# LangWatch

LangWatch is the LLM engineering platform for teams shipping AI to production:
agent simulation testing, evaluations, observability, prompt management, and
governance. Open source and OpenTelemetry-native.

This file is a curated map for LLMs and AI agents exploring the site. For the
full documentation, follow the links to docs.langwatch.ai (use the `.md` suffix
on any doc URL for the markdown source).


# Platform

- [Home](https://langwatch.ai/): What LangWatch is and the problems it solves.
- [LLM observability](https://langwatch.ai/llm-observability): OpenTelemetry-native traces, monitors, and analytics.
- [LLM evaluation](https://langwatch.ai/llm-evaluation): Offline and online evals, custom evaluators, datasets.
- [Agent simulation testing](https://langwatch.ai/agentic-ai-testing): Scenario-based testing for multi-turn agents.
- [Customers](https://langwatch.ai/customers): Case studies from AI teams shipping with LangWatch.


# Pricing and trust

- [Pricing](https://langwatch.ai/pricing): Free tier, team, and enterprise plans.
- [Trust center](https://langwatch.ai/trust-center): Security and compliance posture.
- [Get a demo](https://langwatch.ai/get-a-demo): Book a walkthrough with the team.


# Switch from other platforms

- [Switch from Langfuse](https://langwatch.ai/langfuse-alternative): How LangWatch compares to Langfuse.
- [Switch from Braintrust](https://langwatch.ai/braintrust-alternative): How LangWatch compares to Braintrust.
- [Switch from LangSmith](https://langwatch.ai/langsmith-alternative): How LangWatch compares to LangSmith.
- [Switch from Arize](https://langwatch.ai/arize-alternative): How LangWatch compares to Arize.
- [Switch from Humanloop](https://langwatch.ai/humanloop-alternative): How LangWatch compares to Humanloop.
- [Feature comparison](https://langwatch.ai/comparison): Side-by-side feature comparison across major platforms.


# Better Agents Manifesto

- [Better Agents Manifesto](https://langwatch.ai/better-agents-manifesto): The four values that guide how we build agents.
- [Better Agents CLI](https://github.com/langwatch/better-agents): The companion CLI on GitHub.


# Developer resources

- [SDKs](https://langwatch.ai/sdks): Python and TypeScript SDKs, plus integrations.
- [Evals training for your team](https://langwatch.ai/evals-training): Guided curriculum for evaluating agents.
- [Documentation](https://docs.langwatch.ai/introduction): Full LangWatch docs (Mintlify, follow `.md` for markdown source).
- [Quickstart](https://docs.langwatch.ai/integration/quick-start): Five-minute setup.
- [Python guide](https://docs.langwatch.ai/integration/python/guide): Python SDK guide.
- [TypeScript guide](https://docs.langwatch.ai/integration/typescript/guide): TypeScript SDK guide.
- [Blog](https://langwatch.ai/blog): Engineering posts and product updates.


# Open source

- [LangWatch on GitHub](https://github.com/langwatch/langwatch): The platform repo, Apache 2.0.
- [Scenario](https://github.com/langwatch/scenario): The agent simulation framework.
- [Self-hosting](https://docs.langwatch.ai/self-hosting/overview): Docker and Helm deployment.


# Contact

- Contact: contact@langwatch.ai
- Status: https://status.langwatch.ai/