LangWatch

license

Apache-2.0(core)+MIT(SDKs)

source

public

core features withheld

yes — NOTICE and platform/app/ee/LICENSE.md put platform/app/ee under the LangWatch Enterprise License, covering single sign-on, SCIM provisioning, audit logging, gateway webhooks, licensing, billing and back-office tooling, each of which "verifies a license at runtime before it can be used"

LangWatch's core platform is Apache-2.0 and its SDKs are MIT, but the platform/app/ee directory, covering single sign-on, SCIM, audit logging and billing, is licensed separately under the LangWatch Enterprise License and checks that license at runtime. That gated directory is what makes this open core rather than fully open source.

• https://github.com/langwatch/langwatch recorded 2026-06-04

  Apache-2.0 core, MIT SDKs, langwatch/ee/ enterprise modules requiring commercial license

• https://raw.githubusercontent.com/langwatch/langwatch/main/NOTICE recorded 2026-09-29

  The vendor NOTICE states the license split: "This product is licensed under the Apache License, Version 2.0" with "platform/app/ee/ LangWatch Enterprise License" and MIT for "sdks/python/" and "sdks/typescript/".

• https://raw.githubusercontent.com/langwatch/langwatch/main/platform/app/ee/LICENSE.md recorded 2026-09-29

  The enterprise license says "each verifies a license at runtime before it can be used" and that "Enabling or using an enterprise capability in production requires a valid LangWatch Enterprise License".

• https://raw.githubusercontent.com/langwatch/langwatch/main/README.md recorded 2026-09-29

  The README calls LangWatch "the open-source platform for AI in production", says "LangWatch is Apache 2.0." and that "The enterprise modules under" platform/app/ee/ "need a commercial license in production, and the SDKs are MIT."

• https://raw.githubusercontent.com/langwatch/langwatch/main/sdks/python/LICENSE recorded 2026-09-29

  The Python SDK license file grants use of the software "free of charge, to any person obtaining a copy of this software" and "to deal in the Software without restriction", the MIT terms.

LangWatch publishes no download or active-user figure, leaving GitHub stars on its one declared repository as the only available adoption signal. A star count cannot carry a product very high, because a star is not a use.

• https://api.github.com/repos/langwatch/langwatch recorded 2026-08-13

  stargazers_count = 3486 for langwatch/langwatch. No download, install, customer or user figure is published for this product anywhere the record cites, so stars remain the only signal.

• https://github.com/langwatch/langwatch recorded 2026-06-04

  ~3.3k GitHub stars; no disclosed usage numbers

LangWatch covers OpenTelemetry-native tracing, offline experiments and online production monitoring, versioned prompt management, dataset creation and annotation, and a built-in AI gateway with virtual keys and budgets, plus distinctive agent simulation against a simulated user. That matches Langfuse's feature set without going beyond it.

• https://github.com/langwatch/langwatch recorded 2026-08-13

  README - "The platform for LLM evaluations and AI agent testing. We help teams test, simulate, evaluate, and monitor LLM-powered agents end-to-end", with headline sections for "End-to-end agent simulations" ("Run realistic scenarios against your full stack") and "Eval + observability + prompts in one loop".

• https://langwatch.ai/docs/ai-gateway/overview recorded 2026-09-29

  AI Gateway overview: "One OpenAI- and Anthropic-compatible endpoint for every LLM call in your company, with provider keys kept in LangWatch, a virtual key per application, team or person, budgets that block or warn, and a trace for every request."

• https://langwatch.ai/docs/integration/opentelemetry/guide recorded 2026-09-29

  OpenTelemetry guide: "LangWatch provides a standard OpenTelemetry Protocol (OTLP) endpoint for receiving traces:" and "LangWatch works with any OpenTelemetry-compatible instrumentation library."

• https://langwatch.ai/docs/introduction recorded 2026-09-29

  Docs introduction: "Tracing, evaluations, agent testing, prompt management and more", "experiments on datasets, and monitors on production traffic.", "multi-turn conversations against your agent with a simulated user." and "versioned prompts your code loads at runtime."; navigation lists AI Gateway, Annotations, Datasets and Online Evaluation.

• https://langwatch.ai/docs/prompt-management/overview recorded 2026-09-29

  Prompt management overview: "LangWatch’s prompt management system helps you organize, version, and optimize your AI prompts across your application."