LangChain llms.txt · AI Docs Browser · mdream [llms.txt Tools](https://mdream.dev/llms-txt/langchain/llms-txt) # LangChain llms.txt Browse LangChain documentation as markdown. Click any page in the sidebar to view it, or copy the full llms.txt for your AI tools. docs.langchain.com/llms.txt [Raw llms.txt](https://docs.langchain.com/llms.txt) [Raw llms-full.txt](https://docs.langchain.com/llms-full.txt) Copy Markdown [](https://docs.langchain.com/llms.txt) llms.txt Docs Create Connection List Connections Remove Connection Authenticate Check Oauth Token Exists Check Oauth Tokens Exist Batch Check Workspace Slack Tokens Exist Create Mcp Oauth Provider Create Oauth Provider Delete Oauth Provider Delete Oauth Tokens For User Delete Single Oauth Token Get Oauth Provider Get Platform Oauth Provider Import Oauth Token List Oauth Providers List Oauth Tokens For User List Platform Oauth Providers Oauth Callback Oauth Callback Get Oauth Setup Callback Revoke All Slack Tokens For Workspace Update Oauth Provider Update Token Label Wait For Auth Completion Create Deployment Delete Deployment Delete Deployments Get Deployment Get Free Deployment Count Get Revision List Deployments List Revisions Patch Deployment Patch Deployment Resource Tiers Patch Deployment Tier Redeploy Revision List Forge GitHub Integrations List Forge GitHub Repositories List GitHub Integrations List GitHub Repositories Create Listener Delete Listener Get Listener List Listeners Patch Listener Build Attribute-based access control Access the current run (span) within a traced function Connect an authentication provider Human-in-the-loop using server API Add metadata and tags to traces Account Overview Set up Agent Auth Agent Server A2A JSON-RPC Count Assistants Create Assistant Delete Assistant Get Assistant Get Assistant Graph Get Assistant Schemas Get Assistant Subgraphs Get Assistant Subgraphs by Namespace Get Assistant Versions Patch Assistant Search Assistants Set Latest Assistant Version Count Crons Create Cron Create Thread Cron Delete Cron Get Cron Search Crons Update Cron MCP Get MCP Post Terminate Session Create Background Run Create Run Batch Create Run, Stream Output Create Run, Wait for Output Delete an item. List namespaces with optional match conditions. Retrieve a single item. Search or list items within a namespace prefix. Store or update an item. Protocol v2 Command Protocol v2 Event Stream (SSE) API Documentation Health Check Server Information System Metrics Cancel Run Cancel Runs Create Background Run Create Run, Stream Output Create Run, Wait for Output Delete Run Get Run Join Run Join Run Stream List Runs Copy Thread Count Threads Create Thread Delete Thread Get Thread Get Thread History Get Thread History Post Get Thread State Get Thread State At Checkpoint Get Thread State At Checkpoint Join Thread Stream Patch Thread Prune Threads Search Threads Update Thread State Agent Server changelog Agent Server changelog Distributed tracing with Agent Server How to collect user feedback for Agent Server runs Configure Agent Server for scale Alerts in LangSmith Analyze an experiment Custom instrumentation Annotate traces and runs inline Use annotation queues Manage feedback & annotation queues programmatically Control plane API reference for LangSmith Deployment Application structure Use assertions Assistants Log user feedback using the SDK How to audit evaluator scores Audit logs Authentication & access control Authentication methods Self-hosted LangSmith on AWS Self-hosted LangSmith on Azure How to kick off background runs Export trace data to BigQuery Manage billing in your account Automatically run evaluators on experiments Use server-side caching How to cancel a run LangSmith Cloud changelog LangSmith Chat LangSmith Chat LangSmith Chat LangSmith Chat Implement a CI/CD pipeline using LangSmith Deployment and Evaluation LangGraph CLI Cloud (SaaS) Cloud platform features How to define a code evaluator How to define a code evaluator Coding agent metadata contract How to compare experiment results LangSmith Deployment components How to create a composite evaluator How to create a composite evaluator Conditional tracing Use HTTP headers for runtime configuration Include HTTP headers in server logs Manage assistants Configure checkpointer backend Configure run input and output preview How to add TTLs to your application Context engineering concepts Context Hub LangSmith control plane Cost tracking Create a prompt Create an account and API key How to improve your evaluator with few-shot examples Use cron jobs Add custom authentication How to use a custom checkpointer How to customize the Dockerfile Connect to a custom model How to add custom lifespan events How to add custom middleware Connect to an OpenAI compliant model provider/proxy Custom output rendering How to add custom routes How to use a custom store Monitor projects with dashboards Bulk export trace data Manage bulk export destinations Import exported data Monitor and troubleshoot bulk exports LangSmith data plane Data purging for compliance Data storage and privacy Dataset prebuilt JSON schema types Dataset transformations How to define a target function to evaluate Deploy with Cloudflare Workers Deploy with Deno Deploy Deploy full-stack web apps Deploy Google ADK agents Deploy with Next.js Deploy with Nuxt Deploy other frameworks Reference Enable LangSmith Deployment, Fleet, Insights, and Chat Self-host standalone servers Deploy with SvelteKit Deploy on Cloud Deploy to Cloud Deploy to self-hosted Deploy with LangSmith and Vite Deploy with control plane LangSmith Deployment Deploy your app to cloud Deploy Managed Deep Agents Develop agents Troubleshooting for self-hosted deployments Implement distributed tracing Double texting Add encryption at rest Find and fix your agent's issues with LangSmith Engine LangSmith Engine LangSmith Engine LangSmith Engine security LangSmith Engine on self-hosted LangSmith Engine webhook events Enqueue concurrent LangSmith for Enterprise Cloud Agent Server environment variables Self-hosted Agent Server environment variables Evaluate a chatbot Evaluate a complex agent How to add evaluators to an existing experiment (Python only) How to evaluate a graph How to evaluate agents How to evaluate an application's intermediate steps How to run a pairwise evaluation Evaluate a RAG application Run an evaluation with multimodal content How to evaluate with OpenTelemetry How to retry failed runs in experiments (Python only) LangSmith Evaluation Application-specific evaluation approaches How to run an evaluation asynchronously Evaluation concepts Evaluation quickstart Evaluation types Track and limit evaluator spend Manage evaluators Example data format Experiment configuration Export LangSmith telemetry to your observability backend Query traces using the SDK Frequently asked questions Feedback data format How to fetch performance metrics for an experiment How to filter experiments in the UI Filter traces Access & oversight Agent identity Arcade integration Auth-aware tool responses LangSmith Fleet changelog Channels Use Fleet agents in code Agent platform comparison Computer use Essentials No-code agents with LangSmith Fleet Manage agent settings LangSmith Tool Server Quickstart Remote MCP servers Salesforce integration Schedules Self-hosted Skills Integrate Slack with an agent Integrate Teams with an agent Templates Tool integrations Fleet webhooks Manage workspace administration Self-hosted LangSmith on GCP How to implement generative user interfaces with LangGraph Governance Govern Granular billable usage Rebuild graph at runtime How to handle model rate limits Harbor integrations Time travel using the server API Hybrid Setup guide (legacy) Improve LLM-as-judge evaluators using human feedback Discover errors and usage patterns with Insights Integrations Interrupt concurrent Manage user access in SSO organizations Self-host LangSmith on Kubernetes How to evaluate a runnable LangGraph JS/TS SDK LangGraph Python SDK LangSmith CLI Configure your collector for LangSmith telemetry LangSmith-managed ClickHouse LangSmith MCP Server LangSmith Remote MCP How to define an LLM-as-a-judge evaluator How to define an LLM-as-a-judge evaluator Set up the LLM auth proxy LLM Gateway Traces, Engine, and access control Admin setup Set up coding agents Custom model providers Quickstart PII and secrets redaction Spend policies How to run an evaluation locally (Python only) Local development & testing Log LLM calls Log multimodal traces Log retriever traces Log traces to a specific project Metadata parameters reference Manage contexts with the SDK Manage datasets Create and manage datasets in the UI How to create and manage datasets programmatically Manage evaluators with the SDK Manage your organization using the API Manage prompts Manage prompts programmatically Manage a trace Manage LangSmith with Terraform Managed Deep Agents Managed Deep Agents CLI reference Connect tools and capabilities to Managed Deep Agents Expose LangSmith capabilities with Managed Deep Agents Connect MCP tools to Managed Deep Agents Deploy a Managed Deep Agent Managed Deep Agents example project How Managed Deep Agents work Add identity to Managed Deep Agents Add custom middleware to Managed Deep Agents Managed Deep Agents Managed Deep Agents quickstart Add schedules to Managed Deep Agents Add custom tools to Managed Deep Agents Build a scheduled research agent Configure prompt settings Prevent logging of sensitive data in traces Messages view integrations Messages view trace format reference How to return categorical vs numerical metrics Manage model configurations Monorepo support How to simulate multi-turn interactions Include multimodal content in a prompt Test multi-turn conversations How to return multiple scores in one evaluator Troubleshoot trace nesting LangSmith Observability Observability concepts Trace an LLM application tutorial Tracing quickstart Deploy an observability stack for your LangSmith deployment Observability in Studio Set up online code evaluators Set up composite online evaluators Set up LLM-as-a-judge online evaluators Set up multi-turn online evaluators Document API authentication in OpenAPI Run evals with openevals package Optimize a classifier Organization and workspace operations reference Redact sensitive data with the OpenTelemetry Gateway architecture Set up LangSmith Model providers Collect feedback with presigned URLs Pricing plans Profile configuration How to sync prompts with GitHub Prompt engineering Prompt engineering concepts Prompt engineering quickstart Prompt template format guide How to run evaluations with pytest Query threads using the SDK Get started with Studio Role-based access control How to read experiment results locally Redact secrets from traces LangSmith reference Regions FAQ Reject Concurrent Release stages Release policy RemoteGraph How to evaluate with repetitions Make conversations private Rollback Concurrent Set up automation rules Run backtests on a new version of an agent Run (span) data format How to use the REST API Run an evaluation from the Playground Runs How to run multiple agents on the same thread Set a sampling rate for traces Sandbox auth proxy Sandbox CLI Sandbox mounts Sandbox access permissions Sandbox SDK usage Sandbox service URLs Sandbox snapshots LangSmith Sandboxes Scalability & resilience Delete workspaces Delete organizations Delete traces Generate ClickHouse stats Generate query stats Run support queries against ClickHouse Run support queries against PostgreSQL Basic authentication with email and password Enable blob storage Configure custom TLS certificates Minimum versions for self-hosting dependencies Disaster recovery for self-hosted LangSmith Egress for billing and operational telemetry Configure environment variables in the Helm chart Connect to an external ClickHouse database Connect to an external PostgreSQL database Connect to an external Redis or Valkey database FIPS-compliant images Create an Ingress for installations (Kubernetes) Mirror images for your LangSmith installation View trace counts across your organization Use environment variables for model providers Configure LangSmith for scale Set up SSO with OAuth2.0 and OIDC Deploy LangSmith with Terraform AWS Terraform architecture Deploy LangSmith on AWS with Terraform AWS Terraform quick reference AWS Terraform troubleshooting AWS Terraform variables reference Azure Terraform architecture Deploy LangSmith on Azure with Terraform Azure Terraform quick reference Azure Terraform troubleshooting Azure Terraform variables reference GCP Terraform architecture Deploy LangSmith on GCP with Terraform GCP Terraform quick reference GCP Terraform troubleshooting GCP Terraform variables reference Enable TTL and data retention Customize the error support message Upgrade an installation Interact with your self-hosted instance of LangSmith Customize user management Use an existing secret for your installation (Kubernetes) Self-hosted LangSmith Agent Server metrics Self-hosted LangSmith changelog Install Mission Control Self-hosted platform features How to add semantic search to your agent deployment A2A endpoint in Agent Server Agent Server API reference for LangSmith Deployment MCP endpoint in Agent Server Trace JS functions in serverless environments Set up custom authentication Set up feedback criteria Set up hierarchy Set up resource tags How to set up an application with requirements.txt How to set up a JavaScript application How to set up an application with pyproject.toml LangSmith shared responsibility model LangSmith skills LangSmith API reference Attach access policies to a role Create an access policy Delete an access policy Get an access policy List access policies Execute Create an alert rule Delete an alert rule Get an alert rule Test an alert action to determine if configuration is valid Update an alert rule Add runs to annotation queue Add runs to annotation queue by key Create annotation queue Create identity annotation queue run status Delete annotation queue Delete annotation queues Delete run from annotation queue Delete runs from annotation queue Export annotation queue archived runs Get annotation queue Get annotation queues Get annotation queues for run Get run from annotation queue Get runs from annotation queue Get size from annotation queue Get total archived from annotation queue Get total size from annotation queue Populate annotation queue Resolve annotation queue run Update annotation queue Update run in annotation queue Add a reviewer to an annotation queue Remove a reviewer from an annotation queue Delete API key Delete personal access token Generate API key Generate personal access token Get API keys Get personal access tokens Get audit logs Check SSO email verification status Confirm SSO user email Get public auth info Get SSO settings Login Lookup SSO by email Send SSO email confirmation AWS marketplace fulfillment URL registration Restart a backfill job Cancel bulk export Create bulk export Create bulk export destination Get bulk export Get bulk export destination Get bulk export destinations Get bulk export run Get bulk export runs Get bulk export runs filtered Get bulk exports Update bulk export destination Clone section Create chart Create section Delete chart Delete section Org create chart Org create section Org delete chart Org delete section Org read chart preview Org read charts Org read sections Org read single chart Org read single section Org update chart Org update section Read chart preview Read charts Read sections Read single chart Read single section Update chart Update section Create comment Create sub comment Get comments Get sub comments Like comment Unlike comment Create a commit Get a commit List commits Create a new data plane List data planes for the current organization Clone dataset Create comparative experiment Create dataset Delete comparative experiment Delete dataset Delete datasets Diff dataset versions Download dataset csv Download dataset jsonl Download dataset openai Download dataset openai ft Fetch experiment runs for dataset examples (v2) Fetch shared experiment runs for dataset examples (v2) Generate Get dataset splits Get dataset version Get dataset versions Read dataset Read dataset share state Read datasets Read datasets stream Read examples with runs Share dataset Studio experiment Unshare dataset Update dataset Update dataset splits Update dataset version Upload csv dataset Upload experiment Create directory commit Delete directory repository Get directory contents Bulk delete evaluators Create evaluator Delete evaluator Get evaluator Get evaluator spend List evaluators Update evaluator Count examples Create example Create examples Delete example Delete examples Hard delete examples Legacy update examples Read example Read examples Update example Update examples Upload examples Upload examples from csv Validate example Validate examples Create new experiment view override configuration for a dataset Delete experiment view override configuration Get experiment view override configuration by specific ID Get experiment view override configurations for a dataset Update existing experiment view override configuration Evaluate experiment adhoc Delete default model for a feature Disable a model for a feature List feature configurations Re-enable a disabled model for a feature Set default model for a feature Create feedback config endpoint Delete feedback config endpoint List feedback configs endpoint Update feedback config endpoint Create feedback Create feedback formula ep Create feedback ingest token Create feedback with token get Create feedback with token post Delete feedback Delete feedback formula endpoint Eagerly create feedback Get feedback formula ep List feedback formula ep List feedback ingest tokens Read feedback Read feedbacks Update feedback Update feedback formula ep Create a gateway policy Delete a gateway policy Get a gateway policy List gateway policies Search gateway policies by subject value set Update a gateway policy Create hub environments model Delete hub environments model List hub environments Update hub environments model Get health info Get server info Get agent builder integrations settings Update agent builder integrations settings Create the issues agent for a session (Beta) Delete the issues agent for a session (Beta) Get issues-agent (engine) LCU spend per project for the calling org Get the issues agent config for a session (Beta) List issues agent configs (Beta) Roll an issues agent webhook signing secret Save the agent overview for a session (Beta) Update the issues agent config for a session (Beta) Get issue (Beta) List issues (Beta) List viewed issues for a session (Beta) Mark issue viewed (Beta) Record a fix-verification verdict Start preview-deploy verification for a fix Like repo Get tools Invalidate tools cache Proxy Proxy get Create vendor settings Delete vendor settings Get MCP vendor Get vendor account Get vendor settings List MCP servers for a vendor List MCP vendors List tools for a vendor Replace vendor settings Create onboarding state Get ls user ID Get onboarding state Get the authenticated user's provider user ID Update onboarding state field Create new model price Delete model price Read model price map Update model price Approve OAuth2 authorization request Authorize a device code Exchange grant for OAuth2 tokens Get OAuth2 authorization server metadata Get public OAuth2 client metadata Initiate OAuth2 authorization Register an OAuth2 dynamic client Request OAuth2 device authorization Revoke an OAuth2 token Create job Create log Delete job Delete log Get job Get log List job logs List jobs Update job Get current organization info Add basic auth members to current org Add member to current org Add members to current org batch Change payment plan Claim pending organization invite Create customers and get stripe setup intent Create org personal access token Create org service key Create organization Create organization roles Create SSO settings Create stripe account links endpoint Create stripe checkout sessions endpoint Delete current org pending member Delete org personal access token Delete org service key Delete organization roles Delete pending organization invite Delete SSO settings Export granular usage csv Get company info Get current active org members Get current org members Get current organization info Get current pending org members Get current SSO settings Get current user login methods Get dashboard Get granular usage Get org usage Get organization billing info Get organization info List org members with workspace roles List org personal access tokens List org service keys List organization roles List organizations List pending organization invites List permissions List TTL settings On payment method created Patch current org pending member Remove member from current org Set company info Set default SSO provision Set role restriction Update allowed login methods Update current org member Update current organization info Update current user Update org service key Update organization roles Update SSO settings Upsert TTL settings Add repo owner List repo owners Remove repo owner Create playground settings Delete playground settings Get playground settings List playground settings Update playground settings Create prompt webhook Delete prompt webhook Get prompt webhook List prompt webhooks Test prompt webhook Update prompt webhook Invoke prompt Prompt canvas Count shared examples Generate query for shared dataset runs Get message JSON schema Get shared run Get shared run by ID Get tool def JSON schema Query shared dataset runs Query shared runs Read shared comparative experiments Read shared dataset Read shared dataset feedback Read shared dataset run Read shared dataset tracer sessions Read shared dataset tracer sessions bulk Read shared examples Read shared feedbacks Stats shared dataset runs Create repo Delete repo Delete repos Fork repo Get repo List repo tags List repos Optimize prompt job Update repo Create rule Create run proxy Create runs batch proxy Create runs multipart proxy Delete rule Delete runs Delete runs abac Generate query for runs Get last applied rule Group runs List rule logs List rule logs (v2) List rules Query runs Read run Read run share state Share run Stats group runs Stats runs Thread preview Trigger rule Trigger rules Unshare run Update rule Update run Validate rule Validate runs query Create a run Get a public shared trace run (v2) Ingest runs (batch json) Ingest runs (multipart) List runs in a trace (v2) Query public shared trace runs (v2) Query runs (v2) Query traces (v2) Read run (v2) Share run (v2) Unshare a run (v2) Update a run Batch delete sandboxes Capture a snapshot from a sandbox Create a registry Create a sandbox Create a snapshot Delete a registry Delete a sandbox Delete a snapshot Download a sandbox file Execute a sandbox command Execute a sandbox command over WebSocket Generate a service access token Get a registry Get a sandbox Get a snapshot Get sandbox access decision Get sandbox resource usage Get sandbox status Glob a sandbox filesystem Grep a sandbox filesystem List registries List sandboxes List snapshots Open a sandbox TCP tunnel Start a sandbox Stop a sandbox Update a registry Update a sandbox Upload a sandbox file Create a SCIM token Delete a SCIM token Get a SCIM token List SCIM tokens Update a SCIM token Create service account Delete service account Get service accounts List agent versions for a project Get settings Set tenant handle Get tag transition history Create tag Delete tag Get tag Get tags Update tag Create tenant List tenants Query single thread stats (v2) Query thread traces (v2) Query threads (v2) Create a tool Delete a tool by handle Delete a tool by ID Get a tool by handle Get a tool by ID List tools Update a tool by handle Update a tool by ID Auto-generate insights job config (Beta) Create filter view Create insights job (Beta) Create insights job config (Beta) Create tracer session Delete filter view Delete insights job (Beta) Delete insights job config (Beta) Delete tracer session Delete tracer sessions Get insights job (Beta) Get insights job configs (Beta) Get insights jobs (Beta) Get run cluster from insights job (Beta) Get runs from insights job (Beta) Get tracing project prebuilt dashboard Read filter view Read filter views Read tracer session Read tracer sessions Read tracer sessions runs metadata Rename filter view Update filter view ## What is LangChain's llms.txt? LangChain publishes an `/llms.txt` file that provides AI systems with a structured index of its documentation. It follows the [llms.txt specification](https://llmstxt.org), organizing links to guides, API references, and tutorials under section headings so that LLMs like ChatGPT, Claude, and Gemini can quickly understand what LangChain offers and where to find details. Pass Spec 1 Sections 957 Links 97.6 KB Size ~25.0k Tokens Sections: Docs ## Add LangChain Docs to Your AI Assistant Select your tool to see how to add LangChain's llms.txt as a documentation source. Cursor Windsurf Claude Code ChatGPT Zed Copilot 1. 1 Open any chat or composer panel 2. 2 Type @Docs and select "Add new doc" 3. 3 Paste the URL: https://docs.langchain.com/llms.txt 4. 4 Wait for the green dot (indexing complete) 5. 5 Reference @Docs in chat when asking about LangChain Cursor crawls the URL and indexes all subpages. Add a trailing slash to index child pages too. ## Spec Compliance 4 notes ## Frequently Asked Questions Where is LangChain's llms.txt file? LangChain publishes its llms.txt at https://docs.langchain.com/llms.txt. This file provides a structured, markdown-formatted index of LangChain's documentation that AI systems can consume to understand the project's APIs, guides, and references. How do I use LangChain's llms.txt with AI coding assistants? Copy the llms.txt content and paste it into your AI assistant (Cursor, Windsurf, Claude, ChatGPT) as context. This gives the AI an accurate map of LangChain's documentation so it can provide better code suggestions and answers about LangChain. What does LangChain's llms.txt contain? LangChain's llms.txt contains 1 sections and 957 documentation links in 97.6 KB (~25.0k tokens). Key sections include Docs. How many tokens does LangChain's llms.txt use? The concise llms.txt index is approximately 25.0k tokens (97.6 KB). Most AI assistants can fit this within their context window. For the full expanded documentation, look for an llms-full.txt variant which embeds all content inline. What is LangChain? Framework for developing applications powered by LLMs. LangChain's llms.txt file helps AI systems understand this by providing a structured overview of its documentation, making it easier for developers to get accurate AI-assisted help when working with LangChain. Can I generate an llms.txt for my own project? Yes. Use the free llms.txt generator at mdream.dev/tools/llms-txt/generator to crawl your site and produce a spec-compliant llms.txt file. You can also validate existing files with the llms.txt validator. ## Browse More llms.txt Files [TanStack High-quality open-source libraries for web development](https://mdream.dev/llms-txt/langchain/llms-txt/tanstack) [Fumadocs The documentation framework for Next.js](https://mdream.dev/llms-txt/langchain/llms-txt/fumadocs) [Three.js 3D library for JavaScript](https://mdream.dev/llms-txt/langchain/llms-txt/three-js) [Grafbase The fastest GraphQL gateway](https://mdream.dev/llms-txt/langchain/llms-txt/grafbase) [Bun Incredibly fast JavaScript runtime, bundler, and package manager](https://mdream.dev/llms-txt/langchain/llms-txt/bun) [Cal.com The open-source scheduling infrastructure](https://mdream.dev/llms-txt/langchain/llms-txt/cal-com) [UnoCSS Instant on-demand atomic CSS engine](https://mdream.dev/llms-txt/langchain/llms-txt/unocss) [Resend Email API for developers](https://mdream.dev/llms-txt/langchain/llms-txt/resend) [View all 99 projects ](https://mdream.dev/llms-txt/langchain/llms-txt) ## Related Tools [

llms.txt Generator

Generate an llms.txt for your own project.](https://mdream.dev/llms-txt/langchain/tools/llms-txt/generator) [

llms.txt Validator

Validate your llms.txt against the official spec.](https://mdream.dev/llms-txt/langchain/tools/llms-txt/validator) © 2026 [Harlan Wilton](https://github.com/harlan-zw) · [MIT](https://github.com/harlan-zw/mdream/blob/main/license) [GitHub](https://github.com/harlan-zw/mdream) [Discord](https://discord.com/invite/275MBUBvgP)