues](https://docs.langwatch.ai/features/annotations), keep prompts in Git with the [GitHub integration](https://docs.langwatch.ai/prompt-management/features/essential/github-integration), and [link prompt versions to traces](https://docs.langwatch.ai/prompt-management/features/advanced/link-to-traces).

LangWatch gives you full visibility into agent behavior and the tools to systematically improve reliability, performance, and cost, while keeping you in control of your AI system

## Getting Started

### Cloud ☁️

The easiest way to get started with LangWatch.

[Create a free account](https://app.langwatch.ai) → create a project → get started/ copy your API key.

### Lo
```

---

**Machine-readable endpoints**

- JSON: [`/api/graphcanon/tools/langwatch-langwatch`](/api/graphcanon/tools/langwatch-langwatch)
- LLM index: [/llms.txt](/llms.txt)
- Full corpus: [/llms-full.txt](/llms-full.txt)

_GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_