LangSmith Agent Engineering Platform (Self-Hosted) logo

    LangSmith Agent Engineering Platform (Self-Hosted)

    Sold by
    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.

    Ratings and reviews

    4.5
    151 ratings
    2 star
    1 star
    71%
    28%
    1%
    0%
    0%
    0 AWS reviews
    |
    151 external reviews
    External reviews are from G2 .

    Filters

    Review type

    AWS Marketplace reviews
    External reviews
    Reviews (151)
    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
    Shashank S.

    LangChain Simplifies Building and Connecting LLM Applications

    Reviewed on Oct 15, 2026
    Review provided by G2
    What do you like best about the product?
    I like LangChain because it makes building LLM-powered applications more flexible and organized. Its prompt templates, model integration, documents loaders, text splitters, retrievers, and vector store integrations help connect different components into a single workflow. I also find its RAG capabilities useful for working with external data, while tool calling helps connect language models with other services. The documentations and integration options make it easier to experiment with different approaches when developing AI applications.
    What do you dislike about the product?
    One downside of LangChain is that the learning curve can be steep when working with complex chains, agents, and integration. Debugging workflows sometimes takes extra time, especially when multiple components are connected. Frequent updates and changes between versions can also require code adjustments. Clearer error messages and more consistent documentation across integrations would make the development experience smoother.
    What problems is the product solving and how is that benefiting you?
    LanChain helps me build and experiment with LLM-powered application by connecting language models with prompts, external data, and tools. It is useful for organizing multi-step workflows, working with document retrieval, and building retrieval-augmented generation (RAG) pipelines. It also makes it easier to integrate different model providers and manage chains of operations, reducing the amount of custom code needed for common tasks.
    Roshan P.

    LangChain Makes Building Flexible AI Workflows Fast and Straightforward

    Reviewed on Oct 14, 2026
    Review provided by G2
    What do you like best about the product?
    What I like most about LangChain is how straightforward it makes building AI applications and connecting different language models to external tools and data sources. I also appreciate the flexibility it provides for creating workflows and trying out different models as I iterate. Overall, it saves me development time and makes it easier to manage and improve AI projects without having to build everything from scratch.
    What do you dislike about the product?
    One thing I dislike about LangChain is that it can feel a bit complicated to get started, especially when you’re dealing with different integrations and configuration options. At times, debugging takes longer than I expect, partly because the framework is updated frequently and things change from version to version. The documentation is helpful overall, but I think some examples could be simpler and more beginner-friendly, with clearer steps that are easier to follow.
    What problems is the product solving and how is that benefiting you?
    LangChain helps address the challenge of building AI applications that need to connect language models with external data, APIs, and other tools. It makes it easier to design AI-powered workflows without having to write everything from scratch. For me, that means less development time spent on boilerplate, smoother integration across components, and a more efficient way to build and test AI solutions.
    Mahwish Q.

    Speeds Up RAG App Builds, but Abstractions and Breaking Changes Can Frustrate

    Reviewed on Oct 12, 2026
    Review provided by G2
    What do you like best about the product?
    Langchain's greatest strength is how dramatically it speeds up AI application development through its flexible, model-agnostic framework
    What I like best is its rich ecosystem of pre-built integrations, which makes connecting LLMs to vector database and external data sources for RAG workflows virtually effortless. While the high level of abstraction cam occasionally make debugging tricky, the massive amount of boilerplate code it saves makes Langchain an essential toolkit for building scalable AI applications.
    What do you dislike about the product?
    What developers typically dislike about LangChain is its heavy reliance on over-engineered abstractions, which often wraps straightforward API calls in multiple layers of complex classes and makes debugging stack traces unnecessarily difficult. Additionally, the fast-moving nature of the framework frequently introduces breaking changes and outdated documentation, while adding dependency bloat and friction for simple use cases that would otherwise be handled in a few lines of raw python.
    What problems is the product solving and how is that benefiting you?
    Langchain directly addresses the critical bottleneck of context, engineering and operational friction when bridging raw Large language Models with production software. By providing unified abstractions, it solves the fragmentation of model APIs, the complexity of data ingestion for Retrieval-Augmented Generation (RAG), and the tedious state management required for conversational memory and multi-step agent workflows.
    Shobha D.

    Build AI Apps Fast with Less Glue Code

    Reviewed on Oct 12, 2026
    Review provided by G2
    What do you like best about the product?
    What I like most is how fast you can build things. It handles all the messy glue work between the AI model, prompts, and external data. Instead of writing tons of code from scratch, you can connect the pieces together and test a working app in hours.
    What do you dislike about the product?
    It feels too bloated and complicated for simple tasks. They hide basic things under too many layers, so when something breaks, debugging is painful. Plus, the library changes so fast that old code breaks constantly, and finding clear, up-to-date documentation can be a real headache.
    What problems is the product solving and how is that benefiting you?
    Before LangChain, connecting an AI model to your own files and databases took endless repetitive code. LangChain solves that by providing ready-made building blocks. It benefits me by cutting down setup time, letting me focus on the actual app logic rather than wiring everything manually.
    RaHul K.

    Great modular framework for RAG and agents, though documentation can be confusing

    Reviewed on Oct 10, 2026
    Review provided by G2
    What do you like best about the product?
    What I Like (Pros):
    Massive collection of integrations with various vector stores, models, and APIs.
    Speeds up prototyping and building complex LLM-powered applications significantly.
    Strong community support and pre-built components for standard AI tasks.
    What do you dislike about the product?
    What I Dislike
    Rapid updates and shifting abstractions mean that breaking changes can happen frequently, requiring constant code maintenance.
    Documentation can sometimes be tricky to navigate due to the fast-paced evolution of the framework.
    What problems is the product solving and how is that benefiting you?
    The Problem It Solves:
    Our development team needed a structured, modular way to connect large language models with external data sources, prompt templates, and memory components without writing complex boilerplate code from scratch.
    How We Are Using It (How it's solving the problem):
    We use LangChain at our workplace to orchestrate our LLM workflows, build retrieval-augmented generation (RAG) pipelines, and manage multi-step agent interactions efficiently