Skip to content

Is LangSmith down?

Right now

No. LangSmith is operational.

No incidents reported.

Read from status.smith.langchain.com · every 120s

For agents

proceed

Proceed.

GET upbutler.com/status/langsmith/status.agent.json

MCP: upstream_status {"service":"langsmith"}

Tracing, evals and deployments for LangChain and LangGraph agents.

What LangSmith reports

Operational

Taken as is from LangSmith's own status page API. Incident titles and component names below are theirs.

Open status.smith.langchain.com

UpButler's independent probe

There is no keyless endpoint of LangSmith that says anything useful, so UpButler does not probe it. To check your own LangSmith account, add a monitor with your key: it is yours alone and catches what a shared probe cannot.

LangSmith incidents, last 90 days

No finished incidents on record yet. UpButler keeps what LangSmith publishes for 90 days from the day it starts tracking a service.

Tell your outage from LangSmith's

Declare that your project depends on LangSmith. When one of your monitors fails while LangSmith has an incident that began around the same time, UpButler tags your incident "likely upstream" with their incident linked, says so in the alert and the AI report, and tells your on-call agent not to change code.

npx upbutler init finds the dependency from your env var names and packages. The catalog, dependencies and upstream-aware incidents are on every plan, including Free.

upbutler.yaml
# upbutler.yaml
dependencies:
  - langsmith
Ask before you retry
curl -s https://upbutler.com/status/langsmith/status.agent.json
status.agent.json (live)
{
  "schema": "upbutler.upstream-status/v1",
  "service": "langsmith",
  "verdict": "proceed",
  "status": "operational",
  "reason": "No incidents reported",
  "retryAfterSec": null,
  "incident": null,
  "probe": null
}

Questions

Is LangSmith down right now?
No. As of 2026-10-10 05:10 UTC, LangSmith is operational. This page reads the status again every 2 minutes.
Where does this status come from?
From LangSmith's own status page API at https://status.smith.langchain.com. UpButler reads it once for everyone (not once per visitor) every 120 seconds with conditional requests, and shows it unchanged: incident titles and component names are LangSmith's words.
How can my agent or app check LangSmith status?
Fetch https://upbutler.com/status/langsmith/status.agent.json: a small JSON document with a verdict (proceed, retry, fallback or pause) and retryAfterSec. No key is needed. The same answer is an MCP tool, upstream_status {"service":"langsmith"}, on https://upbutler.com/mcp/public.
How do I know whether an outage is mine or LangSmith's?
Add "langsmith" to the dependencies of your UpButler workspace. When one of your monitors fails while LangSmith has an incident that began around the same time, your incident is tagged "likely upstream" with their incident linked, and your on-call agent is told not to change code.

More in observability and analytics

UpButler is not affiliated with LangSmith. Status and incident text belong to LangSmith and are read from their public status source; the probe result is UpButler's own measurement.