Langfuse Integrations

Claude Duet is a proactive AI agent that helps professionals manage work across connected apps. It delivers a morning brief, monitors connected accounts for items needing attention, and accepts tasks by text or voice in a continuing conversation. The agent can schedule meetings, draft replies and reminders, prepare payroll and agreements, create reports and dashboards, and help build forecasts or web apps. Work continues in a cloud-based virtual machine while the user is away; Claude Duet sends updates when a task is complete or needs review. It carries over Claude account memory, skills, and connected apps, and supports more than 6,000 marketplace connectors and plugins. Before sensitive actions such as sending messages, paying, signing, or deleting, it requests approval. The research-preview app is available on iOS, Android, and the web for eligible Claude Pro and Max subscribers in the United States.

Grok Bot is an AI teammate platform from SpaceXSI that lets users delegate real work to bots across apps, websites, routines, and workflows. Bots can sign in to tools, use them like a person would, keep context over time, and return with finished work or requests for approval. Users can create multiple bots for jobs such as sales outbound, talent scouting, expense management, inbox management, account health, product performance, bug reproduction, and chief-of-staff workflows. Grok Bot can learn workflows by watching a user complete a task once, then save that process as a routine for future execution. Bots can work in parallel, collaborate in shared threads, pass work between one another, and run scheduled routines. Built for teams and individuals that want AI agents to execute tasks instead of only answering questions, Grok Bot helps automate work while keeping users involved when approvals are needed.

OpenAI’s mission is to ensure that artificial general intelligence (AGI)—by which we mean highly autonomous systems that outperform humans at most economically valuable work—benefits all of humanity. We will attempt to directly build safe and beneficial AGI, but will also consider our mission fulfilled if our work aids others to achieve this outcome. Apply our API to any language task — semantic search, summarization, sentiment analysis, content generation, translation, and more — with only a few examples or by specifying your task in English. One simple integration gives you access to our constantly-improving AI technology. Explore how you integrate with the API with these sample completions.

Claude is a next-generation AI assistant developed by Anthropic to help individuals and teams solve complex problems with safety, accuracy, and reliability at its core. It is designed to support a wide range of tasks, including writing, editing, coding, data analysis, and research. Claude allows users to create and iterate on documents, websites, graphics, and code directly within chat using collaborative tools like Artifacts. The platform supports file uploads, image analysis, and data visualization to enhance productivity and understanding. Claude is available across web, iOS, and Android, making it accessible wherever work happens. With built-in web search and extended reasoning capabilities, Claude helps users find information and think through challenging problems more effectively. Anthropic emphasizes security, privacy, and responsible AI development to ensure Claude can be trusted in professional and personal workflows.

Flowise is an open-source platform that enables developers and teams to build AI agents and LLM-powered applications through a visual interface. The platform provides modular building blocks that allow users to create everything from simple chatbot workflows to complex multi-agent systems. With its drag-and-drop design environment, developers can rapidly prototype and deploy AI-powered applications without extensive coding. Flowise supports integrations with more than 100 large language models, embeddings, and vector databases. It also includes features such as human-in-the-loop workflows, observability tools, and execution tracing for monitoring agent behavior. Developers can extend applications through APIs, SDKs, and embedded chat interfaces using TypeScript or Python. By combining visual development tools with scalable infrastructure, Flowise simplifies the process of building and deploying production-ready AI agents.

LangChain is a powerful, composable framework designed for building, running, and managing applications powered by large language models (LLMs). It offers an array of tools for creating context-aware, reasoning applications, allowing businesses to leverage their own data and APIs to enhance functionality. LangChain’s suite includes LangGraph for orchestrating agent-driven workflows, and LangSmith for agent observability and performance management. Whether you're building prototypes or scaling full applications, LangChain offers the flexibility and tools needed to optimize the LLM lifecycle, with seamless integrations and fault-tolerant scalability.

DocsGPT is an open-source platform for private AI agents, assistants and enterprise search over an organisation's own documents, built by Arc53. It runs where the data is allowed to be: Arc53's EU cloud, a dedicated managed instance, the organisation's own servers, or fully air-gapped with no outbound traffic. Teams connect files and services (PDF, DOCX, XLSX, scanned documents with OCR, Google Drive, SharePoint, Confluence, GitHub, S3) and get answers cited to the source passage. Agents call tools and APIs with per-action approval, a visual builder turns document jobs into workflows, and agents can produce DOCX, XLSX, PPTX and PDF files. Any model works: OpenAI, Anthropic, Google and others in the cloud, or local models through Ollama or vLLM. Governance covers OIDC SSO, SCIM 2.0, role-based access, guardrails, usage quotas and an exportable, append-only audit log. MIT licence, 18,000+ GitHub stars.

Hugging Face is a leading platform for AI and machine learning, offering a vast hub for models, datasets, and tools for natural language processing (NLP) and beyond. The platform supports a wide range of applications, from text, image, and audio to 3D data analysis. Hugging Face fosters collaboration among researchers, developers, and companies by providing open-source tools like Transformers, Diffusers, and Tokenizers. It enables users to build, share, and access pre-trained models, accelerating AI development for a variety of industries.

A managed PaaS with a low-code visual builder, VectorDB, and integrations to apps and models for building, testing, and deploying high-performance AI apps on edge. Eliminate costly, error-prone work. Drag and drop models, apps, data, and agents to find what works best. Deploy in under 60 seconds and cut latency in half. Observe, test, and iterate seamlessly. Visibility and tools ensure accuracy and reliability. Make data-driven decisions with request, LLM, and usage reports. See real-time traces by node. Experiments make it easy to optimize everything always embeddings, prompts, models, and more. Everything you need to launch & iterate at scale. Community of bright-minded builders sharing insights, experience & feedback. Distilling the best tips, tricks & techniques for AI application development. An elegant platform to build agentic systems like a team of 100. An intuitive and simple frontend to collaborate and manage AI applications seamlessly.

​LiteLLM is a versatile platform designed to streamline interactions with over 100 Large Language Models (LLMs) through a unified interface. It offers both a Proxy Server (LLM Gateway) and a Python SDK, enabling developers to integrate various LLMs seamlessly into their applications. The Proxy Server facilitates centralized management, allowing for load balancing, cost tracking across projects, and consistent input/output formatting compatible with OpenAI standards. This setup supports multiple providers. It ensures robust observability by generating unique call IDs for each request, aiding in precise tracking and logging across systems. Developers can leverage pre-defined callbacks to log data using various tools. For enterprise users, LiteLLM offers advanced features like Single Sign-On (SSO), user management, and professional support through dedicated channels like Discord and Slack.

Voker is an Agent Analytics Platform for monitoring and improving AI agents in the wild, helping teams make sure their agents are helping, not just responding. It gives builders a way to track what AI agents are saying, identify knowledge gaps, detect abnormalities, and measure improvement over time without digging through logs or waiting for users to complain. Voker connects agent metrics to business outcomes by correlating conversational data with user data that teams are already collecting, making it easier to understand whether an agent is actually improving activation, retention, conversion, support quality, or other product goals. Its self-service analytics are designed for PMs, analysts, and business teams, giving them digestible insights without tickets, bottlenecks, or delays. Developers can install Voker through the SDK, including pip install voker, or use an AI coding tool to scaffold the SDK, add an API key, and instrument an agent in minutes.

AI Workers are autonomous agents built for your business; specialized AI workers that act like real coworkers, not chatbots you prompt. They come with their own professional profile, email, phone number, Slack and Teams presence, initiative, and the ability to work 24/7 without waiting to be asked. Instead of telling them exactly how to complete every step, you set the goal, and they build the workflow, whether that means daily reports, weekly follow-ups, CRM updates, client communication, research, content, finance tasks, HR coordination, design work, development support, or other recurring business operations. It includes specialized AI Workers across marketing, development, design, HR, finance, and other business functions, with each worker designed around a clear role and practical use cases. AI Workers can connect to more than 3,000 tools, including Slack, Microsoft Teams, Gmail, Notion, HubSpot, Salesforce, and other business apps.

Dograh is an open source, self-hostable voice agent platform with a no-code workflow builder for creating production voice agents. Teams can choose their own inbound channels, speech-to-text, LLM, text-to-speech, and telephony providers, or replace the traditional cascade with speech-to-speech models for direct audio-in, audio-out conversations with natural turn-taking, interruption handling, and low latency. The platform supports inbound and outbound calling, widgets, telephony integrations, observability, traces, real-time analytics, hybrid pre-recorded voice plus TTS, and more than 70 languages. Its MCP server lets Claude Code, Cursor, OpenClaw, Codex, and other agent runtimes create, modify, and deploy voice agents directly from development environments. Dograh can run on your own servers, inside a private cloud or VPC, or in a managed environment, with support for models hosted entirely within your perimeter.

Reflexio is an AI-agent learning platform for developers building and operating agents. It ingests agent interactions, execution traces, tool calls, and user corrections through an SDK, REST API, CLI, or supported tracing-platform connections, then extracts recurring failures into reusable playbooks and user profiles. At runtime, an agent can retrieve relevant learned guidance before responding. The Hosted Enterprise portal lets teams inspect, edit, approve, reject, search, and evaluate learnings. Reflexio helps agents apply corrections across interactions without changing model weights. Teams can use the managed cloud service, configure their own model-provider keys, or self-host in AWS, Google Cloud, or Azure. Enterprise trace imports are available from Braintrust, Langfuse Cloud, and LangSmith Cloud; Reflexio also provides a mem0 wrapper and an OpenClaw integration.

evalship helps engineering teams test LLM-powered software through evaluation-suite audits and pull-request reviews. It checks scorers and judges for flaws, identifies missing coverage and evals that may pass incorrectly, and provides findings with code references and suggested fixes. Setup can help a coding agent configure GitHub Actions and open a setup pull request. On later pull requests, evalship compares results with the default branch, flags regressions, flaky evals, and changed prompts or model calls without evaluation coverage, and can provide a merge-gating status check. It reads results from supported test runners and LLM evaluation platforms. Evaluations run in the customer's GitHub Actions with their own model API keys; evalship reviews results rather than executing evaluations. Teams can review evaluation history and receive weekly reports.

TierZero Production Agents investigate incidents, triage alerts, and fix production problems automatically so your engineers can ship faster. When an incident fires, TierZero joins and starts investigating across your full stack: logs, traces, metrics, deploys, code changes, and past incidents. Unlike standalone AI SRE tools that stop at triage, Production Agents cover the full post-merge lifecycle including investigation, remediation, support Q&A, and proactive discovery. TierZero’s Context Engine synthesizes signals from code, infrastructure, conversations, and documents into a living knowledge graph that gets smarter with every issue resolved. Deploy in your environment in under an hour. Every AI investigation is auditable. Built for regulated industries (fintech, healthcare, crypto) where security isn’t optional.

Overmind is a model training and deployment platform for teams building AI agents. It ingests production traces through OpenTelemetry and creates datasets from trace data, file uploads, and connectors for Langfuse, LangSmith, Braintrust, and Galileo. Teams can inspect agent context and runtime behavior, prepare and score datasets, evaluate prompts and models against their own examples, and optimize agent behavior through scored changes. The platform supports LoRA and full fine-tuning of open-weight models, benchmarking with configured evaluators, and deployment through an OpenAI-compatible endpoint; trained weights can also be downloaded. Users can work in the hosted console or run the platform on their own infrastructure with Docker Compose. It is designed for AI engineering and product teams operating agents in production that want to test, improve, or specialize models using their own data.

LlamaIndex is a “data framework” to help you build LLM apps. Connect semi-structured data from API's like Slack, Salesforce, Notion, etc. LlamaIndex is a simple, flexible data framework for connecting custom data sources to large language models. LlamaIndex provides the key tools to augment your LLM applications with data. Connect your existing data sources and data formats (API's, PDF's, documents, SQL, etc.) to use with a large language model application. Store and index your data for different use cases. Integrate with downstream vector store and database providers. LlamaIndex provides a query interface that accepts any input prompt over your data and returns a knowledge-augmented response. Connect unstructured sources such as documents, raw text files, PDF's, videos, images, etc. Easily integrate structured data sources from Excel, SQL, etc. Provides ways to structure your data (indices, graphs) so that this data can be easily used with LLMs.

Mirascope is an open-source library built on Pydantic 2.0 for the most clean, and extensible prompt management and LLM application building experience. Mirascope is a powerful, flexible, and user-friendly library that simplifies the process of working with LLMs through a unified interface that works across various supported providers, including OpenAI, Anthropic, Mistral, Gemini, Groq, Cohere, LiteLLM, Azure AI, Gemini Enterprise Agent Platform, and Bedrock. Whether you're generating text, extracting structured information, or developing complex AI-driven agent systems, Mirascope provides the tools you need to streamline your development process and create powerful, robust applications. Response models in Mirascope allow you to structure and validate the output from LLMs. This feature is particularly useful when you need to ensure that the LLM's response adheres to a specific format or contains certain fields.

Omega is an internally developed AI agent integrated directly into Slack to supercharge sales workflows by handling routine tasks, surfacing insights, and nudging team members toward best practices, all with minimal friction. It seamlessly connects with core tools like Slack, Google Drive, Apollo, Salesforce, and transcript systems to automate time-consuming chores, generating call agendas, summarizing expert calls, locating relevant documents, and tracking deal progression. Omega operates as a modular, multi-agent system, utilizing specialized roles orchestrated via frameworks like AutoGen to plan, execute, and validate actions within the workflow. This architecture runs on a cloud-native, serverless stack using AWS Lambda and Step Functions, enabling flexibility and scale. Observability and iteration are supported through tools like Langfuse, Promptfoo, CI/CD pipelines, and Terraform.

Claude for Legal is an AI assistant from Anthropic that legal professionals can use to work with documents and research materials. It can summarize lengthy files, extract and compare information, draft and revise text, and assist with contract and document analysis. Law firms and in-house legal teams can use Claude for Legal for recurring knowledge and document workflows, providing relevant context and source materials and reviewing generated responses as part of their work. Claude for Legal is available online and through desktop and mobile apps. It supports information processing and drafting; users remain responsible for checking outputs, applying professional judgment, and making legal decisions.