OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Evaluation & Observability

Langwatch

LangWatch is an open-source platform for observing and testing LLMs and AI agents, tracking coding assistants, routing model calls, and supporting AI governance.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Langwatch — OpenViST project profile in Agent Evaluation & Observability.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use LangWatch when a team needs agent observability or evaluation, coding-assistant tracking, model-call routing, or governance workflows across AI tools.

Who it is for

  • AI platform teams that need visibility into LLM calls and agent activity.
  • Developers testing or evaluating agents, including voice agents.
  • Engineering teams monitoring coding-assistant sessions and related costs.
  • Organizations managing model routing, budgets or information about AI-tool use.

Documented uses

  • Trace and inspect LLM or agent activity in production.
  • Create simulation tests and evaluation workflows for agents.
  • Track coding-assistant sessions and costs by pull request or team.
  • Route model calls through an OpenAI- and Anthropic-compatible gateway with virtual keys and budgets.
  • Collect information from documented sources to support AI governance.
Before you choose

Requirements & limits

The project documents a hosted LangWatch Cloud option and self-hosting. The repository describes the project as open source under Apache 2.0.

  • The platform spans observability, agent testing, coding-agent tracking, AI gateway and governance; teams can assess which areas match their workflow.
  • The repository documents self-hosting with Node.js and a separate production self-hosting guide.
  • Listed integrations cover multiple agent frameworks, model providers, coding assistants and governance data sources.
  • The repository identifies TypeScript as the primary language and Apache 2.0 as the license.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install LangWatch on Kubernetes with Helm

Deploy the LangWatch platform to a Kubernetes cluster using the documented Helm quick start.

Before you start

  • A Kubernetes cluster
  • Helm

Steps

  1. Add the LangWatch chart repository: helm repo add langwatch https://langwatch.github.io/langwatch.

  2. Update repositories and pull the chart: helm repo update and helm pull langwatch/langwatch --untar.

  3. Install the chart with the development-size overlay and wait for completion: helm install langwatch ./langwatch --namespace langwatch --create-namespace --set autogen.enabled=true -f langwatch/examples/overlays/size-dev.yaml --wait --timeout 10m.

  4. Forward the app service to access the UI: kubectl -n langwatch port-forward svc/langwatch-app 5560:5560. Before relying on the deployment, replace auto-generated secrets with real ones, following the Kubernetes (Helm) setup instructions.

Expected outcome

The LangWatch stack is installed in the cluster, and the UI service is reachable through the documented port-forward.

Guide limitations

  • The quick-start configuration requests roughly 2.8 CPU and 6.9 Gi of resources.
  • Auto-generated secrets change on every reinstall; replace them before relying on the deployment.
  • The local Kubernetes overlay is not suitable for a general cluster: its local image tags and pullPolicy: Never require a Kind cluster populated with images using make images-local.
  • This quick start does not provide the full production setup; consult the Kubernetes (Helm) instructions for that.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Model inference and serving

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
LangwatchTrace and inspect LLM or agent activity in production.CLI, Self-hosted, Server, WebThe project documents a hosted LangWatch Cloud option and self-hosting. The repository describes the project as open source under Apache 2.0.
AgentOpsTrace LLM calls, tool use and interactions among agents.Web
Evidence and transparency

Sources & review

Official repository ↗Guide documentation ↗
Source record details
Source availability
Active
Sources checked
7 October 2026
Original website title
langwatch/langwatch · Official homepage title · retained in its source language
How we review sourcesSuggest a correction