Deploy LangSmith with Terraform

Provision LangSmith self-hosted on AWS, Azure, or GCP using LangChain’s production-ready Terraform modules.

Self-hosted LangSmith is an add-on to the Enterprise plan designed for LangChain’s largest, most security-conscious customers. See pricing for details, or contact sales to request a license key for trial.

LangChain publishes production-ready Terraform modules for LangSmith self-hosted at github.com/langchain-ai/terraform. The modules provision the cloud foundation (network, cluster, database, cache, object storage, secrets, DNS) and install the LangSmith Helm chart with sensible defaults.

Use this path when you want infrastructure as code from day one. If you already manage cloud infrastructure with your own tooling and need just the application install, follow the Helm installation guide instead.

Prefer Helm? The Kubernetes setup guide walks through installing with Helm against any conformant cluster, no Terraform required. The Terraform path bundles cluster provisioning, secrets wiring, and the Helm release into one workflow.

Choose a provider

AWS (EKS)

Provision EKS, RDS PostgreSQL, ElastiCache, S3, and networking.

Azure (AKS)

Provision AKS, Azure Database for PostgreSQL, Azure Managed Redis, Blob Storage, and Key Vault.

GCP (GKE)

Provision GKE, Cloud SQL, Memorystore, GCS, and Workload Identity.

Prerequisites

Install the following tools before running the modules:

Tool	Version	Purpose
terraform	1.5	Run the modules
kubectl	1.28	Inspect the cluster after provisioning
helm	3.12	Manage the LangSmith chart release
Cloud CLI	latest	aws, az, or gcloud for the target provider

You also need:

• A LangSmith license key. Contact sales to request one.
• Permissions in the target cloud account to create VPC or VNet networking, a managed Kubernetes cluster, managed databases, object storage, secrets, and IAM roles.
• A registered domain (or subdomain) for the LangSmith UI endpoint.

Deployment tiers

Pick a tier with a single Terraform variable. The modules size every dependent resource accordingly.

Tier	PostgreSQL	Redis	ClickHouse	Use case
dev	In-cluster	In-cluster	In-cluster	Demos, evaluations, short-lived POCs
production	Cloud-managed (RDS, Cloud SQL, Azure Database)	Cloud-managed (ElastiCache, Memorystore, Azure Cache)	LangChain Managed ClickHouse	Persistent, scalable production
production-large	Cloud-managed, larger instance class	Cloud-managed, larger instance class	LangChain Managed ClickHouse	High-throughput production

Use in-cluster ClickHouse for development and POC, not production. Production deployments must use LangChain Managed ClickHouse or a self-managed external ClickHouse cluster. Blob storage is always required because trace payloads must not live in ClickHouse.

What the modules provision

• Networking: VPC or VNet with public and private subnets, NAT, and security groups.
• Compute: Managed Kubernetes (EKS, AKS, or GKE) with autoscaling node pools sized per tier.
• Data plane: Managed PostgreSQL, managed Redis or cache, and a blob storage bucket for trace payloads.
• Secrets: Cloud-native secret store (AWS SSM Parameter Store, Azure Key Vault, GCP Secret Manager) synced into Kubernetes by External Secrets Operator.
• Ingress: Cloud-native load balancer by default. Envoy Gateway (Gateway API) is available for multi-namespace dataplane deployments.
• Optional hardening (AWS today): AWS Network Firewall with FQDN egress allowlists, WAFv2, CloudTrail, and a private EKS API endpoint with SSM bastion access.

Enterprise feature toggles

Each module exposes flags for the optional LangSmith add-ons:

• LangSmith Deployment (Agent Server and Fleet)
• Agent Builder
• Insights (ClickHouse-backed analytics)
• Polly (AI evaluation and monitoring)

Toggle each feature in the tfvars file before running make apply.

Need a tailored package?

Enterprise customers can request a tailored Terraform package from their LangChain Solutions Architect. The tailored package adds account-specific defaults, customer-managed key wiring, and any custom hardening agreed during the engagement. The public modules linked above are the same source of truth, so a tailored package stays compatible with the upstream module structure.

Next steps

• Pick a provider above and follow the deployment guide.
• Review required dependency versions for PostgreSQL, ClickHouse, Redis, and Kubernetes.
• Plan capacity with the scaling guide.
• After the application is running, enable LangSmith Deployment to add agent deployment and management to the UI.

---

Connect these docs to Claude, VSCode, and more via MCP for real-time answers.

Edit this page on GitHub or file an issue.