LangChain · 索引內容

Support PlansCreate agentsCreate agentsLast updated: August 20, 2026A comprehensive overview of the LangChain support along with associated onboarding, education, and advisory capabilities.A key distinction among the support offerings lies in the level of supplementary resources, guidance, and assistance provided to the users. These differences cover the depth of support available for troubleshooting and maintenance, the scope of education materials like tutorials and documentation for learning the framework, and the extent of advisory services offered, which could include architectural recommendations or strategic integration consultations.LangSmith Support Plans Feature Base Standard Premium Applicable for Monthly Pay-as-you Go Usage Annual or Multi-year contracts Technical Support Sev 1 — Service UnavailableTotal outage or failure rendering use of the Service impossible 4 hoursBusiness Hours 2 hoursBusiness Hours 30 minutes24x7x365 Sev 2 — Service DegradedSevere degradation without a workaround when the overall Service remains operational — 4 hoursBusiness Hours 2 hours24x7x365 Sev 3 — Service ImpactedPartial functionality issues or non-blocking bugs — 2 business daysBusiness Ho…

LangSmith DeploymentRun agents at scaleLangSmith Deployment is purpose-built infrastructure for running agents in production and standardizes how your organization builds, deploys, and governs agents.Start building Get a demo .mask { position: fixed; top: 0; left: 0; width: 100vw; height: 100vh; pointer-events: none; z-index: 10; will-change: mask-image, -webkit-mask-image; -webkit-mask-image: radial-gradient(circle 0px at 0px 0px, black 0%, transparent 100%); mask-image: radial-gradient(circle 0px at 0px 0px, black 0%, transparent 100%); display: none; } @media (min-width: 992px) { .mask { display: block; } } .mask img { position: absolute; } document.addEventListener("DOMContentLoaded", () => { const section = document.querySelector(".product_hero-section"); const masks = document.querySelectorAll(".mask"); if (!section || !masks.length) return; const MAX_RADIUS = 300; const LERP = 0.15; const THRESHOLD = 0.5; const states = Array.from(masks, () => ({ x: 0, y: 0, r: 0, tx: 0, ty: 0, tr: 0 })); let isInside = false; let isDesktop = window.innerWidth >= 992; // Update breakpoint on resize instead of checking every frame/mousemove window.addEventListener("resize", () => { isDesktop …

BuildBuild agents fast with or without code. Choose your model. Own your harness.Start with proven agent patterns, customize when you need controlOwn your harness, context, memory, and model choiceEnable every team build to agents in natural language with FleetDeep Agents LangGraph LangChain Fleet

LangSmith for StartupsIterate faster, win biggerTest, deploy, monitor, and improve your agents with discounted pricing for buildersApply now Trusted byUse cases in production LangSmith helps startups build better agents.Find failures fast with agent tracingQuickly debug and understand non-deterministic behavior with tracing.Run agents at scale with LangSmith DeploymentPurpose-built infrastructure for deploying long-running agent workloads.Continuously improve agent qualityRun evals before and after shipping, and gather expert feedback on performance.Run agent-generated code safelyLangSmith Sandboxes give agents isolated, ephemeral environments to write and execute code without touching your core infrastructure.Explore the tiersBuildFor early-stage, VC-backed startups and founders. Apply now Benefits:Discounted seat pricingEligibility:First-time customerLess than $10M fundingHave raised at least $25K in seed fundingAdditional eligibility criteria may applyScaleFor early-stage startups backed by our premier VC partners.Apply now Benefits:LangSmith Credits: $10K in credits, available for 1 yearVIP Event Invites: Invitations to events with LangChain leadership team and other frontier f…

CommunityConnect with the LangChain CommunityMeet new peers, ask for advice, and share your knowledge. The LangChain Community is where you learn to build the agents of tomorrow.Meet our communityHelp ForumsNeed help with LangChain products or have questions about implementation? Connect with fellow builders for advice, share best practices, and explore answers in our community-run forums.Sign up Community SlackJump into our Slack and hang out with the LangChain developer community. Stay in the know on industry events, job opportunities, and projects other developers are building.Sign up Full story EventsMeet IRL or virtually with fellow LangChain enthusiasts. Stay in the loop by subscribing to our calendar for all the latest meetups, events, and hands-on workshops.Visit calendar .button-arrow-no-hover:hover .link-arrow { transform: translateX(-0.75rem); } .button-arrow-no-hovert:hover { color: var(--_v-2-colors---c-blue-light--500); } LangChain Community ChampionsInterested in becoming a Community Champion? Start by contributing to our open source packages.Start contributing Building LangChain open source frameworks is a team effort — over 3,500 amazing contributors have poured th…

Case StudiesHow Included Health Built Federated Agents for Healthcare Navigation with Deep Agents and LangGraphSofia SulikowskiSeptember 17, 20268min Go back to blogCreate agentsShare Included Health is an all-in-one healthcare platform that partners with employers and health plans to provide their employees and members with healthcare navigation to services like virtual primary care, behavioral health, urgent care, specialty care, and more. The product experience centers answering medical, financial, or administrative questions via Dot—an AI-powered healthcare guide built on top of a federated multi-agent architecture using Deep Agents and LangGraph.The challenge: healthcare navigation doesn't fit a decision treeHealthcare is one of the few domains where what a person asks for and what they actually need can be entirely different. A member asking "is an artery plaque scan covered by my insurance?" might, with a few follow-up questions, reveal that they are managing elevated cholesterol and have a family history of heart disease. The right response includes the dollar figure—but it may also mean recognizing an opportunity to encourage a conversation with a primary care physician.Hi…

Deep AgentsBuilding an Agent Harness for Life Sciences: Introducing Deep Life SciMichael CunninghamPrab SinghSeptember 17, 20265min Go back to blogCreate agentsShare Key TakeawaysPharma R&D costs have exploded over the past few decades. Agents have the potential to reverse this trend, but general AI tools lack the domain knowledge and data integrations life science actually needs.We built Deep Life Sci, an open source agentic assistant for clinical and lab scientists. It pulls directly from tens of millions of scientific articles, performs data analyses in a secure sandbox, and delegates tasks to hundreds of sub-agents.Deep Life Sci makes owning your intelligence simple. R&D teams can add their own data and context, and then use LangSmith tracing and evals to see what's actually working.Eroom’s law (hint: read Eroom backwards) is Moore’s law’s evil twin. The exponential drop in the price of computing power over the past 70 years has given us personal computers, the internet, cell phones, and now the AI revolution. Pharmaceutical research, unfortunately, has gone in the opposite direction, with the cost of developing each new drug doubling every nine years.AI agents have the potenti…

CustomersLangSmith powers top AI teams, from startups to global enterprisesSee how customers use LangSmith to build, ship, and improve agents in production. .dot-globe-wrap{width:100%;aspect-ratio:1/1;margin:0 auto;display:block} .dot-globe-wrap canvas{display:block;width:100%;height:100%;touch-action:none;cursor:grab} (function(){ const POINTS_RAW = "755,-282,592,-305,-950,65,-351,19,936,-322,797,511,516,-477,-712,23,914,-405,-378,-495,782,-9,699,-715,831,489,264,414,-291,-863,-736,-668,105,725,679,-115,284,851,442,665,667,336,756,-181,629,-770,-326,548,973,229,14,-671,-551,497,381,-526,-761,481,76,-874,242,-969,54,-145,392,908,-274,266,924,838,545,19,-64,972,228,231,202,952,13,-976,217,-544,-350,763,-470,745,473,921,-54,385,-56,956,287,633,765,123,823,100,559,-255,889,380,640,-82,-764,-287,788,-545,807,582,100,238,391,889,-583,-451,676,871,-403,281,723,-206,-659,650,-303,697,260,-616,-744,-247,354,-902,89,-994,-60,587,566,579,293,-593,-750,-175,304,937,-578,-504,642,43,954,298,340,590,732,-377,648,-662,775,-294,560,917,178,357,532,-419,-735,20,465,885,220,929,297,630,777,5,-229,369,901,810,-145,569,-71,784,-617,806,-528,268,404,-411,-817,281,901,331,-446,81,892,780,-416,468,103,-…

LangSmith EngineYour proactive agent engineerLangSmith Engine analyzes production traces, groups related failures, and recommends fixes so your team can improve agent quality faster.Get started Request a demo { "items": [ { "url": "https://vimeo.com/1197143848?fl=tl&fe=ec", "originalUrl": "https://vimeo.com/1197143848?fl=tl&fe=ec", "width": 940, "height": 529, "thumbnailUrl": "https://i.vimeocdn.com/video/2163412891-02cc544681116c7baea89a41e5a6e7f551333eb4163b80e3b6b6e736adaded66-d_1280?region=us", "html": "<iframe class=\"embedly-embed\" src=\"//cdn.embedly.com/widgets/media.html?src=https%3A%2F%2Fplayer.vimeo.com%2Fvideo%2F1197143848%3Fapp_id%3D122963&dntp=1&display_name=Vimeo&url=https%3A%2F%2Fvimeo.com%2F1197143848%3Ffl%3Dtl%26fe%3Dec&image=https%3A%2F%2Fi.vimeocdn.com%2Fvideo%2F2163412891-02cc544681116c7baea89a41e5a6e7f551333eb4163b80e3b6b6e736adaded66-d_1280%3Fregion%3Dus&type=text%2Fhtml&schema=vimeo\" width=\"940\" height=\"529\" scrolling=\"no\" title=\"Vimeo embed\" frameborder=\"0\" allow=\"autoplay; fullscreen; encrypted-media; picture-in-picture\" allowfullscreen=\"true\"></iframe>", "type": "video" } ], "group": "" } .agent-lightbox:hover .lightobox-play { scale: 0.9;…

Scaling Agents in Healthcare & Life SciencesAgent programs in healthcare and life sciences are being built under a different set of constraints than those in most industries. There’s plenty of upside if the constraints can be resolved. Success can mean hours of manual review compressed into minutes, data spread across a dozen systems finally queryable in one place, and clinicians getting time back from documentation. At the same time, the cost of a wrong answer can be higher here than almost anywhere else, which changes how teams build.September 15, 2026Create agentsShare Agent programs in healthcare and life sciences are being built under a different set of constraints than those in most industries. There’s plenty of upside if the constraints can be resolved. Success can mean hours of manual review compressed into minutes, data spread across a dozen systems finally queryable in one place, and clinicians getting time back from documentation. At the same time, the cost of a wrong answer can be higher here than almost anywhere else, which changes how teams build.Across payers, providers, and biopharma, we are seeing that earning the level of trust required to scale agents is much har…

Tutorials & How-TosAgent ArchitectureHow we built LangChain's Paid Media AgentAmal IrgashevDanny LambertJan GomezSeptember 13, 202619min Go back to blogCreate agentsShare Key TakeawaysTreat agents like knowledge workers. The strongest results came from giving the agent a well-designed workspace with a sandbox, software, business context, and clear operating instructions. The system prompt became a map that helped the agent find what it needed without carrying everything in context.Use models for judgment and code for consistency. Calculations, source-of-truth rules, and safeguards were better handled in code. That made the agent faster, cheaper, and more reliable, while the model focused on interpreting results and recommending what to do next.Design agents around the full workflow. The agent needed to find the right tools, work within clear permissions, and move from analysis to action. That meant proposing campaign changes, routing them through human approval, and verifying that the changes were applied correctly.Use abstractions to focus on the agent’s job. Managed Deep Agents manages hosting, sandboxes, Slack integration, and schedules, so you can focus on the tools, context, a…

Scaling Agents in Europe & The Middle East: Lessons from Schneider Electric, Vodafone, and monday.comNew Guide on Scaling Agents in Europe & the Middle East to see how Schneider Electric, Vodafone, and monday.com are approaching production AI at scale, from establishing shared agent platforms and LLMOps practices to designing multi-agent architectures with stronger observability, evaluation, and control.September 3, 2026Create agentsShare Agent programs in the region are taking a different path from the consumer-facing applications that get a lot of attention. Fewer teams are starting with a single flashy chatbot. More are starting with a platform, often because they already have a dozen agent proofs of concept scattered across business units, and no consistent way to bring them into production.This is a pattern we’re seeing appear across industries with very different levels of regulatory pressure. From energy and telecom to insurance, banking, and retail, the underlying challenge is consistent. Companies are finding agents easy to prototype and much harder to operate. Operating well requires an infrastructure layer that many teams did not anticipate when they built their first ag…

Featured storiesView AllLangChain LabsAgent ArchitectureObservability & EvalsCase Studies /* === CHECKED STATE === */ /* Span text color */ .v2-checkbox-field-blog:has(.w--redirected-checked) .v2-checkbox-label-blog { color: var(--_v-2-colors---c-blue-light--900); } /* Outer wrapper - gradient border */ .v2-checkbox-field-blog-stroke:has(.w--redirected-checked) { background-image: linear-gradient(#7fc8ff, #4c789940); } Filter by2All postsAgent ArchitectureCase StudiesCompany AnnouncementsConceptual GuideDeep AgentsDeploymentEngineeringHarrison's In the LoopLangChainLangChain LabsLangGraphLangSmithMax Agency PodcastNewsletterObservability & EvalsOpen SourcePartnerSystems at LangChainTutorials & How-TosThank you! Your submission has been received!Oops! Something went wrong while submitting the form. document.getElementById('email-form').addEventListener('keydown', function (e) { if (e.key === 'Enter') { e.preventDefault(); // stop native GET submit } }); Harrison's In the LoopWhat does it mean to "own your intelligence"?Harrison ChaseJuly 25, 20269minOpen SourceAgent ArchitectureLangChainBuilding a Harness with JevSydney RunkleHunter LovellSeptember 17, 20265minTutorials & How-TosAge…

Tutorials & How-TosHow we built LangChain’s GTM AgentThe LangChain TeamMarch 9, 202611min Go back to blogCreate agentsShare By Vishnu Suresh and Jess OuEvery outbound at LangChain used to start the same way: a rep toggling between tabs. Salesforce for the account record, Gong for call history, LinkedIn for the contact, the company website for context. Fifteen minutes of research before a single word was written, and no easy way to know if a teammate had already reached out yesterday. Inbound follow-up used to mean manually dropping the same message into Apollo for every new contact. We built a GTM agent that runs the process end-to-end. It triggers on new Salesforce leads, checks whether we should reach out, gathers context (including meeting history), and sends a Slack draft (with reasoning + sources) for the rep to approve. We built it on Deep Agents because this is a long-running, multi-step process that has to orchestrate multiple tools and large amounts of data reliably.Key resultsLead-to-qualified-opportunity conversion rate up 250% from December 2025 to March 2026, driving 3x more pipeline dollars in the same periodSince December, reps have increased their follow up with low…

Case StudiesHow Credit Genie uses OpenWiki to keep codebase knowledge fresh, searchable, and automatedKara KadriSeptember 10, 20266min Go back to blogCreate agentsShare Key TakeawaysCredit Genie needed a better way to keep codebase knowledge current. As its AI and ML Engineering teams scaled, docs in Notion, READMEs, and AGENTS.md files became stale and hard to find.OpenWiki turned documentation into part of the development lifecycle. Credit Genie uses OpenWiki to automatically generate and update repo-level documentation based on code changes.The team built a searchable portal across repositories. By aggregating OpenWiki docs into a GitHub Pages portal, Credit Genie gave engineers and stakeholders one place to search and understand systems.The system helps both people and coding agents. Engineers use the portal to understand unfamiliar systems, while coding agents are prompted to check the openwiki/ folder before making changes.Automation removed the maintenance burden. Nightly OpenWiki runs, automated PRs, auto-merge workflows, and daily portal rebuilds keep documentation fresh without relying on manual upkeep.OpenWiki reduced tribal knowledge. Important context is no longer lock…

Deep AgentsConnections: Managed credentials and per-caller identity for Managed Deep AgentsVictor MoreiraSeptember 9, 20268min Go back to blogCreate agentsShare Key TakeawaysKeep credentials out of your project. A connection lives in your LangSmith workspace, not in .env and not in the build. Rotate or revoke it without touching code or redeploying.Give each caller their own identity. A user-owned connection resolves to whoever is asking, so the ticket your agent files carries their handle rather than a bot’s.Skip the OAuth plumbing. Managed Deep Agents runs the authorization round-trip. No callback route, no token store, no refresh logic, no consent screen in your project.Connections are available now in Managed Deep Agents v0.7.0+.Every agent eventually needs to act on someone's behalf — search the web, file a ticket, open a pull request. Today that usually means one API key hard-coded across every deployment, and every action showing up under a service account. A key in .env answers what the agent may do. It has no way to answer who asked.That is what Connections fixes. A connection is a named credential in your LangSmith workspace that your tools read at run time, by slug, thro…

What is an AI sandbox?September 7, 2026Create agentsShare Key TakeawaysAn AI sandbox gives an agent an isolated workspace for running code and completing tasks while keeping host systems outside the execution boundary.An agent needs a sandbox when it runs generated code, especially when untrusted inputs can influence access to private data or external systems.A real sandbox requires more than a temporary directory or timed process. It combines filesystem and kernel isolation with controls for network access, compute, credentials, and retained state.A sandbox limits what a compromised agent can access or send, but it does not replace narrow tool permissions or human review for consequential actions.LangSmith Sandboxes make isolated execution part of deployment, so teams can manage sandbox policies alongside tracing, evals, and deployments through the same platform.An AI sandbox is an isolated execution environment with its own filesystem, processes, network policy, and kernel boundary. It lets an agent install packages, run code, and create artifacts without inheriting access to the machine that launched it.Agents can handle more complex tasks when they can read files, run code, and…

LangSmith vs Arize: AI agent observability, evals, and deployment comparedCompare LangSmith and Arize for AI agent engineering. Feature-by-feature breakdown of observability, evaluation, deployment, pricing, and migration. September 10, 2026Create agentsShare LangSmith is a fully framework-agnostic platform for agent engineering, combining observability, evaluation, and deployment so teams can iterate quickly. It is trusted by Harvey, Clay, Cloudflare, Cisco, and millions of developers worldwide. Both LangSmith and Arize provide tracing and evals for LLM applications and AI agents in production. However, LangSmith supports the full Agent Development lifecycle, from traces to evals to deployment, in one platform, and isn't just for those in the LangChain/LangGraph ecosystem.Full-lifecycle agent engineering in one platformProduction traces that feed directly into evals and improvementsBuilt-in deployment for stateful agentsGet a demo of LangSmith's agent engineering platformWhat sets LangSmith apart from Arize?Arize earns G2 praise for intuitive navigation and responsive support. Its OpenTelemetry (aka OTel)-native instrumentation is strong, making it a capable monitoring platform fo…

LangSmith SandboxesGive agents a secure computerEphemeral, isolated sandboxes designed for agent-generated code.Get started Request a demo { "items": [ { "url": "https://vimeo.com/1213434778", "originalUrl": "https://vimeo.com/1213434778", "width": 940, "height": 529, "thumbnailUrl": "https://i.vimeocdn.com/video/2184102339-98b6361747bddc1f1f4ff6d0075496b1d23a337f1935ea99f41102fdd2f177de-d_1280?region=us", "html": "<iframe class=\"embedly-embed\" src=\"//cdn.embedly.com/widgets/media.html?src=https%3A%2F%2Fplayer.vimeo.com%2Fvideo%2F1213434778%3Fapp_id%3D122963&dntp=1&display_name=Vimeo&url=https%3A%2F%2Fvimeo.com%2F1213434778&image=https%3A%2F%2Fi.vimeocdn.com%2Fvideo%2F2184102339-98b6361747bddc1f1f4ff6d0075496b1d23a337f1935ea99f41102fdd2f177de-d_1280%3Fregion%3Dus&type=text%2Fhtml&schema=vimeo\" width=\"940\" height=\"529\" scrolling=\"no\" title=\"Vimeo embed\" frameborder=\"0\" allow=\"autoplay; fullscreen; encrypted-media; picture-in-picture\" allowfullscreen=\"true\"></iframe>", "type": "video" } ], "group": "" } .agent-lightbox:hover .lightobox-play { scale: 0.9; } .w-lightbox-backdrop { z-index: 9999; } Helping top teams ship great agentsUse cases in production img[alt="BRI…

LangSmith FleetAgents for the whole companyGive every team the ability to build agents, use them in apps they already rely on, and manage them with security and control.Start building Get a demo .mask { position: fixed; top: 0; left: 0; width: 100vw; height: 100vh; pointer-events: none; z-index: 10; will-change: mask-image, -webkit-mask-image; -webkit-mask-image: radial-gradient(circle 0px at 0px 0px, black 0%, transparent 100%); mask-image: radial-gradient(circle 0px at 0px 0px, black 0%, transparent 100%); display: none; } @media (min-width: 992px) { .mask { display: block; } } .mask img { position: absolute; } document.addEventListener("DOMContentLoaded", () => { const section = document.querySelector(".product_hero-section"); const masks = document.querySelectorAll(".mask"); if (!section || !masks.length) return; const MAX_RADIUS = 300; const LERP = 0.15; const THRESHOLD = 0.5; const states = Array.from(masks, () => ({ x: 0, y: 0, r: 0, tx: 0, ty: 0, tr: 0 })); let isInside = false; let isDesktop = window.innerWidth >= 992; // Update breakpoint on resize instead of checking every frame/mousemove window.addEventListener("resize", () => { isDesktop = window.innerWidth >= 992; }, …

LangSmith Observability: AI Agent Observability PlatformKnow what your agents are really doingLangSmith Observability gives you complete visibility into agent behavior.‍Trace your preferred framework or integrate LangSmith with any agent stack using our Python, Typescript, Go, or Java SDKs.Start building Get a demo .mask { position: fixed; top: 0; left: 0; width: 100vw; height: 100vh; pointer-events: none; z-index: 10; will-change: mask-image, -webkit-mask-image; -webkit-mask-image: radial-gradient(circle 0px at 0px 0px, black 0%, transparent 100%); mask-image: radial-gradient(circle 0px at 0px 0px, black 0%, transparent 100%); display: none; } @media (min-width: 992px) { .mask { display: block; } } .mask img { position: absolute; } document.addEventListener("DOMContentLoaded", () => { const section = document.querySelector(".product_hero-section"); const masks = document.querySelectorAll(".mask"); if (!section || !masks.length) return; const MAX_RADIUS = 300; const LERP = 0.15; const THRESHOLD = 0.5; const states = Array.from(masks, () => ({ x: 0, y: 0, r: 0, tx: 0, ty: 0, tr: 0 })); let isInside = false; let isDesktop = window.innerWidth >= 992; // Update breakpoint on resize ins…

langgraphBalance agent control with agencyDesign agents that reliably handle complex tasks with LangGraph, an agent runtime and low-level orchestration framework.Start building Read the docs Trusted by companies shaping the future of agentsUse cases in production img[alt="BRIDGEWATER"] { position: relative; top: -12px; } How does LangGraph help?Guide, moderate, and control your agent with human-in-the-loopPrevent agents from veering off course with easy-to-add moderation and quality controls. Add human-in-the-loop checks to steer and approve agent actions.Add human-in-the-loop Build expressive, customizable agent workflowsLangGraph’s low-level primitives provide the flexibility needed to create fully customizable agents. Design diverse control flows — single, multi-agent, hierarchical — all using one framework.See different agent architectures Persist memory for future interactionsLangGraph’s built-in memory stores conversation histories and maintains context over time, enabling rich, personalized interactions across sessions.Learn about agent memory First-class streaming for better UX designBridge user expectations and agent capabilities with native token-by-token streaming, showi…

Terms of ServiceCreate agentsLangChain Terms of ServiceLast updated: June 02, 2026These Terms of Service (together with any applicable Order Forms, exhibits, and incorporated attachments, the “Agreement”) govern access to and use of the LangSmith Platform and are entered into by and between LangChain Inc., a Delaware corporation (“LangChain”), and the individual or entity (“Customer”) that: (a) enters into an Order Form that expressly incorporates this Agreement by reference; or (b) accesses or uses the LangSmith Platform (including via a Free Access Plans, as defined below). If the individual accepting this Agreement is accepting on behalf of a company or other legal entity, such individual represents that they have the authority to bind Customer to the terms and conditions of this Agreement. If the individual accepting this Agreement does not have such authority or does not agree with the terms of the Agreement, such individual must not accept this Agreement and may not use the LangSmith Platform. Capitalized terms shall have the meaning outlined in Section 1 (Definitions) and others are defined contextually in this Agreement.1. Definitions “Affiliate” means an entity that owns o…

CompanyEnabling every company to own their intelligenceLangChain provides the open agent engineering platform and open source frameworks teams need to build, control, and own their agent intelligence.Our missionWe believe that LLMs are extremely powerful. They are more powerful when put to work through agents that can use data and take actions. Generic AI can get a company started, but real agent advantage comes from adapting that intelligence to your own workflows, customers, policies, and tools. Our mission is to enable every company to own their intelligence.We develop open source projects to stay ahead of the best patterns for building agents. Then, we incorporate these learnings into LangSmith - our commercial agent engineering platform. LangSmith gives companies control over the layers that matter, like models, context, and deployment, so they can own their agent intelligence and keep improving it, whether they build on our open source frameworks or not.The LangChain storyLangChain started as Harrison Chase's side project in late 2022. It was a single Python package pushed from a personal GitHub account with no grand plan behind it. Then ChatGPT launched, and everything chang…

Built with LangGraphHear how industry leaders use LangGraph to ship powerful, production-ready AI applications.Start building Get a demo LinkedInUberKlarnaElasticAppfolio .home_cards-toc-link.w--current .cards-toc-circle { opacity: 100%; } .home_cards-toc-link .cards-toc-circle { opacity: 0%; } const mq = window.matchMedia('(max-width: 768px)'); function init() { if (!mq.matches) return; const wrapper = document.querySelector('.home_cards-toc-wrapper'); if (!wrapper) return; const observer = new MutationObserver(() => { const activeLink = wrapper.querySelector('.w--current'); if (!activeLink) return; const targetLeft = activeLink.offsetLeft - wrapper.offsetLeft - wrapper.offsetWidth / 2 + activeLink.offsetWidth / 2; try { wrapper.scrollTo({ left: targetLeft, behavior: 'smooth', }); } catch (e) { wrapper.scrollLeft = targetLeft; } }); wrapper.querySelectorAll('.home_cards-toc-link').forEach((link) => { observer.observe(link, { attributes: true, attributeFilter: ['class'] }); }); } init(); if (mq.addEventListener) { mq.addEventListener('change', init); } else if (mq.addListener) { mq.addListener(init); } @media only screen and (max-width: 992px) { .home_cards-toc-link { min-width: fi…