Use cron jobs

There are many situations in which it is useful to run an assistant on a schedule.

For example, say that you’re building an assistant that runs daily and sends an email summary of the day’s news. You could use a cron job to run the assistant every day at 8:00 PM.

LangSmith Deployment supports cron jobs, which run on a user-defined schedule. The user specifies a schedule, an assistant, and some input. After that, on the specified schedule, the server will:

• Create a new thread with the specified assistant
• Send the specified input to that thread

Note that this sends the same input to the thread every time.

The LangSmith Deployment API provides several endpoints for creating and managing cron jobs. See the API reference for more details.

Sometimes you don’t want to run your graph based on user interaction, but rather you would like to schedule your graph to run on a schedule - for example if you wish for your graph to compose and send out a weekly email of to-dos for your team. LangSmith Deployment allows you to do this without having to write your own script by using the Crons client. To schedule a graph job, you need to pass a cron expression to inform the client when you want to run the graph. Cron jobs are run in the background and do not interfere with normal invocations of the graph.

Setup

First, let’s set up our SDK client, assistant, and thread:

Python

from langgraph_sdk import get_client

client = get_client(url=<DEPLOYMENT_URL>)
# Using the graph deployed with the name "agent"
assistant_id = "agent"
# create thread
thread = await client.threads.create()
print(thread)

Javascript

import { Client } from "@langchain/langgraph-sdk";

const client = new Client({ apiUrl: <DEPLOYMENT_URL> });
// Using the graph deployed with the name "agent"
const assistantId = "agent";
// create thread
const thread = await client.threads.create();
console.log(thread);

CURL

curl --request POST \
    --url <DEPLOYMENT_URL>/assistants/search \
    --header 'Content-Type: application/json' \
    --data '{
        "limit": 10,
        "offset": 0
    }' | jq -c 'map(select(.config == null or .config == {})) | .[0].graph_id' && \
curl --request POST \
    --url <DEPLOYMENT_URL>/threads \
    --header 'Content-Type: application/json' \
    --data '{}'

Output:

{
'thread_id': '9dde5490-2b67-47c8-aa14-4bfec88af217',
'created_at': '2024-08-30T23:07:38.242730+00:00',
'updated_at': '2024-08-30T23:07:38.242730+00:00',
'metadata': {},
'status': 'idle',
'config': {},
'values': None
}

Cron job on a thread

To create a cron job associated with a specific thread, you can write:

Python

# This schedules a job to run at 15:27 (3:27PM) every day
cron_job = await client.crons.create_for_thread(
    thread["thread_id"],
    assistant_id,
    schedule="27 15 * * *",
    input={"messages": [{"role": "user", "content": "What time is it?"}]},
)

Javascript

// This schedules a job to run at 15:27 (3:27PM) every day
const cronJob = await client.crons.create_for_thread(
  thread["thread_id"],
  assistantId,
  {
    schedule: "27 15 * * *",
    input: { messages: [{ role: "user", content: "What time is it?" }] }
  }
);

CURL

curl --request POST \
    --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/runs/crons \
    --header 'Content-Type: application/json' \
    --data '{
        "assistant_id": <ASSISTANT_ID>,
    }'

Note that it is very important to delete Cron jobs that are no longer useful. Otherwise you could rack up unwanted API charges to the LLM! You can delete a Cron job using the following code:

Python

await client.crons.delete(cron_job["cron_id"])

Javascript

await client.crons.delete(cronJob["cron_id"]);

CURL

curl --request DELETE \
    --url <DEPLOYMENT_URL>/runs/crons/<CRON_ID>

Cron job stateless

You can also create stateless cron jobs by using the following code. Stateless cron jobs create a new thread for each execution:

Python

# This schedules a job to run at 15:27 (3:27PM) every day
cron_job_stateless = await client.crons.create(
    assistant_id,
    schedule="27 15 * * *",
    input={"messages": [{"role": "user", "content": "What time is it?"}]},
)

Javascript

// This schedules a job to run at 15:27 (3:27PM) every day
const cronJobStateless = await client.crons.create(
  assistantId,
  {
    schedule: "27 15 * * *",
    input: { messages: [{ role: "user", content: "What time is it?" }] }
  }
);

CURL

curl --request POST \
    --url <DEPLOYMENT_URL>/runs/crons \
    --header 'Content-Type: application/json' \
    --data '{
        "assistant_id": <ASSISTANT_ID>,
    }'

Again, remember to delete your job once you are done with it!

Python

await client.crons.delete(cron_job_stateless["cron_id"])

Javascript

await client.crons.delete(cronJobStateless["cron_id"]);

CURL

curl --request DELETE \
    --url <DEPLOYMENT_URL>/runs/crons/<CRON_ID>

Thread cleanup for stateless crons

This feature requires LangGraph API version 0.5.18 or later and Python SDK 0.3.2 or later, or JavaScript SDK 1.4.0 or later.

Every time a stateless cron is triggered, a new thread is created. Control what happens to that thread after the run completes using the on_run_completed parameter:

• "delete" (default): Automatically deletes the thread after the run completes.
• "keep": Preserves the thread for later retrieval. You are responsible for cleaning up these threads. See how to add TTLs to your application for the recommended approach.

Example: Keeping threads for later retrieval

Python

# Create a stateless cron that keeps threads after execution.
# Configure checkpointer.ttl in langgraph.json to auto-delete old threads.
# See: https://docs.langchain.com/langsmith/configure-ttl
cron_job = await client.crons.create(
    assistant_id,
    schedule="27 15 * * *",
    input={"messages": [{"role": "user", "content": "Daily report"}]},
    on_run_completed="keep"
)

# You can later retrieve the runs and their results
runs = await client.runs.search(
    metadata={"cron_id": cron_job["cron_id"]}
)

Javascript

// Create a stateless cron that keeps threads after execution.
// Configure checkpointer.ttl in langgraph.json to auto-delete old threads.
// See: https://docs.langchain.com/langsmith/configure-ttl
const cronJob = await client.crons.create(
  assistantId,
  {
    schedule: "27 15 * * *",
    input: { messages: [{ role: "user", content: "Daily report" }] },
    onRunCompleted: "keep"
  }
);

// You can later retrieve the runs and their results
const runs = await client.runs.search({
  metadata: { cron_id: cronJob["cron_id"] }
});

CURL

# Create a stateless cron that keeps threads after execution.
# Configure checkpointer.ttl in langgraph.json to auto-delete old threads.
# See: https://docs.langchain.com/langsmith/configure-ttl
curl --request POST \
    --url <DEPLOYMENT_URL>/runs/crons \
    --header 'Content-Type: application/json' \
    --data '{
        "assistant_id": "<ASSISTANT_ID>",
        "schedule": "27 15 * * *",
        "input": {"messages": [{"role": "user", "content": "Daily report"}]},
        "on_run_completed": "keep"
    }'

---

Edit this page on GitHub or file an issue.

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