Langchain on AI Knowledge Base

A2A endpoint in Agent Server

Mon, 01 Jan 0001 00:00:00 +0000

A2A JSON-RPC

Mon, 01 Jan 0001 00:00:00 +0000

Communicate with an assistant using the Agent-to-Agent (A2A) Protocol over JSON-RPC 2.0.

Access & oversight

Mon, 01 Jan 0001 00:00:00 +0000

Control who can access agents, how they authenticate, and audit everything they do.

Access the current run (span) within a traced function

Mon, 01 Jan 0001 00:00:00 +0000

Add custom authentication

Mon, 01 Jan 0001 00:00:00 +0000

Add encryption at-rest

Mon, 01 Jan 0001 00:00:00 +0000

Add metadata and tags to traces

Mon, 01 Jan 0001 00:00:00 +0000

Agent Builder webhooks

Mon, 01 Jan 0001 00:00:00 +0000

Integrate agent publishing with external systems, CI/CD pipelines, or custom deployment workflows.

Agent Chat UI

Mon, 01 Jan 0001 00:00:00 +0000

Agent Chat UI

Mon, 01 Jan 0001 00:00:00 +0000

Agent Chat UI

Mon, 01 Jan 0001 00:00:00 +0000

Agent Chat UI

Mon, 01 Jan 0001 00:00:00 +0000

Agent Client Protocol (ACP)

Mon, 01 Jan 0001 00:00:00 +0000

Expose Deep Agents over the Agent Client Protocol (ACP) to integrate with code editors and IDEs.

Agent Client Protocol (ACP)

Mon, 01 Jan 0001 00:00:00 +0000

Expose Deep Agents over the Agent Client Protocol (ACP) to integrate with code editors and IDEs.

Agent identity

Mon, 01 Jan 0001 00:00:00 +0000

Choose whether your Fleet agent authenticates with its own credentials or with each user’s credentials.

Agent Server

Mon, 01 Jan 0001 00:00:00 +0000

Agent Server API reference for LangSmith Deployment

Mon, 01 Jan 0001 00:00:00 +0000

Agent Server changelog

Mon, 01 Jan 0001 00:00:00 +0000

agent-server-openapi

Mon, 01 Jan 0001 00:00:00 +0000

Agents

Mon, 01 Jan 0001 00:00:00 +0000

Agents

Mon, 01 Jan 0001 00:00:00 +0000

Alerts in LangSmith

Mon, 01 Jan 0001 00:00:00 +0000

Analyze an experiment

Mon, 01 Jan 0001 00:00:00 +0000

Annotate traces and runs inline

Mon, 01 Jan 0001 00:00:00 +0000

API Documentation

Mon, 01 Jan 0001 00:00:00 +0000

A local reference to the Agent Server API documentation.

App development in LangSmith Deployment

Mon, 01 Jan 0001 00:00:00 +0000

Application structure

Mon, 01 Jan 0001 00:00:00 +0000

Application structure

Mon, 01 Jan 0001 00:00:00 +0000

Application structure

Mon, 01 Jan 0001 00:00:00 +0000

Application-specific evaluation approaches

Mon, 01 Jan 0001 00:00:00 +0000

Assistants

Mon, 01 Jan 0001 00:00:00 +0000

Async subagents

Mon, 01 Jan 0001 00:00:00 +0000

Launch background subagents that run concurrently while the supervisor continues interacting with the user

Async subagents

Mon, 01 Jan 0001 00:00:00 +0000

Launch background subagents that run concurrently while the supervisor continues interacting with the user

Attribute-based access control

Mon, 01 Jan 0001 00:00:00 +0000

Audit logs

Mon, 01 Jan 0001 00:00:00 +0000

Track and review administrative actions across your LangSmith organization for security, compliance, and operational visibility.

Auth-aware tool responses

Mon, 01 Jan 0001 00:00:00 +0000

Format tool responses to trigger OAuth flows and resume execution automatically.

Auth-aware tool responses

Mon, 01 Jan 0001 00:00:00 +0000

Format tool responses to trigger OAuth flows and resume execution automatically.

Authentication & access control

Mon, 01 Jan 0001 00:00:00 +0000

Authentication methods

Mon, 01 Jan 0001 00:00:00 +0000

Automatically run evaluators on experiments

Mon, 01 Jan 0001 00:00:00 +0000

Backends

Mon, 01 Jan 0001 00:00:00 +0000

Choose and configure filesystem backends for deep agents. You can specify routes to different backends, implement virtual filesystems, and enforce policies.

Backends

Mon, 01 Jan 0001 00:00:00 +0000

Choose and configure filesystem backends for deep agents. You can specify routes to different backends, implement virtual filesystems, and enforce policies.

Basic authentication with email and password

Mon, 01 Jan 0001 00:00:00 +0000

Branching chat

Mon, 01 Jan 0001 00:00:00 +0000

Edit messages, regenerate responses, and navigate conversation branches

Branching chat

Mon, 01 Jan 0001 00:00:00 +0000

Edit messages, regenerate responses, and navigate conversation branches

Build a content builder agent

Mon, 01 Jan 0001 00:00:00 +0000

Build a content writing agent with brand memory, skills, subagents, and image generation

Build a content builder agent

Mon, 01 Jan 0001 00:00:00 +0000

Build a content writing agent with brand memory, skills, subagents, and image generation

Build a custom RAG agent with LangGraph

Mon, 01 Jan 0001 00:00:00 +0000

Build a custom RAG agent with LangGraph

Mon, 01 Jan 0001 00:00:00 +0000

This guide shows how to build a RAG pipeline where the agent decides when and how to retrieve documents, rather than always retrieving on every query. Focus on the routing logic that lets the agent skip retrieval for questions it can answer directly — this is the key difference between naive RAG and agentic RAG. Compare this approach with Pinecone’s retrieval patterns and Cohere’s reranking strategies to see how different parts of the RAG stack complement each other. A common pitfall is over-retrieving: adding too many retrieval nodes or fetching too many documents degrades both latency and answer quality, so tune your retrieval thresholds carefully.

Build a custom SQL agent

Mon, 01 Jan 0001 00:00:00 +0000

Build a data analysis agent

Mon, 01 Jan 0001 00:00:00 +0000

Build an agent that analyzes data files, generates visualizations, and shares results

Build a deep research agent

Mon, 01 Jan 0001 00:00:00 +0000

Build a multi-step web research agent with subagent delegation

Build a deep research agent

Mon, 01 Jan 0001 00:00:00 +0000

Build a multi-step web research agent with subagent delegation

Build a multi-source knowledge base with routing

Mon, 01 Jan 0001 00:00:00 +0000

Build a multi-source knowledge base with routing

Mon, 01 Jan 0001 00:00:00 +0000

This guide demonstrates a router pattern where a top-level agent dispatches queries to specialized sub-agents based on the knowledge domain, which is one of the most practical multi-agent architectures for production systems. The routing mechanism avoids the cost and latency of sending every query to every knowledge source by using an LLM to classify intent first. Focus on how the router prompt is structured and how fallback behavior works when no sub-agent matches, as these are the failure modes you will encounter most in real deployments. Compare this approach with CrewAI’s delegation model and LangGraph’s conditional edges to understand the tradeoffs between explicit routing and emergent coordination.

Build a personal assistant with subagents

Mon, 01 Jan 0001 00:00:00 +0000

Build a personal assistant with subagents

Mon, 01 Jan 0001 00:00:00 +0000

Build a RAG agent with LangChain

Mon, 01 Jan 0001 00:00:00 +0000

Build a RAG agent with LangChain

Mon, 01 Jan 0001 00:00:00 +0000

This guide assembles LangChain’s retrieval primitives into a complete RAG agent capable of querying external knowledge and synthesizing answers with citations. The key architectural decision covered here is when to use a simple retrieval chain versus a full agentic RAG loop where the model decides whether and how to retrieve. Pay attention to the prompt engineering patterns for grounding LLM responses in retrieved context, as poorly constructed prompts are the primary cause of hallucination in RAG systems. Read the retrieval guide first for the underlying abstractions, then use this guide to see how they combine in a production-oriented pattern.

Build a semantic search engine with LangChain

Mon, 01 Jan 0001 00:00:00 +0000

Build a semantic search engine with LangChain

Mon, 01 Jan 0001 00:00:00 +0000

Build a SQL agent

Mon, 01 Jan 0001 00:00:00 +0000

Build a SQL agent

Mon, 01 Jan 0001 00:00:00 +0000

Build a SQL assistant with on-demand skills

Mon, 01 Jan 0001 00:00:00 +0000

Build a SQL assistant with on-demand skills

Mon, 01 Jan 0001 00:00:00 +0000

Build a voice agent with LangChain

Mon, 01 Jan 0001 00:00:00 +0000

Build a voice agent with LangChain

Mon, 01 Jan 0001 00:00:00 +0000

Build customer support with handoffs

Mon, 01 Jan 0001 00:00:00 +0000

Build customer support with handoffs

Mon, 01 Jan 0001 00:00:00 +0000

Bulk exporting trace data

Mon, 01 Jan 0001 00:00:00 +0000

Call agents from code

Mon, 01 Jan 0001 00:00:00 +0000

Invoke Agent Builder agents from Python, JavaScript, or any language through the REST API.

Call agents from code

Mon, 01 Jan 0001 00:00:00 +0000

Invoke Fleet agents from Python, JavaScript, or any language through the REST API.

Cancel Run

Mon, 01 Jan 0001 00:00:00 +0000

Cancel Runs

Mon, 01 Jan 0001 00:00:00 +0000

Cancel one or more runs. Can cancel runs by thread ID and run IDs, or by status filter.

Case studies

Mon, 01 Jan 0001 00:00:00 +0000

Case studies

Mon, 01 Jan 0001 00:00:00 +0000

Channels

Mon, 01 Jan 0001 00:00:00 +0000

Configure channels to trigger your Fleet agents automatically.

Choosing between Graph and Functional APIs

Mon, 01 Jan 0001 00:00:00 +0000

Choosing between Graph and Functional APIs

Mon, 01 Jan 0001 00:00:00 +0000

Cloud

Mon, 01 Jan 0001 00:00:00 +0000

Co-marketing

Mon, 01 Jan 0001 00:00:00 +0000

Co-marketing

Mon, 01 Jan 0001 00:00:00 +0000

Compare traces

Mon, 01 Jan 0001 00:00:00 +0000

Comparison with OpenCode and Claude Agent SDK

Mon, 01 Jan 0001 00:00:00 +0000

Compare LangChain Deep Agents with OpenCode and Claude Agent SDK to choose the right tool for your use case

Comparison with OpenCode and Claude Agent SDK

Mon, 01 Jan 0001 00:00:00 +0000

Compare LangChain Deep Agents with OpenCode and Claude Agent SDK to choose the right tool for your use case

Component architecture

Mon, 01 Jan 0001 00:00:00 +0000

Component architecture

Mon, 01 Jan 0001 00:00:00 +0000

Conditional tracing

Mon, 01 Jan 0001 00:00:00 +0000

Configuration

Mon, 01 Jan 0001 00:00:00 +0000

Configure the Deep Agents CLI with config.toml, hooks, and MCP servers

Configure checkpointer backend

Mon, 01 Jan 0001 00:00:00 +0000

Configure Agent Server to use PostgreSQL, MongoDB, or a custom implementation for checkpoint storage.

Configure custom TLS certificates

Mon, 01 Jan 0001 00:00:00 +0000

Configure LangSmith Agent Server for scale

Mon, 01 Jan 0001 00:00:00 +0000

Configure LangSmith for scale

Mon, 01 Jan 0001 00:00:00 +0000

Configure prompt settings

Mon, 01 Jan 0001 00:00:00 +0000

Configure run input and output preview

Mon, 01 Jan 0001 00:00:00 +0000

Configure threads

Mon, 01 Jan 0001 00:00:00 +0000

Configure webhook notifications for LangSmith alerts

Mon, 01 Jan 0001 00:00:00 +0000

Configure webhook notifications for rules

Mon, 01 Jan 0001 00:00:00 +0000

Configure your collector for LangSmith telemetry

Mon, 01 Jan 0001 00:00:00 +0000

Connect an authentication provider

Mon, 01 Jan 0001 00:00:00 +0000

Connect to a custom model

Mon, 01 Jan 0001 00:00:00 +0000

Connect to an external ClickHouse database

Mon, 01 Jan 0001 00:00:00 +0000

Connect to an external PostgreSQL database

Mon, 01 Jan 0001 00:00:00 +0000

Connect to an external Redis database

Mon, 01 Jan 0001 00:00:00 +0000

Connect to an OpenAI compliant model provider/proxy

Mon, 01 Jan 0001 00:00:00 +0000

Context engineering in agents

Mon, 01 Jan 0001 00:00:00 +0000

Context engineering in agents

Mon, 01 Jan 0001 00:00:00 +0000

Context engineering in Deep Agents

Mon, 01 Jan 0001 00:00:00 +0000

Control what context your deep agent has access to and how it is managed across long-running tasks

Context engineering in Deep Agents

Mon, 01 Jan 0001 00:00:00 +0000

Control what context your deep agent has access to and how it is managed across long-running tasks

Context overview

Mon, 01 Jan 0001 00:00:00 +0000

Context overview

Mon, 01 Jan 0001 00:00:00 +0000

Contributing

Mon, 01 Jan 0001 00:00:00 +0000

Contributing

Mon, 01 Jan 0001 00:00:00 +0000

Contributing integrations

Mon, 01 Jan 0001 00:00:00 +0000

Contributing integrations

Mon, 01 Jan 0001 00:00:00 +0000

Contributing to code

Mon, 01 Jan 0001 00:00:00 +0000

Contributing to code

Mon, 01 Jan 0001 00:00:00 +0000

Contributing to documentation

Mon, 01 Jan 0001 00:00:00 +0000

Contributing to documentation

Mon, 01 Jan 0001 00:00:00 +0000

Control plane API reference for LangSmith Deployment

Mon, 01 Jan 0001 00:00:00 +0000

Copy Thread

Mon, 01 Jan 0001 00:00:00 +0000

Create a new thread with a copy of the state and checkpoints from an existing thread.

Core capabilities overview

Mon, 01 Jan 0001 00:00:00 +0000

Overview of Agent Server core capabilities including streaming, human-in-the-loop, MCP, A2A, distributed tracing, webhooks, and double-texting.

Cost tracking

Mon, 01 Jan 0001 00:00:00 +0000

Count Assistants

Mon, 01 Jan 0001 00:00:00 +0000

Get the count of assistants matching the specified criteria.

Count Crons

Mon, 01 Jan 0001 00:00:00 +0000

Get the count of crons matching the specified criteria.

Count Threads

Mon, 01 Jan 0001 00:00:00 +0000

Get the count of threads matching the specified criteria.

Create a prompt

Mon, 01 Jan 0001 00:00:00 +0000

Create an account and API key

Mon, 01 Jan 0001 00:00:00 +0000

Create an Ingress for installations (Kubernetes)

Mon, 01 Jan 0001 00:00:00 +0000

Create and manage datasets in the UI

Mon, 01 Jan 0001 00:00:00 +0000

Create Assistant

Mon, 01 Jan 0001 00:00:00 +0000

Create an assistant.

Create Background Run

Mon, 01 Jan 0001 00:00:00 +0000

Create a run and return the run ID immediately. Don’t wait for the final run output.

Create Background Run

Mon, 01 Jan 0001 00:00:00 +0000

Create a run in existing thread, return the run ID immediately. Don’t wait for the final run output.

Create Cron

Mon, 01 Jan 0001 00:00:00 +0000

Create a cron to schedule runs on new threads.

Create Run Batch

Mon, 01 Jan 0001 00:00:00 +0000

Create a batch of runs and return immediately.

Create Run, Stream Output

Mon, 01 Jan 0001 00:00:00 +0000

Create a run and stream the output.

Create Run, Stream Output

Mon, 01 Jan 0001 00:00:00 +0000

Create a run in existing thread. Stream the output.

Create Run, Wait for Output

Mon, 01 Jan 0001 00:00:00 +0000

Create a run, wait for the final output and then return it.

Create Run, Wait for Output

Mon, 01 Jan 0001 00:00:00 +0000

Create a run in existing thread. Wait for the final output and then return it.

Create Thread

Mon, 01 Jan 0001 00:00:00 +0000

Create a thread.

Create Thread Cron

Mon, 01 Jan 0001 00:00:00 +0000

Create a cron to schedule runs on a thread.

Custom instrumentation

Mon, 01 Jan 0001 00:00:00 +0000

Custom middleware

Mon, 01 Jan 0001 00:00:00 +0000

Custom middleware

Mon, 01 Jan 0001 00:00:00 +0000

Custom model providers

Mon, 01 Jan 0001 00:00:00 +0000

Configure any LangChain-compatible model provider for the Deep Agents CLI

Custom model providers

Mon, 01 Jan 0001 00:00:00 +0000

Configure any LangChain-compatible model provider for the Deep Agents CLI

Custom output rendering

Mon, 01 Jan 0001 00:00:00 +0000

Custom workflow

Mon, 01 Jan 0001 00:00:00 +0000

Custom workflow

Mon, 01 Jan 0001 00:00:00 +0000

Customize Deep Agents

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to customize deep agents with system prompts, tools, subagents, and more

Customize Deep Agents

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to customize deep agents with system prompts, tools, subagents, and more

Customize the error support message

Mon, 01 Jan 0001 00:00:00 +0000

Customize support contact information in the LangSmith frontend for self-hosted deployments.

Customize user management

Mon, 01 Jan 0001 00:00:00 +0000

Data purging for compliance

Mon, 01 Jan 0001 00:00:00 +0000

Data storage and privacy

Mon, 01 Jan 0001 00:00:00 +0000

Dataset prebuilt JSON schema types

Mon, 01 Jan 0001 00:00:00 +0000

Dataset transformations

Mon, 01 Jan 0001 00:00:00 +0000

Deep Agents

Mon, 01 Jan 0001 00:00:00 +0000

Deep Agents

Mon, 01 Jan 0001 00:00:00 +0000

Deep Agents CLI

Mon, 01 Jan 0001 00:00:00 +0000

Terminal coding agent built on the Deep Agents SDK

Deep Agents CLI

Mon, 01 Jan 0001 00:00:00 +0000

Terminal coding agent built on the Deep Agents SDK

Deep Agents overview

Mon, 01 Jan 0001 00:00:00 +0000

Build agents that can plan, use subagents, and leverage file systems for complex tasks

Deep Agents overview

Mon, 01 Jan 0001 00:00:00 +0000

Build agents that can plan, use subagents, and leverage file systems for complex tasks

Delete an item.

Mon, 01 Jan 0001 00:00:00 +0000

Delete Assistant

Mon, 01 Jan 0001 00:00:00 +0000

Delete an assistant by ID.

Delete Cron

Mon, 01 Jan 0001 00:00:00 +0000

Delete a cron by ID.

Delete organizations

Mon, 01 Jan 0001 00:00:00 +0000

Delete Run

Mon, 01 Jan 0001 00:00:00 +0000

Delete a run by ID.

Delete Thread

Mon, 01 Jan 0001 00:00:00 +0000

Delete a thread by ID.

Delete traces

Mon, 01 Jan 0001 00:00:00 +0000

Delete workspaces

Mon, 01 Jan 0001 00:00:00 +0000

Deploy an observability stack for your LangSmith deployment

Mon, 01 Jan 0001 00:00:00 +0000

Deploy on Cloud

Mon, 01 Jan 0001 00:00:00 +0000

Deploy other frameworks

Mon, 01 Jan 0001 00:00:00 +0000

Deploy with control plane

Mon, 01 Jan 0001 00:00:00 +0000

Deploy your app to Cloud

Mon, 01 Jan 0001 00:00:00 +0000

Discover errors and usage patterns with the Insights Agent

Mon, 01 Jan 0001 00:00:00 +0000

Distributed tracing with Agent Server

Mon, 01 Jan 0001 00:00:00 +0000

Unify traces when calling your deployed Agent Server from another service using RemoteGraph or the SDK.

Document API authentication in OpenAPI

Mon, 01 Jan 0001 00:00:00 +0000

Double texting

Mon, 01 Jan 0001 00:00:00 +0000

Durable execution

Mon, 01 Jan 0001 00:00:00 +0000

Durable execution

Mon, 01 Jan 0001 00:00:00 +0000

Egress for billing and operational telemetry

Mon, 01 Jan 0001 00:00:00 +0000

Enable blob storage

Mon, 01 Jan 0001 00:00:00 +0000

Enable Insights

Mon, 01 Jan 0001 00:00:00 +0000

Enable LangSmith Deployment

Mon, 01 Jan 0001 00:00:00 +0000

Enable Polly

Mon, 01 Jan 0001 00:00:00 +0000

Enable TTL and data retention

Mon, 01 Jan 0001 00:00:00 +0000

Enqueue concurrent

Mon, 01 Jan 0001 00:00:00 +0000

Environment variables

Mon, 01 Jan 0001 00:00:00 +0000

Errors

Mon, 01 Jan 0001 00:00:00 +0000

Errors

Mon, 01 Jan 0001 00:00:00 +0000

Essentials

Mon, 01 Jan 0001 00:00:00 +0000

Agent Builder’s core features

Essentials

Mon, 01 Jan 0001 00:00:00 +0000

Fleet’s core features

Evals

Mon, 01 Jan 0001 00:00:00 +0000

Evaluate agent trajectories using deterministic matching or LLM-as-judge evaluators with AgentEvals and LangSmith.

Evals

Mon, 01 Jan 0001 00:00:00 +0000

Evaluate agent trajectories using deterministic matching or LLM-as-judge evaluators with AgentEvals and LangSmith.

Evaluate a chatbot

Mon, 01 Jan 0001 00:00:00 +0000

Evaluate a complex agent

Mon, 01 Jan 0001 00:00:00 +0000

Evaluate a RAG application

Mon, 01 Jan 0001 00:00:00 +0000

Evaluation concepts

Mon, 01 Jan 0001 00:00:00 +0000

Evaluation quickstart

Mon, 01 Jan 0001 00:00:00 +0000

This is the fastest path into LangSmith evaluation and the right starting point before the deeper evaluator guides. The key takeaway is the dataset to target-function to evaluator to run loop, which is the mental model every other LangSmith eval feature builds on. Pay attention to how examples and the evaluation client are wired up, since that boilerplate carries over to LLM-as-judge work. A common beginner mistake is evaluating against a dataset that does not represent production traffic, which produces reassuring but meaningless scores.

Evaluation types

Mon, 01 Jan 0001 00:00:00 +0000

Example data format

Mon, 01 Jan 0001 00:00:00 +0000

Experiment configuration

Mon, 01 Jan 0001 00:00:00 +0000

Export LangSmith telemetry to your observability backend

Mon, 01 Jan 0001 00:00:00 +0000

Feedback data format

Mon, 01 Jan 0001 00:00:00 +0000

Filter traces

Mon, 01 Jan 0001 00:00:00 +0000

Fleet webhooks

Mon, 01 Jan 0001 00:00:00 +0000

Integrate agent publishing with external systems, CI/CD pipelines, or custom deployment workflows.

Frameworks, runtimes, and harnesses

Mon, 01 Jan 0001 00:00:00 +0000

Understand the differences between LangChain, LangGraph, and Deep Agents and when to use each one

Frameworks, runtimes, and harnesses

Mon, 01 Jan 0001 00:00:00 +0000

Understand the differences between LangChain, LangGraph, and Deep Agents and when to use each one

Frequently asked questions

Mon, 01 Jan 0001 00:00:00 +0000

Frequently Asked Questions

Mon, 01 Jan 0001 00:00:00 +0000

Frontend

Mon, 01 Jan 0001 00:00:00 +0000

Build React UIs that display real-time subagent streams from deep agents

Frontend

Mon, 01 Jan 0001 00:00:00 +0000

Build generative UIs with real-time streaming from LangChain agents, LangGraph graphs, and custom APIs

Frontend

Mon, 01 Jan 0001 00:00:00 +0000

Build React UIs that display real-time subagent streams from deep agents

Frontend

Mon, 01 Jan 0001 00:00:00 +0000

Build generative UIs with real-time streaming from LangChain agents, LangGraph graphs, and custom APIs

Functional API overview

Mon, 01 Jan 0001 00:00:00 +0000

Functional API overview

Mon, 01 Jan 0001 00:00:00 +0000

Generate ClickHouse stats

Mon, 01 Jan 0001 00:00:00 +0000

Generate query stats

Mon, 01 Jan 0001 00:00:00 +0000

Generative UI

Mon, 01 Jan 0001 00:00:00 +0000

Render AI-generated user interfaces using json-render

Generative UI

Mon, 01 Jan 0001 00:00:00 +0000

Render AI-generated user interfaces using json-render

Get Assistant

Mon, 01 Jan 0001 00:00:00 +0000

Get an assistant by ID.

Get Assistant Graph

Mon, 01 Jan 0001 00:00:00 +0000

Get an assistant by ID.

Get Assistant Schemas

Mon, 01 Jan 0001 00:00:00 +0000

Get an assistant by ID.

Get Assistant Subgraphs

Mon, 01 Jan 0001 00:00:00 +0000

Get an assistant’s subgraphs.

Get Assistant Subgraphs by Namespace

Mon, 01 Jan 0001 00:00:00 +0000

Get an assistant’s subgraphs filtered by namespace.

Get Assistant Versions

Mon, 01 Jan 0001 00:00:00 +0000

Get all versions of an assistant.

Get help

Mon, 01 Jan 0001 00:00:00 +0000

Get help

Mon, 01 Jan 0001 00:00:00 +0000

Get Run

Mon, 01 Jan 0001 00:00:00 +0000

Get a run by ID.

Get started with Studio

Mon, 01 Jan 0001 00:00:00 +0000

Get Thread

Mon, 01 Jan 0001 00:00:00 +0000

Get a thread by ID.

Get Thread History

Mon, 01 Jan 0001 00:00:00 +0000

Get all past states for a thread.

Get Thread History Post

Mon, 01 Jan 0001 00:00:00 +0000

Get all past states for a thread.

Get Thread State

Mon, 01 Jan 0001 00:00:00 +0000

Get state for a thread.

Get Thread State At Checkpoint

Mon, 01 Jan 0001 00:00:00 +0000

Get state for a thread at a specific checkpoint.

Get Thread State At Checkpoint

Mon, 01 Jan 0001 00:00:00 +0000

Get state for a thread at a specific checkpoint.

Going to production

Mon, 01 Jan 0001 00:00:00 +0000

Take your Deep Agent to production with persistent memory, sandboxes, resilience middleware, and deployment options

Going to production

Mon, 01 Jan 0001 00:00:00 +0000

Take your Deep Agent to production with persistent memory, sandboxes, resilience middleware, and deployment options

Granular billable usage

Mon, 01 Jan 0001 00:00:00 +0000

Retrieve detailed trace usage data broken down by workspace, project, user, or API key.

Graph API overview

Mon, 01 Jan 0001 00:00:00 +0000

Graph API overview

Mon, 01 Jan 0001 00:00:00 +0000

Graph execution

Mon, 01 Jan 0001 00:00:00 +0000

Visualize multi-step graph pipelines with per-node status and streaming content

Graph execution

Mon, 01 Jan 0001 00:00:00 +0000

Visualize multi-step graph pipelines with per-node status and streaming content

Guardrails

Mon, 01 Jan 0001 00:00:00 +0000

Implement safety checks and content filtering for your agents

Guardrails

Mon, 01 Jan 0001 00:00:00 +0000

Implement safety checks and content filtering for your agents

Handoffs

Mon, 01 Jan 0001 00:00:00 +0000

Handoffs

Mon, 01 Jan 0001 00:00:00 +0000

LangChain’s handoff mechanism lets you transfer execution between agents in a multi-agent graph, and it is worth comparing directly with OpenAI’s Agents SDK handoffs, which use explicit handoff objects rather than graph edges. Focus on how handoffs in LangChain are implemented as special tool calls that the framework intercepts to reroute execution — understanding this internal mechanism helps you debug cases where handoffs silently fail. Read the “Thinking in LangGraph” doc first, because handoffs only make sense once you understand LangGraph’s state machine model. Be mindful that handoff state serialization can be a source of subtle bugs when agents pass complex objects between each other.

Harness capabilities

Mon, 01 Jan 0001 00:00:00 +0000

Harness capabilities

Mon, 01 Jan 0001 00:00:00 +0000

Health Check

Mon, 01 Jan 0001 00:00:00 +0000

Check the health status of the server. Optionally check database connectivity.

How to add custom lifespan events

Mon, 01 Jan 0001 00:00:00 +0000

How to add custom middleware

Mon, 01 Jan 0001 00:00:00 +0000

How to add custom routes

Mon, 01 Jan 0001 00:00:00 +0000

How to add evaluators to an existing experiment (Python only)

Mon, 01 Jan 0001 00:00:00 +0000

How to add semantic search to your agent deployment

Mon, 01 Jan 0001 00:00:00 +0000

How to add TTLs to your application

Mon, 01 Jan 0001 00:00:00 +0000

How to audit evaluator scores

Mon, 01 Jan 0001 00:00:00 +0000

How to cancel a run

Mon, 01 Jan 0001 00:00:00 +0000

Cancel a single run or multiple runs via the API, and choose between interrupt and rollback actions.

How to collect user feedback for Agent Server runs

Mon, 01 Jan 0001 00:00:00 +0000

How to compare experiment results

Mon, 01 Jan 0001 00:00:00 +0000

How to create a composite evaluator

Mon, 01 Jan 0001 00:00:00 +0000

How to create a composite evaluator

Mon, 01 Jan 0001 00:00:00 +0000

How to create and manage datasets programmatically

Mon, 01 Jan 0001 00:00:00 +0000

How to customize the Dockerfile

Mon, 01 Jan 0001 00:00:00 +0000

How to define a code evaluator

Mon, 01 Jan 0001 00:00:00 +0000

How to define a code evaluator

Mon, 01 Jan 0001 00:00:00 +0000

How to define a summary evaluator

Mon, 01 Jan 0001 00:00:00 +0000

How to define a target function to evaluate

Mon, 01 Jan 0001 00:00:00 +0000

How to define an LLM-as-a-judge evaluator

Mon, 01 Jan 0001 00:00:00 +0000

How to define an LLM-as-a-judge evaluator

Mon, 01 Jan 0001 00:00:00 +0000

LLM-as-judge is the workhorse evaluator for open-ended outputs where exact-match scoring is impossible, so this page becomes essential the moment you move past trivial test cases. Pay close attention to how you define the judge prompt and scoring schema — vague rubrics produce noisy, irreproducible scores, the most common pitfall here. This is conceptually the same technique RAGAS and OpenAI’s agent evals implement, but LangSmith binds the judge directly to traced runs. Read the evaluation quickstart first to understand datasets and runs.

How to evaluate a graph

Mon, 01 Jan 0001 00:00:00 +0000

How to evaluate a runnable

Mon, 01 Jan 0001 00:00:00 +0000

How to evaluate an application's intermediate steps

Mon, 01 Jan 0001 00:00:00 +0000

How to evaluate an LLM application

Mon, 01 Jan 0001 00:00:00 +0000

How to evaluate with OpenTelemetry

Mon, 01 Jan 0001 00:00:00 +0000

How to evaluate with repetitions

Mon, 01 Jan 0001 00:00:00 +0000

How to evaluate your agent with trajectory evaluations

Mon, 01 Jan 0001 00:00:00 +0000

How to fetch performance metrics for an experiment

Mon, 01 Jan 0001 00:00:00 +0000

How to filter experiments in the UI

Mon, 01 Jan 0001 00:00:00 +0000

How to handle model rate limits

Mon, 01 Jan 0001 00:00:00 +0000

How to implement generative user interfaces with LangGraph

Mon, 01 Jan 0001 00:00:00 +0000

How to improve your evaluator with few-shot examples

Mon, 01 Jan 0001 00:00:00 +0000

How to interact with a deployment using RemoteGraph

Mon, 01 Jan 0001 00:00:00 +0000

How to kick off background runs

Mon, 01 Jan 0001 00:00:00 +0000

How to read experiment results locally

Mon, 01 Jan 0001 00:00:00 +0000

How to retry failed runs in experiments (Python only)

Mon, 01 Jan 0001 00:00:00 +0000

How to return categorical vs numerical metrics

Mon, 01 Jan 0001 00:00:00 +0000

How to return multiple scores in one evaluator

Mon, 01 Jan 0001 00:00:00 +0000

How to run a pairwise evaluation

Mon, 01 Jan 0001 00:00:00 +0000

How to run an evaluation asynchronously

Mon, 01 Jan 0001 00:00:00 +0000

How to run an evaluation locally (Python only)

Mon, 01 Jan 0001 00:00:00 +0000

How to run evaluations with pytest

Mon, 01 Jan 0001 00:00:00 +0000

How to run evaluations with Vitest/Jest

Mon, 01 Jan 0001 00:00:00 +0000

How to run multiple agents on the same thread

Mon, 01 Jan 0001 00:00:00 +0000

How to set up a JavaScript application

Mon, 01 Jan 0001 00:00:00 +0000

How to set up an application with pyproject.toml

Mon, 01 Jan 0001 00:00:00 +0000

How to set up an application with requirements.txt

Mon, 01 Jan 0001 00:00:00 +0000

How to simulate multi-turn interactions

Mon, 01 Jan 0001 00:00:00 +0000

How to sync prompts with GitHub

Mon, 01 Jan 0001 00:00:00 +0000

How to upload experiments run outside of LangSmith with the REST API

Mon, 01 Jan 0001 00:00:00 +0000

How to use a custom checkpointer

Mon, 01 Jan 0001 00:00:00 +0000

Replace the built-in Postgres checkpointer with a custom BaseCheckpointSaver implementation in your agent deployment.

How to use a custom store

Mon, 01 Jan 0001 00:00:00 +0000

Replace the built-in Postgres store with a custom BaseStore implementation in your agent deployment.

How to use prebuilt evaluators

Mon, 01 Jan 0001 00:00:00 +0000

How to use Studio

Mon, 01 Jan 0001 00:00:00 +0000

How to use the REST API

Mon, 01 Jan 0001 00:00:00 +0000

Human-in-the-loop

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to configure human approval for sensitive tool operations

Human-in-the-loop

Mon, 01 Jan 0001 00:00:00 +0000

Human-in-the-loop

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to configure human approval for sensitive tool operations

Human-in-the-loop

Mon, 01 Jan 0001 00:00:00 +0000

Human-in-the-Loop

Mon, 01 Jan 0001 00:00:00 +0000

Add approval workflows with interrupt-based human review

Human-in-the-Loop

Mon, 01 Jan 0001 00:00:00 +0000

Add approval workflows with interrupt-based human review

Human-in-the-loop using server API

Mon, 01 Jan 0001 00:00:00 +0000

Hybrid

Mon, 01 Jan 0001 00:00:00 +0000

Implement a CI/CD pipeline using LangSmith Deployment and Evaluation

Mon, 01 Jan 0001 00:00:00 +0000

Implement a LangChain integration

Mon, 01 Jan 0001 00:00:00 +0000

Implement a LangChain integration

Mon, 01 Jan 0001 00:00:00 +0000

Implement distributed tracing

Mon, 01 Jan 0001 00:00:00 +0000

Import exported data

Mon, 01 Jan 0001 00:00:00 +0000

Import LangSmith bulk-exported Parquet data into BigQuery, Snowflake, Redshift, Clickhouse, or DuckDB.

Improve LLM-as-judge evaluators using human feedback

Mon, 01 Jan 0001 00:00:00 +0000

Include HTTP headers in server logs

Mon, 01 Jan 0001 00:00:00 +0000

Include multimodal content in a prompt

Mon, 01 Jan 0001 00:00:00 +0000

Install LangChain

Mon, 01 Jan 0001 00:00:00 +0000

Install LangChain

Mon, 01 Jan 0001 00:00:00 +0000

Install LangGraph

Mon, 01 Jan 0001 00:00:00 +0000

Install LangGraph

Mon, 01 Jan 0001 00:00:00 +0000

Integrate Slack with an agent

Mon, 01 Jan 0001 00:00:00 +0000

Connect the LangSmith Agent Builder to your Slack workspace to let your agents communicate with users in Slack.

Integrate Slack with an agent

Mon, 01 Jan 0001 00:00:00 +0000

Connect LangSmith Fleet to your Slack workspace to let your agents communicate with users in Slack.

Integrate Teams with an agent

Mon, 01 Jan 0001 00:00:00 +0000

Connect LangSmith Fleet to Microsoft Teams by bringing your own Azure Bot to let agents communicate with users in Teams.

Integration testing

Mon, 01 Jan 0001 00:00:00 +0000

Test agents with real LLM APIs by organizing tests, managing keys, handling flakiness, and controlling costs.

Integration testing

Mon, 01 Jan 0001 00:00:00 +0000

Test agents with real LLM APIs by organizing tests, managing keys, handling flakiness, and controlling costs.

Integrations

Mon, 01 Jan 0001 00:00:00 +0000

Integrations

Mon, 01 Jan 0001 00:00:00 +0000

Integrations

Mon, 01 Jan 0001 00:00:00 +0000

Integrations

Mon, 01 Jan 0001 00:00:00 +0000

Interact with your self-hosted instance of LangSmith

Mon, 01 Jan 0001 00:00:00 +0000

Interrupt concurrent

Mon, 01 Jan 0001 00:00:00 +0000

Interrupts

Mon, 01 Jan 0001 00:00:00 +0000

Interrupts

Mon, 01 Jan 0001 00:00:00 +0000

Join & rejoin streams

Mon, 01 Jan 0001 00:00:00 +0000

Disconnect from and reconnect to running agent streams

Join & rejoin streams

Mon, 01 Jan 0001 00:00:00 +0000

Disconnect from and reconnect to running agent streams

Join Run

Mon, 01 Jan 0001 00:00:00 +0000

Wait for a run to finish.

Join Run Stream

Mon, 01 Jan 0001 00:00:00 +0000

Join a run stream. This endpoint streams output in real-time from a run similar to the /threads/THREAD_ID/runs/stream endpoint. If the run has been created with ‘stream_resumable=true’, the stream can be resumed from the last seen event ID.

Join Thread Stream

Mon, 01 Jan 0001 00:00:00 +0000

This endpoint streams output in real-time from a thread. The stream will include the output of each run executed sequentially on the thread and will remain open indefinitely. It is the responsibility of the calling client to close the connection.

LangChain Academy

Mon, 01 Jan 0001 00:00:00 +0000

LangChain Academy

Mon, 01 Jan 0001 00:00:00 +0000

LangChain overview

Mon, 01 Jan 0001 00:00:00 +0000

LangChain is an open source framework with a pre-built agent architecture and integrations for any model or tool — so you can build agents that adapt as fast as the ecosystem evolves

LangChain overview

Mon, 01 Jan 0001 00:00:00 +0000

LangChain is an open source framework with a pre-built agent architecture and integrations for any model or tool — so you can build agents that adapt as fast as the ecosystem evolves

LangChain SDK

Mon, 01 Jan 0001 00:00:00 +0000

LangChain SDK

Mon, 01 Jan 0001 00:00:00 +0000

LangChain v1 migration guide

Mon, 01 Jan 0001 00:00:00 +0000

LangChain v1 migration guide

Mon, 01 Jan 0001 00:00:00 +0000

LangGraph CLI

Mon, 01 Jan 0001 00:00:00 +0000

LangGraph JS/TS SDK

Mon, 01 Jan 0001 00:00:00 +0000

LangGraph overview

Mon, 01 Jan 0001 00:00:00 +0000

Gain control with LangGraph to design agents that reliably handle complex tasks

LangGraph overview

Mon, 01 Jan 0001 00:00:00 +0000

Gain control with LangGraph to design agents that reliably handle complex tasks

LangGraph Python SDK

Mon, 01 Jan 0001 00:00:00 +0000

LangGraph runtime

Mon, 01 Jan 0001 00:00:00 +0000

LangGraph runtime

Mon, 01 Jan 0001 00:00:00 +0000

LangGraph SDK

Mon, 01 Jan 0001 00:00:00 +0000

LangGraph SDK

Mon, 01 Jan 0001 00:00:00 +0000

LangGraph v1 migration guide

Mon, 01 Jan 0001 00:00:00 +0000

LangGraph v1 migration guide

Mon, 01 Jan 0001 00:00:00 +0000

LangSmith Agent Builder

Mon, 01 Jan 0001 00:00:00 +0000

Create helpful AI agents without code. Start from a template, connect your accounts, and let the agent handle routine work while you stay in control.

LangSmith API reference

Mon, 01 Jan 0001 00:00:00 +0000

LangSmith CLI

Mon, 01 Jan 0001 00:00:00 +0000

Query and manage LangSmith projects, traces, runs, datasets, evaluators, experiments, and threads from the terminal

LangSmith control plane

Mon, 01 Jan 0001 00:00:00 +0000

LangSmith data plane

Mon, 01 Jan 0001 00:00:00 +0000

LangSmith Deployment

Mon, 01 Jan 0001 00:00:00 +0000

Deploy and manage agents with durable execution, real-time streaming, and horizontal scaling.

LangSmith Deployment

Mon, 01 Jan 0001 00:00:00 +0000

Deploy and manage agents with durable execution, real-time streaming, and horizontal scaling.

LangSmith Deployment

Mon, 01 Jan 0001 00:00:00 +0000

LangSmith Deployment

Mon, 01 Jan 0001 00:00:00 +0000

LangSmith Deployment

Mon, 01 Jan 0001 00:00:00 +0000

LangSmith Deployment

Mon, 01 Jan 0001 00:00:00 +0000

LangGraph deployment through LangSmith provides managed infrastructure for hosting graph-based agents with built-in tracing, monitoring, and versioning. This guide covers the deployment pipeline from local development to hosted execution, including environment configuration and API endpoint setup. A key consideration is that deploying to LangSmith introduces a vendor dependency that affects your architecture, so evaluate the tracing and observability benefits against the portability tradeoffs before committing. If you need self-hosted deployment or want to compare alternatives, review this alongside general containerization approaches for Python applications.

LangSmith Deployment components

Mon, 01 Jan 0001 00:00:00 +0000

LangSmith Deployment SDK

Mon, 01 Jan 0001 00:00:00 +0000

LangSmith docs

Mon, 01 Jan 0001 00:00:00 +0000

LangSmith Evaluation

Mon, 01 Jan 0001 00:00:00 +0000

LangSmith Fetch

Mon, 01 Jan 0001 00:00:00 +0000

LangSmith Fleet

Mon, 01 Jan 0001 00:00:00 +0000

Create helpful AI agents without code. Start from a template, connect your accounts, and let the agent handle routine work while you stay in control.

LangSmith for Enterprise

Mon, 01 Jan 0001 00:00:00 +0000

Deployment options, access control, data privacy, cost controls, and security compliance for Enterprise users.

LangSmith Go SDK

Mon, 01 Jan 0001 00:00:00 +0000

LangSmith Java SDK

Mon, 01 Jan 0001 00:00:00 +0000

LangSmith JS/TS SDK

Mon, 01 Jan 0001 00:00:00 +0000

LangSmith MCP Server

Mon, 01 Jan 0001 00:00:00 +0000

Use the Model Context Protocol (MCP) server to let language models fetch conversation history, prompts, runs, datasets, experiments, and billing from LangSmith.

LangSmith Observability

Mon, 01 Jan 0001 00:00:00 +0000

LangSmith Observability

Mon, 01 Jan 0001 00:00:00 +0000

LangSmith Observability

Mon, 01 Jan 0001 00:00:00 +0000

LangSmith Observability

Mon, 01 Jan 0001 00:00:00 +0000

LangSmith Observability

Mon, 01 Jan 0001 00:00:00 +0000

LangSmith Polly

Mon, 01 Jan 0001 00:00:00 +0000

LangSmith Polly

Mon, 01 Jan 0001 00:00:00 +0000

LangSmith Polly

Mon, 01 Jan 0001 00:00:00 +0000

LangSmith Polly

Mon, 01 Jan 0001 00:00:00 +0000

LangSmith Python SDK

Mon, 01 Jan 0001 00:00:00 +0000

LangSmith reference

Mon, 01 Jan 0001 00:00:00 +0000

LangSmith shared responsibility model

Mon, 01 Jan 0001 00:00:00 +0000

Overview of how LangChain and customers share security responsibilities for the LangSmith platform.

LangSmith skills

Mon, 01 Jan 0001 00:00:00 +0000

Use Agent Skills to work with LangSmith traces, datasets, and evaluators from your coding agent.

LangSmith status

Mon, 01 Jan 0001 00:00:00 +0000

LangSmith Studio

Mon, 01 Jan 0001 00:00:00 +0000

LangSmith Studio

Mon, 01 Jan 0001 00:00:00 +0000

LangSmith Studio

Mon, 01 Jan 0001 00:00:00 +0000

LangSmith Studio

Mon, 01 Jan 0001 00:00:00 +0000

LangSmith Studio

Mon, 01 Jan 0001 00:00:00 +0000

LangSmith Tool Server

Mon, 01 Jan 0001 00:00:00 +0000

LangSmith Tool Server

Mon, 01 Jan 0001 00:00:00 +0000

LangSmith-managed ClickHouse

Mon, 01 Jan 0001 00:00:00 +0000

Learn

Mon, 01 Jan 0001 00:00:00 +0000

Tutorials, conceptual guides, and resources to help you get started.

Learn

Mon, 01 Jan 0001 00:00:00 +0000

Tutorials, conceptual guides, and resources to help you get started.

List namespaces with optional match conditions.

Mon, 01 Jan 0001 00:00:00 +0000

List Runs

Mon, 01 Jan 0001 00:00:00 +0000

List runs for a thread.

Local development & testing

Mon, 01 Jan 0001 00:00:00 +0000

Log LLM calls

Mon, 01 Jan 0001 00:00:00 +0000

Log multimodal traces

Mon, 01 Jan 0001 00:00:00 +0000

Log retriever traces

Mon, 01 Jan 0001 00:00:00 +0000

Log traces to a specific project

Mon, 01 Jan 0001 00:00:00 +0000

Log user feedback using the SDK

Mon, 01 Jan 0001 00:00:00 +0000

Long-term memory

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to extend deep agents with persistent memory across threads

Long-term memory

Mon, 01 Jan 0001 00:00:00 +0000

Long-term memory

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to extend deep agents with persistent memory across threads

Long-term memory

Mon, 01 Jan 0001 00:00:00 +0000

Make conversations private

Mon, 01 Jan 0001 00:00:00 +0000

Manage a trace

Mon, 01 Jan 0001 00:00:00 +0000

Compare traces side-by-side, share traces publicly, and view server logs from the trace view in LangSmith.

Manage Agent Builder

Mon, 01 Jan 0001 00:00:00 +0000

Manage agent settings

Mon, 01 Jan 0001 00:00:00 +0000

Manage your agents in Agent Builder.

Manage agent settings

Mon, 01 Jan 0001 00:00:00 +0000

Manage your agents in Fleet.

Manage assistants

Mon, 01 Jan 0001 00:00:00 +0000

Manage billing in your account

Mon, 01 Jan 0001 00:00:00 +0000

Manage bulk export destinations

Mon, 01 Jan 0001 00:00:00 +0000

Configure and manage S3-compatible export destinations for LangSmith bulk exports.

Manage datasets

Mon, 01 Jan 0001 00:00:00 +0000

Manage feedback & annotation queues programmatically

Mon, 01 Jan 0001 00:00:00 +0000

Manage Fleet

Mon, 01 Jan 0001 00:00:00 +0000

Manage model configurations

Mon, 01 Jan 0001 00:00:00 +0000

Manage model configurations and control their availability across LangSmith features.

Manage prompts

Mon, 01 Jan 0001 00:00:00 +0000

Manage prompts programmatically

Mon, 01 Jan 0001 00:00:00 +0000

Manage user access in SSO organizations

Mon, 01 Jan 0001 00:00:00 +0000

Manage your organization using the API

Mon, 01 Jan 0001 00:00:00 +0000

Markdown messages

Mon, 01 Jan 0001 00:00:00 +0000

Render LLM responses as rich, formatted markdown with proper streaming support

Markdown messages

Mon, 01 Jan 0001 00:00:00 +0000

Render LLM responses as rich, formatted markdown with proper streaming support

MCP endpoint in Agent Server

Mon, 01 Jan 0001 00:00:00 +0000

MCP Get

Mon, 01 Jan 0001 00:00:00 +0000

Implemented according to the Streamable HTTP Transport specification.

MCP Post

Mon, 01 Jan 0001 00:00:00 +0000

Implemented according to the Streamable HTTP Transport specification.

MCP Tools

Mon, 01 Jan 0001 00:00:00 +0000

Load additional tools from MCP (Model Context Protocol) servers

Memory

Mon, 01 Jan 0001 00:00:00 +0000

Add persistent memory to agents built with Deep Agents so they learn and improve across conversations

Memory

Mon, 01 Jan 0001 00:00:00 +0000

Memory

Mon, 01 Jan 0001 00:00:00 +0000

Add persistent memory to agents built with Deep Agents so they learn and improve across conversations

Memory

Mon, 01 Jan 0001 00:00:00 +0000

Memory in LangGraph goes beyond simple conversation history to include persistent state checkpoints that survive across graph executions, which is essential for building agents that maintain context across sessions. Focus on the distinction between short-term message memory and long-term checkpoint-based state, as choosing the wrong persistence strategy leads to either excessive token consumption or lost context. The checkpointer abstraction is the key integration point, and you should understand how it interacts with graph state before selecting a storage backend. This guide pairs well with the streaming guide, since memory and streaming together determine how your agent behaves in real-time interactive scenarios.

Memory overview

Mon, 01 Jan 0001 00:00:00 +0000

Memory overview

Mon, 01 Jan 0001 00:00:00 +0000

Message queues

Mon, 01 Jan 0001 00:00:00 +0000

Queue multiple messages and manage them while the agent processes sequentially

Message queues

Mon, 01 Jan 0001 00:00:00 +0000

Queue multiple messages and manage them while the agent processes sequentially

Messages

Mon, 01 Jan 0001 00:00:00 +0000

Messages

Mon, 01 Jan 0001 00:00:00 +0000

Metadata parameters reference

Mon, 01 Jan 0001 00:00:00 +0000

Mirror images for your LangSmith installation

Mon, 01 Jan 0001 00:00:00 +0000

Model Context Protocol (MCP)

Mon, 01 Jan 0001 00:00:00 +0000

Model Context Protocol (MCP)

Mon, 01 Jan 0001 00:00:00 +0000

LangChain’s MCP integration allows you to expose MCP servers as LangChain tools, bridging two of the most important ecosystems in the AI tooling space. This is particularly valuable if you have existing MCP servers and want to use them within LangChain agents or LangGraph workflows without rewriting tool definitions. Focus on how MCP tool schemas map to LangChain’s tool interface and what metadata is preserved or lost in translation. Be aware that MCP’s streaming and sampling capabilities may not map perfectly to LangChain’s tool abstraction, so test complex MCP servers thoroughly after integration.

Model providers

Mon, 01 Jan 0001 00:00:00 +0000

Models

Mon, 01 Jan 0001 00:00:00 +0000

Models

Mon, 01 Jan 0001 00:00:00 +0000

Models

Mon, 01 Jan 0001 00:00:00 +0000

Models

Mon, 01 Jan 0001 00:00:00 +0000

Monitor and troubleshoot bulk exports

Mon, 01 Jan 0001 00:00:00 +0000

Monitor bulk export status, manage running exports, and troubleshoot failures.

Monitor projects with dashboards

Mon, 01 Jan 0001 00:00:00 +0000

Monorepo support

Mon, 01 Jan 0001 00:00:00 +0000

Multi-agent

Mon, 01 Jan 0001 00:00:00 +0000

Multi-agent

Mon, 01 Jan 0001 00:00:00 +0000

null

Mon, 01 Jan 0001 00:00:00 +0000

Observability concepts

Mon, 01 Jan 0001 00:00:00 +0000

Observability in Studio

Mon, 01 Jan 0001 00:00:00 +0000

openapi

Mon, 01 Jan 0001 00:00:00 +0000

Optimize a classifier

Mon, 01 Jan 0001 00:00:00 +0000

Organization and workspace operations reference

Mon, 01 Jan 0001 00:00:00 +0000

Overview

Mon, 01 Jan 0001 00:00:00 +0000

Overview

Mon, 01 Jan 0001 00:00:00 +0000

Build UIs that display real-time subagent streams, task progress, and sandbox for Deep Agents

Overview

Mon, 01 Jan 0001 00:00:00 +0000

Stream real-time updates from deep agent runs and subagent execution

Overview

Mon, 01 Jan 0001 00:00:00 +0000

Build generative UIs with real-time streaming from LangChain agents

Overview

Mon, 01 Jan 0001 00:00:00 +0000

Control and customize agent execution at every step

Overview

Mon, 01 Jan 0001 00:00:00 +0000

Stream real-time updates from agent runs

Overview

Mon, 01 Jan 0001 00:00:00 +0000

Render LangGraph agents to the frontend

Overview

Mon, 01 Jan 0001 00:00:00 +0000

Build UIs that display real-time subagent streams, task progress, and sandbox for Deep Agents

Overview

Mon, 01 Jan 0001 00:00:00 +0000

Stream real-time updates from deep agent runs and subagent execution

Overview

Mon, 01 Jan 0001 00:00:00 +0000

Build generative UIs with real-time streaming from LangChain agents

Overview

Mon, 01 Jan 0001 00:00:00 +0000

Control and customize agent execution at every step

Overview

Mon, 01 Jan 0001 00:00:00 +0000

Stream real-time updates from agent runs

Overview

Mon, 01 Jan 0001 00:00:00 +0000

Render LangGraph agents to the frontend

Patch Assistant

Mon, 01 Jan 0001 00:00:00 +0000

Update an assistant.

Patch Thread

Mon, 01 Jan 0001 00:00:00 +0000

Update a thread.

Persistence

Mon, 01 Jan 0001 00:00:00 +0000

Persistence

Mon, 01 Jan 0001 00:00:00 +0000

Philosophy

Mon, 01 Jan 0001 00:00:00 +0000

LangChain exists to be the easiest place to start building with LLMs, while also being flexible and production-ready.

Philosophy

Mon, 01 Jan 0001 00:00:00 +0000

LangChain exists to be the easiest place to start building with LLMs, while also being flexible and production-ready.

Prebuilt middleware

Mon, 01 Jan 0001 00:00:00 +0000

Prebuilt middleware for common agent use cases

Prebuilt middleware

Mon, 01 Jan 0001 00:00:00 +0000

Prebuilt middleware for common agent use cases

Prevent logging of sensitive data in traces

Mon, 01 Jan 0001 00:00:00 +0000

Pricing FAQ

Mon, 01 Jan 0001 00:00:00 +0000

Pricing FAQ

Mon, 01 Jan 0001 00:00:00 +0000

Pricing plans

Mon, 01 Jan 0001 00:00:00 +0000

Prompt engineering

Mon, 01 Jan 0001 00:00:00 +0000

Prompt engineering concepts

Mon, 01 Jan 0001 00:00:00 +0000

Prompt engineering quickstart

Mon, 01 Jan 0001 00:00:00 +0000

Prompt template format guide

Mon, 01 Jan 0001 00:00:00 +0000

Prune Threads

Mon, 01 Jan 0001 00:00:00 +0000

Prune threads by ID. The ‘delete’ strategy removes threads entirely. The ‘keep_latest’ strategy prunes old checkpoints but keeps threads and their latest state.

Publish an integration

Mon, 01 Jan 0001 00:00:00 +0000

Publish an integration

Mon, 01 Jan 0001 00:00:00 +0000

Query threads using the SDK

Mon, 01 Jan 0001 00:00:00 +0000

Programmatically fetch and inspect multi-turn conversation threads from your LangSmith projects.

Query traces (SDK)

Mon, 01 Jan 0001 00:00:00 +0000

Quickstart

Mon, 01 Jan 0001 00:00:00 +0000

Build an agent from a template

Quickstart

Mon, 01 Jan 0001 00:00:00 +0000

Build an agent from a template

Quickstart

Mon, 01 Jan 0001 00:00:00 +0000

Build your first deep agent in minutes

Quickstart

Mon, 01 Jan 0001 00:00:00 +0000

Quickstart

Mon, 01 Jan 0001 00:00:00 +0000

Quickstart

Mon, 01 Jan 0001 00:00:00 +0000

Build your first deep agent in minutes

Quickstart

Mon, 01 Jan 0001 00:00:00 +0000

Quickstart

Mon, 01 Jan 0001 00:00:00 +0000

Reasoning tokens

Mon, 01 Jan 0001 00:00:00 +0000

Display model thinking and reasoning processes in collapsible blocks

Reasoning tokens

Mon, 01 Jan 0001 00:00:00 +0000

Display model thinking and reasoning processes in collapsible blocks

Rebuild graph at runtime

Mon, 01 Jan 0001 00:00:00 +0000

Rebuild your graph with different configurations for each run using ServerRuntime.

Reference

Mon, 01 Jan 0001 00:00:00 +0000

Reference

Mon, 01 Jan 0001 00:00:00 +0000

Regions FAQ

Mon, 01 Jan 0001 00:00:00 +0000

Reject Concurrent

Mon, 01 Jan 0001 00:00:00 +0000

Release policy

Mon, 01 Jan 0001 00:00:00 +0000

Release policy

Mon, 01 Jan 0001 00:00:00 +0000

Release versions

Mon, 01 Jan 0001 00:00:00 +0000

Remote MCP servers

Mon, 01 Jan 0001 00:00:00 +0000

Connect Agent Builder to popular remote MCP servers

Remote MCP servers

Mon, 01 Jan 0001 00:00:00 +0000

Connect Fleet to popular remote MCP servers

RemoteGraph

Mon, 01 Jan 0001 00:00:00 +0000

Retrieval

Mon, 01 Jan 0001 00:00:00 +0000

Retrieval

Mon, 01 Jan 0001 00:00:00 +0000

LangChain’s retrieval guide covers the foundational abstractions for document loading, splitting, embedding, and querying that underpin every RAG application built on the framework. Understanding the Retriever interface is critical because it is the common contract that vector stores, BM25 indexes, and custom retrieval strategies all implement. Focus on how retrievers compose with chains and agents, since the retrieval step is often the performance bottleneck in production RAG pipelines. Read this before the RAG-specific guide to ensure you understand the building blocks before seeing them assembled into a full application.

Retrieve a single item.

Mon, 01 Jan 0001 00:00:00 +0000

Role-based access control

Mon, 01 Jan 0001 00:00:00 +0000

Rollback Concurrent

Mon, 01 Jan 0001 00:00:00 +0000

Router

Mon, 01 Jan 0001 00:00:00 +0000

Router

Mon, 01 Jan 0001 00:00:00 +0000

Run (span) data format

Mon, 01 Jan 0001 00:00:00 +0000

Run a LangGraph app locally

Mon, 01 Jan 0001 00:00:00 +0000

Run a local server

Mon, 01 Jan 0001 00:00:00 +0000

Run a local server

Mon, 01 Jan 0001 00:00:00 +0000

Run an evaluation from the Playground

Mon, 01 Jan 0001 00:00:00 +0000

Run an evaluation from the prompt playground

Mon, 01 Jan 0001 00:00:00 +0000

Run an evaluation with multimodal content

Mon, 01 Jan 0001 00:00:00 +0000

Run backtests on a new version of an agent

Mon, 01 Jan 0001 00:00:00 +0000

Run support queries against ClickHouse

Mon, 01 Jan 0001 00:00:00 +0000

Run support queries against PostgreSQL

Mon, 01 Jan 0001 00:00:00 +0000

Runs

Mon, 01 Jan 0001 00:00:00 +0000

An overview of runs in Agent Server, including how to kick off background runs, stateless runs, and cancel runs.

Runtime

Mon, 01 Jan 0001 00:00:00 +0000

Runtime

Mon, 01 Jan 0001 00:00:00 +0000

Sandbox

Mon, 01 Jan 0001 00:00:00 +0000

Build an IDE-like UI for a coding agent backed by a sandbox environment

Sandbox

Mon, 01 Jan 0001 00:00:00 +0000

Build an IDE-like UI for a coding agent backed by a sandbox environment

Sandbox auth proxy

Mon, 01 Jan 0001 00:00:00 +0000

Inject credentials into outbound API requests from sandboxes without hardcoding secrets.

Sandbox SDK usage

Mon, 01 Jan 0001 00:00:00 +0000

Create and manage sandboxes programmatically with the Python or TypeScript SDK.

Sandbox templates

Mon, 01 Jan 0001 00:00:00 +0000

Define container images, resource limits, and configuration for sandboxes using templates.

Sandbox warm pools

Mon, 01 Jan 0001 00:00:00 +0000

Pre-provision sandboxes for faster execution with automatic replenishment.

Sandboxes

Mon, 01 Jan 0001 00:00:00 +0000

Execute code in isolated environments with sandbox backends

Sandboxes

Mon, 01 Jan 0001 00:00:00 +0000

Execute code in isolated environments with sandbox backends

Sandboxes overview

Mon, 01 Jan 0001 00:00:00 +0000

Use managed sandboxes to safely execute code and interact with the filesystem in isolated environments.

Scalability & resilience

Mon, 01 Jan 0001 00:00:00 +0000

Schedules

Mon, 01 Jan 0001 00:00:00 +0000

Configure schedules to run your Fleet agents on a recurring basis.

Search Assistants

Mon, 01 Jan 0001 00:00:00 +0000

Search for assistants.

Search Crons

Mon, 01 Jan 0001 00:00:00 +0000

Search all active crons

Search or list items within a namespace prefix.

Mon, 01 Jan 0001 00:00:00 +0000

Lists items ordered by last updated time. If a ‘query’ is provided, performs a natural language search instead. Supports pagination via ’limit’ and ‘offset’, and filtering via ‘filter’.

Search Threads

Mon, 01 Jan 0001 00:00:00 +0000

Search for threads.

Security policy

Mon, 01 Jan 0001 00:00:00 +0000

Security policy

Mon, 01 Jan 0001 00:00:00 +0000

Self-host LangSmith on Kubernetes

Mon, 01 Jan 0001 00:00:00 +0000

Self-host LangSmith with Docker

Mon, 01 Jan 0001 00:00:00 +0000

Self-host standalone servers

Mon, 01 Jan 0001 00:00:00 +0000

Self-hosted

Mon, 01 Jan 0001 00:00:00 +0000

Self-hosted LangSmith

Mon, 01 Jan 0001 00:00:00 +0000

Self-hosted LangSmith changelog

Mon, 01 Jan 0001 00:00:00 +0000

Self-hosted LangSmith on AWS

Mon, 01 Jan 0001 00:00:00 +0000

Self-hosted LangSmith on Azure

Mon, 01 Jan 0001 00:00:00 +0000

Self-hosted LangSmith on GCP

Mon, 01 Jan 0001 00:00:00 +0000

Server Information

Mon, 01 Jan 0001 00:00:00 +0000

Get server version information, feature flags, and metadata.

Set a sampling rate for traces

Mon, 01 Jan 0001 00:00:00 +0000

Set Latest Assistant Version

Mon, 01 Jan 0001 00:00:00 +0000

Set the latest version for an assistant.

Set up Agent Auth (Beta)

Mon, 01 Jan 0001 00:00:00 +0000

Enable secure access from agents to any system using OAuth 2.0 credentials with Agent Auth.

Set up automation rules

Mon, 01 Jan 0001 00:00:00 +0000

Set up composite online evaluators

Mon, 01 Jan 0001 00:00:00 +0000

Set up custom authentication

Mon, 01 Jan 0001 00:00:00 +0000

Set up feedback criteria

Mon, 01 Jan 0001 00:00:00 +0000

Set up hierarchy

Mon, 01 Jan 0001 00:00:00 +0000

Set up hybrid LangSmith

Mon, 01 Jan 0001 00:00:00 +0000

Set up LangSmith

Mon, 01 Jan 0001 00:00:00 +0000

Set up LLM-as-a-judge online evaluators

Mon, 01 Jan 0001 00:00:00 +0000

Set up multi-turn online evaluators

Mon, 01 Jan 0001 00:00:00 +0000

Set up online code evaluators

Mon, 01 Jan 0001 00:00:00 +0000

Set up resource tags

Mon, 01 Jan 0001 00:00:00 +0000

Set up SSO with OAuth2.0 and OIDC

Mon, 01 Jan 0001 00:00:00 +0000

Set up the LLM auth proxy

Mon, 01 Jan 0001 00:00:00 +0000

Deploy an Envoy-based auth proxy that validates LangSmith-signed JWTs and routes LLM requests to your upstream provider or gateway.

Share or unshare a trace publicly

Mon, 01 Jan 0001 00:00:00 +0000

Short-term memory

Mon, 01 Jan 0001 00:00:00 +0000

Short-term memory

Mon, 01 Jan 0001 00:00:00 +0000

Skills

Mon, 01 Jan 0001 00:00:00 +0000

Use skills to give your agents access to specific capabilities.

Skills

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to extend your deep agent’s capabilities with skills

Skills

Mon, 01 Jan 0001 00:00:00 +0000

Skills

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to extend your deep agent’s capabilities with skills

Skills

Mon, 01 Jan 0001 00:00:00 +0000

Specify a custom run ID

Mon, 01 Jan 0001 00:00:00 +0000

How to specify a custom run ID when tracing with LangSmith.

Stateless runs

Mon, 01 Jan 0001 00:00:00 +0000

Store or update an item.

Mon, 01 Jan 0001 00:00:00 +0000

Streaming

Mon, 01 Jan 0001 00:00:00 +0000

Streaming

Mon, 01 Jan 0001 00:00:00 +0000

Streaming in LangGraph operates at multiple levels – token-level streaming from the LLM, node-level events as the graph executes, and custom event emission – and understanding which level to use for your application is critical for responsive UX. The most common pitfall is subscribing to token streams when you actually need node-level events, which floods the client with data it cannot usefully render. Pay attention to how streaming interacts with tool calls and conditional edges, since intermediate nodes may emit partial results that should not be shown to users. Read the workflows-and-agents guide first to understand graph execution flow before layering streaming on top.

Streaming API

Mon, 01 Jan 0001 00:00:00 +0000

Structured output

Mon, 01 Jan 0001 00:00:00 +0000

Render structured agent responses with custom UI components instead of plain text

Structured output

Mon, 01 Jan 0001 00:00:00 +0000

Structured output

Mon, 01 Jan 0001 00:00:00 +0000

Render structured agent responses with custom UI components instead of plain text

Structured output

Mon, 01 Jan 0001 00:00:00 +0000

Studio troubleshooting

Mon, 01 Jan 0001 00:00:00 +0000

Subagent streaming

Mon, 01 Jan 0001 00:00:00 +0000

Display specialist subagents with streaming content, progress tracking, and collapsible cards

Subagent streaming

Mon, 01 Jan 0001 00:00:00 +0000

Display specialist subagents with streaming content, progress tracking, and collapsible cards

Subagents

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to use subagents to delegate work and keep context clean

Subagents

Mon, 01 Jan 0001 00:00:00 +0000

Subagents

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to use subagents to delegate work and keep context clean

Subagents

Mon, 01 Jan 0001 00:00:00 +0000

Subgraphs

Mon, 01 Jan 0001 00:00:00 +0000

Subgraphs

Mon, 01 Jan 0001 00:00:00 +0000

System Metrics

Mon, 01 Jan 0001 00:00:00 +0000

Get system metrics in Prometheus or JSON format for monitoring and observability.

Templates

Mon, 01 Jan 0001 00:00:00 +0000

Start faster with curated Agent Builder templates and customize tools, prompts, and triggers.

Templates

Mon, 01 Jan 0001 00:00:00 +0000

Start faster with curated Fleet templates and customize tools, prompts, and channels.

Terminate Session

Mon, 01 Jan 0001 00:00:00 +0000

Implemented according to the Streamable HTTP Transport specification.

Test

Mon, 01 Jan 0001 00:00:00 +0000

Strategies for testing LangChain agents, including unit tests, integration tests, and trajectory evaluations.

Test

Mon, 01 Jan 0001 00:00:00 +0000

Test

Mon, 01 Jan 0001 00:00:00 +0000

Strategies for testing LangChain agents, including unit tests, integration tests, and trajectory evaluations.

Test

Mon, 01 Jan 0001 00:00:00 +0000

Test a ReAct agent with Pytest/Vitest and LangSmith

Mon, 01 Jan 0001 00:00:00 +0000

Test multi-turn conversations

Mon, 01 Jan 0001 00:00:00 +0000

Thinking in LangGraph

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to think about building agents with LangGraph

Thinking in LangGraph

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to think about building agents with LangGraph

Time travel

Mon, 01 Jan 0001 00:00:00 +0000

Inspect, navigate, and resume from any checkpoint in the conversation history

Time travel

Mon, 01 Jan 0001 00:00:00 +0000

Inspect, navigate, and resume from any checkpoint in the conversation history

Time travel using the server API

Mon, 01 Jan 0001 00:00:00 +0000

Todo list

Mon, 01 Jan 0001 00:00:00 +0000

Track agent progress with a real-time todo list synced from agent state

Todo list

Mon, 01 Jan 0001 00:00:00 +0000

Track agent progress with a real-time todo list synced from agent state

Tool calling

Mon, 01 Jan 0001 00:00:00 +0000

Display agent tool calls with rich, type-safe UI cards

Tool calling

Mon, 01 Jan 0001 00:00:00 +0000

Display agent tool calls with rich, type-safe UI cards

Tool integrations

Mon, 01 Jan 0001 00:00:00 +0000

Give your agents access to a wide range of tools and services.

Tool integrations

Mon, 01 Jan 0001 00:00:00 +0000

Give your agents access to a wide range of tools and services.

Tools

Mon, 01 Jan 0001 00:00:00 +0000

Tools

Mon, 01 Jan 0001 00:00:00 +0000

Trace Amazon Bedrock applications

Mon, 01 Jan 0001 00:00:00 +0000

Trace an LLM application tutorial

Mon, 01 Jan 0001 00:00:00 +0000

Trace Anthropic applications

Mon, 01 Jan 0001 00:00:00 +0000

Trace AutoGen applications

Mon, 01 Jan 0001 00:00:00 +0000

Trace Claude Agent SDK applications

Mon, 01 Jan 0001 00:00:00 +0000

Trace Claude Code applications

Mon, 01 Jan 0001 00:00:00 +0000

Trace CrewAI applications

Mon, 01 Jan 0001 00:00:00 +0000

Trace Deep Agents applications

Mon, 01 Jan 0001 00:00:00 +0000

Trace DeepSeek applications

Mon, 01 Jan 0001 00:00:00 +0000

Trace generator functions

Mon, 01 Jan 0001 00:00:00 +0000

Trace Google ADK applications

Mon, 01 Jan 0001 00:00:00 +0000

Trace Google Gemini applications

Mon, 01 Jan 0001 00:00:00 +0000

Trace Instructor applications

Mon, 01 Jan 0001 00:00:00 +0000

Trace JS functions in serverless environments

Mon, 01 Jan 0001 00:00:00 +0000

Trace LangChain applications (Python and JS/TS)

Mon, 01 Jan 0001 00:00:00 +0000

Trace LangGraph applications

Mon, 01 Jan 0001 00:00:00 +0000

Trace LiveKit applications

Mon, 01 Jan 0001 00:00:00 +0000

Trace Mastra applications

Mon, 01 Jan 0001 00:00:00 +0000

Trace Microsoft Agent Framework applications

Mon, 01 Jan 0001 00:00:00 +0000

Trace Mistral applications

Mon, 01 Jan 0001 00:00:00 +0000

Trace n8n workflows

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to trace n8n AI workflows in LangSmith.

Trace OpenAI Agents SDK applications

Mon, 01 Jan 0001 00:00:00 +0000

Trace OpenAI applications

Mon, 01 Jan 0001 00:00:00 +0000

Trace Pipecat applications

Mon, 01 Jan 0001 00:00:00 +0000

Trace PydanticAI applications

Mon, 01 Jan 0001 00:00:00 +0000

Trace query syntax

Mon, 01 Jan 0001 00:00:00 +0000

Trace Semantic Kernel applications

Mon, 01 Jan 0001 00:00:00 +0000

Trace Vercel AI SDK applications (JS/TS only)

Mon, 01 Jan 0001 00:00:00 +0000

Trace with API

Mon, 01 Jan 0001 00:00:00 +0000

Trace with OpenTelemetry

Mon, 01 Jan 0001 00:00:00 +0000

Trace with Temporal

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to trace Temporal workflows and activities in LangSmith using OpenTelemetry.

Trace without setting environment variables

Mon, 01 Jan 0001 00:00:00 +0000

Tracing quickstart

Mon, 01 Jan 0001 00:00:00 +0000

Triggers

Mon, 01 Jan 0001 00:00:00 +0000

Configure triggers to start your Agent Builder agents automatically.

Troubleshoot trace nesting

Mon, 01 Jan 0001 00:00:00 +0000

Troubleshoot variable caching

Mon, 01 Jan 0001 00:00:00 +0000

Troubleshooting

Mon, 01 Jan 0001 00:00:00 +0000

Troubleshooting for self-hosted deployments

Mon, 01 Jan 0001 00:00:00 +0000

Unit testing

Mon, 01 Jan 0001 00:00:00 +0000

Test agent logic without API calls using fake chat models and in-memory persistence.

Unit testing

Mon, 01 Jan 0001 00:00:00 +0000

Test agent logic without API calls using fake chat models and in-memory persistence.

Update Cron

Mon, 01 Jan 0001 00:00:00 +0000

Update a cron job by ID.

Update Thread State

Mon, 01 Jan 0001 00:00:00 +0000

Add state to a thread.

Upgrade an installation

Mon, 01 Jan 0001 00:00:00 +0000

Upload files with traces

Mon, 01 Jan 0001 00:00:00 +0000

Use an existing secret for your installation (Kubernetes)

Mon, 01 Jan 0001 00:00:00 +0000

Use annotation queues

Mon, 01 Jan 0001 00:00:00 +0000

Use cron jobs

Mon, 01 Jan 0001 00:00:00 +0000

Use environment variables for model providers

Mon, 01 Jan 0001 00:00:00 +0000

Use HTTP headers for runtime configuration

Mon, 01 Jan 0001 00:00:00 +0000

Use server-side caching

Mon, 01 Jan 0001 00:00:00 +0000

Cache values server-side in your agent deployment using stale-while-revalidate and key-value cache APIs.

Use the functional API

Mon, 01 Jan 0001 00:00:00 +0000

Use the functional API

Mon, 01 Jan 0001 00:00:00 +0000

Use the graph API

Mon, 01 Jan 0001 00:00:00 +0000

Use the graph API

Mon, 01 Jan 0001 00:00:00 +0000

Use threads

Mon, 01 Jan 0001 00:00:00 +0000

Use time-travel

Mon, 01 Jan 0001 00:00:00 +0000

Use time-travel

Mon, 01 Jan 0001 00:00:00 +0000

Use tools in a prompt

Mon, 01 Jan 0001 00:00:00 +0000

Use webhooks

Mon, 01 Jan 0001 00:00:00 +0000

User management

Mon, 01 Jan 0001 00:00:00 +0000

Using standard tests

Mon, 01 Jan 0001 00:00:00 +0000

Using standard tests

Mon, 01 Jan 0001 00:00:00 +0000

Versioning

Mon, 01 Jan 0001 00:00:00 +0000

Versioning

Mon, 01 Jan 0001 00:00:00 +0000

View server logs for a trace

Mon, 01 Jan 0001 00:00:00 +0000

View trace counts across your organization

Mon, 01 Jan 0001 00:00:00 +0000

What's new in LangChain v1

Mon, 01 Jan 0001 00:00:00 +0000

What's new in LangChain v1

Mon, 01 Jan 0001 00:00:00 +0000

What's new in LangGraph v1

Mon, 01 Jan 0001 00:00:00 +0000

What's new in LangGraph v1

Mon, 01 Jan 0001 00:00:00 +0000

Workflows and agents

Mon, 01 Jan 0001 00:00:00 +0000

Workflows and agents

Mon, 01 Jan 0001 00:00:00 +0000

This guide draws the critical distinction between deterministic workflows and autonomous agents in LangGraph, which is the most important conceptual decision you make when designing a LangGraph application. Workflows use predefined edges and conditional branching, while agents use LLM-driven decisions to determine the next step. Understanding when to choose each pattern, and when to combine them, directly impacts the reliability, cost, and debuggability of your application. Start here before diving into specific LangGraph features like memory or streaming, as the workflow-vs-agent framing shapes every subsequent design choice.

Workload isolation

Mon, 01 Jan 0001 00:00:00 +0000

Workspace setup

Mon, 01 Jan 0001 00:00:00 +0000

Add required workspace secrets for models and tools used by Agent Builder.

Workspace setup

Mon, 01 Jan 0001 00:00:00 +0000

Add required workspace secrets for models and tools used by Fleet.

Write your prompt with AI

Mon, 01 Jan 0001 00:00:00 +0000