Listing Thumbnail

    LangSmith Agent Engineering Platform (Self-Hosted)

     Info
    Sold by: LangChain 
    Deployed on AWS
    LangSmith provides tools for developing, debugging, and deploying LLM applications. It helps you trace requests, evaluate outputs, test prompts, and manage deployments in one place. LangSmith is framework agnostic, so you can use it with or without LangChain open-source libraries langchain and langgraph. Prototype locally, then move to production with integrated monitoring and evaluation to build more reliable AI systems. LangSmith provides: - Observability to see exactly how your agent thinks and acts with detailed tracing and aggregate trend metrics. - Evaluation to test and score agent behavior on production data and offline datasets for continuous improvement. - Deployment to ship your agent in one click, using scalable infrastructure built for long-running tasks.
    4.5
    These options are for LangSmith Agent Engineering Platform (Self-Hosted).
    View 1 other option

    Overview

    Play video

    LangSmith Observability and Evals is a unified observability & evals platform where teams can debug, test, and monitor AI app performance - whether building with LangChain or not.

    Find failures fast with agent observability. Quickly debug and understand non-deterministic LLM app behavior with tracing. See what your agent is doing step by step, then fix issues to improve latency and response quality.

    Evaluate your agent's performance. Evaluate your app by saving production traces to datasets, then score performance with LLM-as-Judge evaluators. Gather human feedback from subject-matter experts to assess response relevance, correctness, harmfulness, and other criteria.

    Experiment with models and prompts in the Playground, and compare outputs across different prompt versions. Any teammate can use the Prompt Canvas UI to directly recommend and improve prompts.

    Track business-critical metrics like costs, latency, and response quality with live dashboards, then get alerted when problems arise and drill into root cause.

    LangSmith Deployments is a purpose-built infrastructure and management layer for deploying and scaling long-running, stateful agents -- offering:

    • 1-click deployment to go live in minutes,
    • 30 API endpoints for designing custom user experiences that fit any interaction pattern
    • Horizontal scaling to handle bursty, long-running traffic
    • A persistence layer to support memory, conversational history, and async collaboration with human-in-the-loop or multi-agent workflows
    • Native LangSmith Studio, the agent IDE, for easy debugging, visibility, and iteration

    LangSmith Agent Builder: Give every team the ability to build, use, and improve AI agents with the security your org requires.

    Highlights

    • LangSmith Observability and Evals is a unified observability & evals platform where teams can debug, test, and monitor AI app performance - whether building with LangChain or not. Quickly debug and understand non-deterministic LLM app behavior with tracing. See what your agent is doing step by step, then fix issues to improve latency and response quality.
    • LangSmith Deployments is a purpose-built infrastructure and management layer for deploying and scaling long-running, stateful agents offering 1/1-click deployment to go live in minutes, 2/Horizontal scaling to handle bursty, long-running traffic 3/A persistence layer to support memory, conversational history, and async collaboration with human-in-the-loop or multi-agent workflows.
    • Please note: there is a $150k annual Platform License plus a minimum $150k annual usage commitment to access this package. To discuss enterprise pricing or to activate your commitment and obtain your license key after signup, please contact us at https://www.langchain.com/contact-sales - alternatively, our self-serve cloud-based products are available at https://www.langchain.com

    Details

    Delivery method

    Supported services

    Delivery option
    LangSmith Helm Chart

    Latest version

    Operating system
    Linux

    Deployed on AWS

    Features and programs

    Trust center

    Trust center
    Access real-time vendor security and compliance information through their Trust Center powered by Drata or Vanta. Review certifications and security standards before purchase.

    Financing for AWS Marketplace purchases

    AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
    Financing for AWS Marketplace purchases

    Pricing

    LangSmith Agent Engineering Platform (Self-Hosted)

     Info
    Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
    Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator  to estimate your infrastructure costs.

    Usage costs (5)

     Info
    Dimension
    Cost/unit
    Per Trace
    $0.01
    Per Agent Run
    $0.01
    Metered Usage Amount
    $0.01
    Minimum annual usage commitment, billed in advance
    $150,000.00
    Per Agent Builder Run
    $0.10

    AI Insights

     Info

    Dimensions summary

    You pay for what you use across five independent metering dimensions. Per Trace charges cover observability data captured when your agents run. Per Agent Run and Per Agent Builder Run charge for agent executions on the platform. Metered Usage Amount tracks normalized compute and storage consumption from deployments, engine analysis, and related services. The Minimum annual usage commitment is billed in advance, setting a baseline you draw down against as usage accrues. These dimensions add together based on actual consumption, so your total scales with trace volume, agent activity, and resources used.

    Top-of-mind questions for buyers

    A trace is a single execution of your application—an agent run, evaluator, or playground session. One trace can include many steps, such as model calls and other tracked events. All those steps roll up into the single trace you are billed for.
    It tracks normalized units of work and storage across services. Compute-related work is measured in LangChain Compute Units, and data stored or managed is measured in LangChain Storage Units. Deployments, engine analysis, and sandboxes all consume these units at different rates based on the resources they use.
    It depends on your workload. High trace volume from heavy observability pushes Per Trace charges up. Running agents in production drives Per Agent Run and Metered Usage Amount through deployment uptime and engine analysis. All dimensions bill independently and add together on one invoice based on actual consumption.
    www.langchain.com
    Helpful?

    Custom pricing options

    Request a private offer to receive a custom quote.

    How can we make this page better?

    Tell us how we can improve this page, or report an issue with this product.
    Tell us how we can improve this page, or report an issue with this product.

    Legal

    Vendor terms and conditions

    Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .

    Content disclaimer

    Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.

    Usage information

     Info

    Delivery details

    LangSmith Helm Chart

    Supported services: Learn more 
    • Amazon EKS
    Helm chart

    Helm charts are Kubernetes YAML manifests combined into a single package that can be installed on Kubernetes clusters. The containerized application is deployed on a cluster by running a single Helm install command to install the seller-provided Helm chart.

    Version release notes

    LangSmith 0.13.14 release

    Additional details

    Usage instructions

    See https://docs.smith.langchain.com/self_hosting  for full installation and configuration instructions.

    Resources

    Support

    Vendor support

    AWS infrastructure support

    AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.

    Similar products

    Customer reviews

    Ratings and reviews

     Info
    4.5
    152 ratings
    5 star
    4 star
    3 star
    2 star
    1 star
    71%
    28%
    1%
    0%
    0%
    0 AWS reviews
    |
    152 external reviews
    External reviews are from G2 .
    satvick m.

    Modular, Vendor-Independent Framework for Powerful Agentic LLM Workflows

    Reviewed on Nov 05, 2026
    Review provided by G2
    What do you like best about the product?
    I value the modularity and vendor independence, which make it faster and more flexible to build complex Large Language Model (LLM) applications. Agentic Workflows: Through tools like the core framework and companion runtimes like LangGraph, it enables agents to plan, reason, and execute multi-step tasks autonomously.
    What do you dislike about the product?
    LangChain takes relatively simple tasks—like calling an LLM or formatting a prompt with Python f-strings—and wraps them in heavy layers of custom classes, chains, and routing logic (such as LCEL or Runnable sequences). As a result, otherwise straightforward logic can become hard to follow, trace, or debug when something breaks.
    What problems is the product solving and how is that benefiting you?
    Vendor lock-in and model switching: moving from one provider (like OpenAI) to another (like Anthropic or Llama) usually means rewriting custom API layers. LangChain offers a unified interface, so switching models can be minimal—sometimes even a single-line change. Raw LLMs are stateless and don’t inherently remember previous conversation turns. LangChain includes built-in memory management modules that help persist and recall context across interactions.
    Biotechnology

    Flexible Agentic Workflows with LangChain and LangGraph

    Reviewed on Nov 05, 2026
    Review provided by G2
    What do you like best about the product?
    What I like most about LangChain is the flexibility it gives me when building agentic workflows. I work with systems that involve multiple tools, agents, models, and external data sources, and LangChain makes it fairly easy to connect those pieces without locking me into one specific setup. I especially like the LangGraph ecosystem for workflows where I need more control over state, tool execution, and how agents interact. It has also been useful that I can start experimenting quickly and then gradually make the system more structured as the project grows.
    What do you dislike about the product?
    The main downside for me is that the ecosystem has gotten pretty large, so it can sometimes be difficult to figure out which abstraction or package I should actually be using. Between LangChain, LangGraph, LangSmith, the different provider integrations, and newer agent tooling, there is a bit of a learning curve even if you already know the basics. I also find that debugging can get frustrating once an agent workflow becomes more complex. Sometimes I want to understand exactly what is happening underneath the framework, and the extra abstraction makes that harder than working directly with the underlying APIs. The documentation has improved a lot, but I still occasionally end up jumping between different pages or examples to figure out the current recommended approach.
    What problems is the product solving and how is that benefiting you?
    I mainly use LangChain to design domain-specific agent harnesses for scientific and drug discovery workflows, both in my work at Genentech and in my PhD research. These systems often need to connect models with scientific tools, data sources, and multi-step reasoning workflows, so having a common framework for putting those pieces together is very useful. For me, the biggest benefit is being able to experiment with different agent designs without having to build all of the orchestration from scratch each time. I can prototype a workflow, swap models or tools, change how the agents interact, and gradually make it more structured as the research evolves. That makes it especially useful for research projects where the workflow itself is still being figured out.
    Financial Services

    Easy to learn: syntax is quickly mastered

    Reviewed on Oct 27, 2026
    Review provided by G2
    What do you like best about the product?
    It's easy to learn, the syntax is quickly learned
    What do you dislike about the product?
    It requires installing many Python components on Windows
    What problems is the product solving and how is that benefiting you?
    Created an agent with Ollama for cybersecurity activities
    Subrata D.

    Essential framework for extracting fundamental data for stock scoring.

    Reviewed on Oct 24, 2026
    Review provided by G2
    What do you like best about the product?
    Langchain makes it incredibly easy for me to connect AI models to my external data sources. I use it to build data pipelines that can parse complex corporate earnings PDFs and extract the key financial metrics straight into my Python-based fundamental stock-scoring models.
    What do you dislike about the product?
    The framework gets updated very frequently. I appreciate the new features, but the constant changes sometimes break backward compatibility with my older algorithmic trading scripts, which means I have to do manual maintenance to keep everything working.
    What problems is the product solving and how is that benefiting you?
    It automates my core fundamental analysis. Rather than manually reading through quarterly reports, my Langchain scripts automatically extract and summarize the sentiment, then feed that information straight into my broader equity analysis workflow for the NSE and BSE.
    Abinash D.

    Langchain Makes Agent Orchestration and Observability Easy

    Reviewed on Oct 21, 2026
    Review provided by G2
    What do you like best about the product?
    Langchain helps me create Agent Orchestrations with single API Call making Tool calling, state, retries, and more importantly observability easy, i love its community support and sdk
    What do you dislike about the product?
    it has a lot of Abstractions, and every package update brings a lot of breaking Changes, and Docs sometimes are not up to date sometimes feel instability to maintain the app.
    What problems is the product solving and how is that benefiting you?
    Langchain fills the gap between my API vendor and my app, helping me build faster and try llm features and move to different Api vendor with slight to very no code modifications
    View all reviews