Dify Integrations

Notion is a highly versatile and collaborative workspace designed to help individuals and teams manage documents, wikis, projects, and tasks efficiently. It offers a wide array of features like customizable views for workflows, project tracking, and document creation, all within a single platform. Notion allows users to create a shared knowledge base, organize notes, and collaborate seamlessly on content creation. Additionally, its built-in AI assistance features help users summarize, write, and instantly search for relevant content, significantly enhancing productivity. The platform integrates effortlessly with other popular apps such as Slack, Google Drive, and Trello, providing a seamless experience for teams looking for an all-in-one platform to manage their projects, goals, and knowledge in an organized, collaborative environment.

GitHub is the world’s most secure, most scalable, and most loved developer platform. Join millions of developers and businesses building the software that powers the world. Build with the world’s most innovative communities, backed by our best tools, support, and services. If you manage multiple contributors , there’s a free option: GitHub Team for Open Source. We also run GitHub Sponsors, where we help fund your work. The Pack is back. We’ve partnered up to give students and teachers free access to the best developer tools—for the school year and beyond. Work for a government-recognized nonprofit, association, or 501(c)(3)? Get a discounted Organization account on us.

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.

GPT-4 (Generative Pre-trained Transformer 4) is a large-scale unsupervised language model, yet to be released by OpenAI. GPT-4 is the successor to GPT-3 and part of the GPT-n series of natural language processing models, and was trained on a dataset of 45TB of text to produce human-like text generation and understanding capabilities. Unlike most other NLP models, GPT-4 does not require additional training data for specific tasks. Instead, it can generate text or answer questions using only its own internally generated context as input. GPT-4 has been shown to be able to perform a wide variety of tasks without any task specific training data such as translation, summarization, question answering, sentiment analysis and more.

Firecrawl is a web data platform that enables developers and AI applications to search, scrape, and interact with websites at scale through a unified API. The platform extracts clean, structured content from web pages and delivers it in formats such as Markdown, JSON, screenshots, and other machine-readable outputs. Designed specifically for AI agents, Firecrawl allows systems to access real-time web information, navigate websites, and automate data collection workflows. It supports advanced features including JavaScript rendering, smart waiting, media parsing, and interactive page actions such as clicking, typing, and scrolling. Developers can integrate Firecrawl quickly using SDKs, APIs, MCP clients, and open-source tools. Trusted by thousands of companies, the platform helps organizations build reliable AI-powered applications that depend on accurate and accessible web data.

The core of extensible programming is defining functions. Python allows mandatory and optional arguments, keyword arguments, and even arbitrary argument lists. Whether you're new to programming or an experienced developer, it's easy to learn and use Python. Python can be easy to pick up whether you're a first-time programmer or you're experienced with other languages. The following pages are a useful first step to get on your way to writing programs with Python! The community hosts conferences and meetups to collaborate on code, and much more. Python's documentation will help you along the way, and the mailing lists will keep you in touch. The Python Package Index (PyPI) hosts thousands of third-party modules for Python. Both Python's standard library and the community-contributed modules allow for endless possibilities.

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.

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.

TinyFish is an enterprise AI platform that builds and operates “enterprise web agents” designed to execute complex workflows directly across the web at massive scale. Instead of relying on APIs or manual processes, these agents interact with websites the way humans do, navigating interfaces, extracting data, and completing multi-step tasks across thousands of platforms simultaneously. It is built to handle the growing complexity of the modern web, where valuable data is often fragmented, hidden behind logins, or constantly changing, making traditional automation unreliable. TinyFish agents are powered by infrastructure that can learn, adapt, and scale, enabling them to maintain accuracy and reliability even as web environments evolve. It is designed around outcome-driven workflows rather than isolated tasks, meaning agents can execute entire processes such as pricing intelligence, inventory tracking, or market monitoring from start to finish.

Tencent Cloud Lighthouse is a next-generation cloud server service designed for lightweight application scenarios, providing an out-of-the-box experience that allows users to quickly build and deploy websites, web applications, mini programs, mini games, and development environments without complex setup. It integrates core cloud resources, including computing, storage, and networking, into preconfigured bundles, simplifying infrastructure management and enabling users to launch applications in just a few clicks. It offers a wide range of prebuilt images that include operating systems and popular software stacks such as WordPress, LAMP, Node.js, and Docker, allowing applications to be initialized automatically without manual installation or configuration. Lighthouse instances function as virtual cloud servers with CPU, storage, and network components, optimized for low to medium workloads like small websites, blogs, ecommerce platforms, and testing environments.

Dock is the AI workspace for you, your team, and every agent you run. It gives humans and AI agents the same shared cloud workspace, where everyone can read and write the same state in real time instead of working across scattered chats, files, and one-off outputs. Dock is built around tables with typed columns, rich-text docs, and agents as first-class identities, each with their own API keys, permissions, and audit trail rather than delegated human tokens. Teams can use Dock to plan, research, decide, and ship with humans and AI on the same surface, with use cases across engineering, go-to-market, research, operations, solo work, and agency workflows. Engineering teams can manage sprint planning, spec docs, and incident response; GTM teams can organize content calendars, sales pipelines, and customer success; research teams can track interviews, themes, and competitive intelligence; and operations teams can manage runbooks, recruiting, compliance, and onboarding.

Hindsight is an agent memory system built to create smarter AI agents that learn over time instead of starting every conversation from zero. Most agent memory systems focus on recalling conversation history, but Hindsight is focused on making agents learn, not just remember. It gives AI agents persistent long-term memory using biomimetic data structures, helping them retain facts, recall relevant context, and reflect on experience as part of reasoning. Hindsight is designed for agents that need to understand who a user is, what has been discussed, what preferences have emerged, what decisions were made, and how behavior should adapt across sessions. It provides three core operations: retain, recall, and reflect. Retain stores new information, recall retrieves the right memories when needed, and reflect helps agents synthesize observations, form mental models, and learn from prior interactions.

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.

Connect your LLM applications to the world, and access clean, accurate, high-quality context. Get enhanced search details from billions of web documents, including news, images, videos, and more. It achieves ranking performance of 280M~560M models with only 80M parameters, offering faster inference and lower cost.

Elestio is a fully managed DevOps platform that enables users to deploy over 350 open source software applications on dedicated virtual machines in under three minutes. It handles installation, configuration, encryption, backups, software and OS updates, live monitoring, and more, allowing users to focus on utilizing the software to its fullest potential. Elestio supports deployment on various cloud providers, including DigitalOcean, AWS, VULTR, Hetzner, Linode, Scaleway, and on-premise environments, offering flexibility and control without vendor lock-in. All services are delivered on dedicated hardware, providing full access to underlying resources and kernel-level security. Connections between the user's computer, the dashboard, and services are encrypted end-to-end with TLS, ensuring data security. It also offers a fully managed CI/CD system, supporting GitHub, GitLab, and Docker registries as sources, and is compatible with any Linux tech stack.

An intuitive yet comprehensive evaluation platform to iteratively optimize your AI-driven products. Streamline LLMOps workflow, build confidence, and gain a competitive edge. EvalsOne is your all-in-one toolbox for optimizing your application evaluation process. Imagine a Swiss Army knife for AI, equipped to tackle any evaluation scenario you throw its way. Suitable for crafting LLM prompts, fine-tuning RAG processes, and evaluating AI agents. Choose from rule-based or LLM-based approaches to automate the evaluation process. Integrate human evaluation seamlessly, leveraging the power of expert judgment. Applicable to all LLMOps stages from development to production environments. EvalsOne provides an intuitive process and interface, that empowers teams across the AI lifecycle, from developers to researchers and domain experts. Easily create evaluation runs and organize them in levels. Quickly iterate and perform in-depth analysis through forked runs.