LangSmith Integrations

LangChain provides a comprehensive framework that empowers developers to build and scale intelligent applications using large language models (LLMs). By integrating data and APIs, LangChain enables context-aware applications that can perform reasoning tasks. The suite includes LangGraph, a tool for orchestrating complex workflows, and LangSmith, a platform for monitoring and optimizing LLM-driven agents. LangChain supports the full lifecycle of LLM applications, offering tools to handle everything from initial design and deployment to post-launch performance management. Its flexibility makes it an ideal solution for businesses looking to enhance their applications with AI-powered reasoning and automation.

Achieve enhanced precision and control through LangGraph, enabling the creation of agents capable of efficiently managing intricate tasks. The LangGraph Platform facilitates the development and scaling of agent-driven applications. With its adaptable framework, LangGraph accommodates various control mechanisms, including single-agent, multi-agent, hierarchical, and sequential flows, effectively addressing intricate real-world challenges. Reliability is guaranteed by the straightforward integration of moderation and quality loops, which ensure agents remain focused on their objectives. Additionally, LangGraph Platform allows you to create templates for your cognitive architecture, making it simple to configure tools, prompts, and models using LangGraph Platform Assistants. Featuring inherent statefulness, LangGraph agents work in tandem with humans by drafting work for review and awaiting approval prior to executing actions. Users can easily monitor the agent’s decisions, and the "time-travel" feature enables rolling back to revisit and amend previous actions for a more accurate outcome. This flexibility ensures that the agents not only perform tasks effectively but also adapt to changing requirements and feedback.

dcode is a versatile open-source terminal coding assistant designed specifically for developers and software teams. Utilizing the Deep Agents SDK, it enables the planning and execution of coding tasks, allows for the inspection and editing of project files, runs various tools, and can assign work to subagents. Its interactive terminal interface provides a continuous stream of responses and facilitates the resumption of conversations across different sessions, while the headless mode is tailored for scripted and CI workflows. Users can choose from a range of compatible model providers and input their own credentials, enabling them to customize aspects such as models, tools, plugins, skills, memory, middleware, hooks, and approval rules. The platform offers the option to approve or reject tool calls, and supports code execution both locally and in designated remote sandboxes. Furthermore, dcode is compatible with MCP tools and can integrate with LangSmith to track prompts, responses, tool calls, errors, and token utilization. Overall, it is designed for developers seeking to configure and examine an AI coding agent, rather than relying on a pre-defined coding assistant, thus fostering a more tailored coding experience. This flexibility makes it an appealing choice for those who prioritize customization and control in their development processes.

evalship is quality control for LLM evals, delivered as a GitHub App. Setup is one line for a coding agent such as Claude Code or Codex: the agent reads your evals, finds the test cases that can't fail, and opens a pull request that wires them into CI. From then on, each pull request gets a comment naming the evals the change broke, the likely cause in the diff, the flaky evals left out, and any new AI call without an eval. When you want better results or lower bills, Optimize has your agent run experiments on your prompts and models, and evalship tells you which variants beat the current one beyond chance. You pick what ships. evalship sits next to Langfuse, Braintrust, LangSmith or promptfoo rather than replacing them, and your evals keep running on your own infrastructure.

Simplify your MLOps pipelines. ZenML allows you to manage, deploy and scale any infrastructure. ZenML is open-source and free. Two simple commands will show you the magic. ZenML can be set up in minutes and you can use all your existing tools. ZenML interfaces ensure your tools work seamlessly together. Scale up your MLOps stack gradually by changing components when your training or deployment needs change. Keep up to date with the latest developments in the MLOps industry and integrate them easily. Define simple, clear ML workflows and save time by avoiding boilerplate code or infrastructure tooling. Write portable ML codes and switch from experiments to production in seconds. ZenML's plug and play integrations allow you to manage all your favorite MLOps software in one place. Prevent vendor lock-in by writing extensible, tooling-agnostic, and infrastructure-agnostic code.

Disco.dev serves as an open-source personal hub designed for the integration of the Model Context Protocol (MCP), enabling users to easily discover, launch, customize, and remix MCP servers without any setup or infrastructure burdens. This platform offers convenient plug-and-play connectors alongside a collaborative workspace that allows users to quickly deploy servers using either CLI or local execution methods. Users can also delve into community-shared servers, remix them, and adapt them for their specific workflows. By eliminating infrastructure constraints, this efficient approach not only speeds up the development of AI automation but also makes agentic tools more accessible to a broader audience. Additionally, it encourages collaborative efforts among both technical and non-technical users, promoting a modular ecosystem that embraces remixability and innovation. Overall, Disco.dev stands as a pivotal resource for those looking to enhance their MCP experience without traditional limitations.

Voker serves as an innovative Agent Analytics Platform that focuses on the oversight and enhancement of AI agents operating in real-world settings, ensuring that these agents are not merely reactive but genuinely beneficial. This platform enables developers to monitor the interactions of AI agents, pinpoint areas needing improvement, identify any irregularities, and assess progress over time, all without the hassle of sifting through extensive logs or relying solely on user feedback. By linking the performance metrics of agents to tangible business results, Voker allows teams to correlate conversational insights with existing user data, providing clarity on whether an agent is effectively contributing to goals such as user activation, retention, conversion rates, support quality, and other key performance indicators. The user-friendly self-service analytics are tailored for product managers, analysts, and business teams, offering them actionable insights without the issues of support tickets or workflow interruptions. Additionally, developers can easily integrate Voker into their systems using the SDK; they can do this via a simple pip install command or leverage an AI coding tool to quickly set up the SDK, input the necessary API key, and configure an agent within just a few minutes. Thus, Voker not only streamlines the monitoring process but also empowers teams to leverage data for continuous improvement of their AI agents.

Deep Agents serves as an open-source library and agent framework designed for the creation of LLM-driven agents capable of executing multi-step tasks. This library features an agent loop equipped with functionalities such as planning, persistent memory, file-system access, and the ability to delegate tasks to subagents, while also enabling developers to connect various model providers and tools seamlessly. Aimed at software developers and teams focused on crafting tailored agent applications, it supports diverse workflows including research, programming, and other scenarios necessitating planning and action across multiple steps. Additionally, developers have the flexibility to enhance the framework's capabilities by incorporating custom tools, middleware, and backends, while also integrating with LangGraph and LangSmith for effective orchestration, tracing, and deployment processes. Ultimately, Deep Agents functions as a foundational software development framework, empowering users to create and operate agents within their specific applications and environments, rather than providing a pre-built agent for end-users. This versatility makes it an invaluable asset for those looking to innovate in the realm of agent-based application development.

Reflexio serves as a platform for developers focused on the creation and management of AI agents, utilizing a variety of input methods such as an SDK, REST API, CLI, or connections to supported tracing platforms to gather data from agent interactions, execution traces, tool calls, and user corrections. By identifying common failures, it generates reusable playbooks and user profiles that enhance the learning process. When an agent is in operation, it can access pertinent guidance derived from these learnings prior to formulating a response. The Hosted Enterprise portal provides teams with the capability to explore, modify, approve, reject, search, and assess the acquired knowledge effectively. Reflexio enables agents to implement necessary corrections across various interactions without needing to alter the underlying model weights. Additionally, teams have the flexibility to utilize the managed cloud service, set up their own model-provider keys, or opt for self-hosting on platforms like AWS, Google Cloud, or Azure. Furthermore, enterprise trace imports are supported from sources such as Braintrust, Langfuse Cloud, and LangSmith Cloud, while Reflexio also features a mem0 wrapper and integration with OpenClaw, thus offering a comprehensive suite of tools for enhancing agent performance. This multifaceted approach ensures that developers can optimize their AI agents while leveraging the flexibility of various deployment options.

Prism serves as the desktop AI engineering solution from Navier AI, tailored for teams engaged in hardware, mechanical, aerospace, and various engineering disciplines. This comprehensive platform integrates parametric CAD, 3D visualization, physics simulations, code editing, and reporting functionalities all within a single application. Users have the ability to articulate a part or study using natural language, refine or create CAD designs, and leverage AI agents to configure and execute physics solvers, craft scripts, assess results, and produce visual outputs such as plots, dashboards, reports, or presentation slides. The catalog of solvers encompasses 12 distinct families, including notable options like OpenFOAM, SU2, CalculiX, Elmer, Project Chrono, and OpenModelica, in addition to Navier AI’s proprietary Ferro solver. Engineers can seamlessly import STEP files, evaluate scripts, meshes, and solver inputs, while also running multiple agents concurrently to investigate various design avenues. Prism is compatible with Windows, macOS, and Linux operating systems, with local solver workflows executed directly on the user’s machine. The agent necessitates an internet connection and transmits the information it processes to Navier AI’s backend model for analysis. Additionally, users have the option to utilize cloud computing resources for executing approved solver tasks, enhancing flexibility and efficiency in their engineering projects. This amalgamation of features empowers engineers to optimize their workflow and improve design outcomes.

Transitioning from development to production, as well as from traditional data engineering to artificial intelligence, requires securing the various environments, pipelines, tools, and open-source components integral to your data and AI supply chain. It is essential to continuously identify, prevent, and rectify security and compliance vulnerabilities in AI before they reach production. In addition, monitoring AI applications in real-time allows for the detection and mitigation of adversarial AI attacks while enforcing specific application guardrails. Noma integrates smoothly across your data and AI supply chain and applications, providing a detailed map of all data pipelines, notebooks, MLOps tools, open-source AI elements, and both first- and third-party models along with datasets, thereby automatically generating a thorough AI/ML bill of materials (BOM). Additionally, Noma constantly identifies and offers actionable solutions for security issues, including misconfigurations, AI-related vulnerabilities, and non-compliant training data usage throughout your data and AI supply chain. This proactive approach enables organizations to enhance their AI security posture effectively, ensuring that potential threats are addressed before they can impact production. Ultimately, adopting such measures not only fortifies security but also boosts overall confidence in AI systems.

AgentForge serves as a robust SaaS platform dedicated to simplifying the creation and personalization of AI agents. With its fully integrated NextJS boilerplate, users can efficiently build, deploy, and evaluate AI applications. The platform boasts a variety of pre-built AI agents, customizable graphs, reusable UI components, and an interactive playground for hands-on experimentation. Furthermore, AgentForge seamlessly connects with widely-used AI tools like Langchain, Langgraph, Langsmith, OpenAI, Groq, and Llamma, providing essential components for AI application development. Its features include observability through Langsmith and access to over 20 themes via daisyUI, making it suitable for both small-scale projects and more complex endeavors. The pricing structure is straightforward, requiring only a one-time payment for lifetime access to all features, updates, and enhancements, thus avoiding the burden of ongoing subscription costs. Ultimately, AgentForge is crafted to streamline the AI development process, ensuring that developers and businesses can harness its capabilities with ease. This makes it an invaluable resource for anyone looking to innovate in the realm of artificial intelligence.

TierZero Production Agents actively monitor incidents, manage alerts, and autonomously resolve production issues, enabling your engineering teams to release updates more swiftly. When an incident occurs, TierZero immediately engages, conducting a thorough investigation that spans your entire stack, including logs, traces, metrics, deployments, code alterations, and historical incidents. Unlike conventional AI SRE tools that merely handle triage, Production Agents encompass the entire post-merge process, which includes investigation, remediation, support Q&A, and proactive discovery. The Context Engine from TierZero integrates signals from code, infrastructure, discussions, and documentation into a dynamic knowledge graph that evolves and improves with each resolved issue. Installation within your environment can be accomplished in less than an hour, and every AI-driven investigation is fully auditable. This solution is specifically designed for highly regulated industries, such as fintech, healthcare, and cryptocurrency, where maintaining security is imperative. Furthermore, with its continuous learning capabilities, TierZero not only addresses current incidents but also anticipates potential future challenges.

Overmind serves as a comprehensive platform for the training and deployment of AI agents, catering specifically to teams engaged in this field. It processes production traces via OpenTelemetry, generating datasets from various sources including trace data, file uploads, and integrations with Langfuse, LangSmith, Braintrust, and Galileo. Teams have the capability to analyze agent context and performance in real-time, prepare and assess datasets, and test prompts and models against their tailored examples, all while refining agent behavior through evaluated modifications. The platform facilitates both LoRA and complete fine-tuning of open-weight models, offering benchmarking with custom evaluators and deployment through an OpenAI-compatible endpoint; additionally, users have the option to download trained weights. Furthermore, users can opt to engage with the hosted console or deploy the platform within their own infrastructure using Docker Compose. Designed for AI engineering and product teams managing agents in live environments, Overmind empowers users to effectively experiment, enhance, and customize models with their proprietary data for optimized outcomes. This flexibility ensures that teams can adapt their workflows according to their specific needs and preferences.

The Azure Marketplace serves as an extensive digital storefront, granting users access to a vast array of certified, ready-to-use software applications, services, and solutions provided by both Microsoft and various third-party vendors. This platform allows businesses to easily explore, purchase, and implement software solutions directly within the Azure cloud ecosystem. It features a diverse selection of products, encompassing virtual machine images, AI and machine learning models, developer tools, security features, and applications tailored for specific industries. With various pricing structures, including pay-as-you-go, free trials, and subscriptions, Azure Marketplace makes the procurement process more straightforward and consolidates billing into a single Azure invoice. Furthermore, its seamless integration with Azure services empowers organizations to bolster their cloud infrastructure, streamline operational workflows, and accelerate their digital transformation goals effectively. As a result, businesses can leverage cutting-edge technology solutions to stay competitive in an ever-evolving market.