Mastra AI Integrations

Apify is a full-stack web scraping and automation platform helping anyone get value from the web. At its core is Apify Store, a marketplace with over 10,000 Actors where developers build, publish, and monetize automation tools. Actors are serverless cloud programs that extract data, automate web tasks, and run AI agents. Developers build them using JavaScript, Python, or Crawlee, Apify's open-source library. Build once, publish to Store, and earn when others use it. Thousands of developers do this - Apify handles infrastructure, billing, and monthly payouts. Apify Store has ready-made Actors for scraping Amazon, Google Maps, social media, tracking prices, lead-gen, and more. Actors handle proxies, CAPTCHAs, JavaScript rendering, headless browsers, and scaling. Everything runs on Apify's cloud with 99.95% uptime. SOC2, GDPR, and CCPA compliant. Integrate with Zapier, Make, n8n, and LangChain. Apify's MCP server lets AI like Claude dynamically discover and use Actors

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.

Gemini is Google’s advanced AI assistant designed to help users think, create, learn, and complete tasks with a new level of intelligence. Powered by Google’s most capable models, including Gemini 3, it enables users to ask complex questions, generate content, analyze information, and explore ideas through natural conversation. Gemini can create images, videos, summaries, study plans, and first drafts while also providing feedback on uploaded files and written work. The platform is grounded in Google Search, allowing it to deliver accurate, up-to-date information and support deep follow-up questions. Gemini connects seamlessly with Google apps like Gmail, Docs, Calendar, Maps, YouTube, and Photos to help users complete tasks without switching tools. Features such as Gemini Live, Deep Research, and Gems enhance brainstorming, research, and personalized workflows. Available through flexible free and paid plans, Gemini supports everyday users, students, and professionals across devices.

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.

Mistral AI is a pioneering artificial intelligence startup specializing in open-source generative AI. The company offers a range of customizable, enterprise-grade AI solutions deployable across various platforms, including on-premises, cloud, edge, and devices. Flagship products include "Le Chat," a multilingual AI assistant designed to enhance productivity in both personal and professional contexts, and "La Plateforme," a developer platform that enables the creation and deployment of AI-powered applications. Committed to transparency and innovation, Mistral AI positions itself as a leading independent AI lab, contributing significantly to open-source AI and policy development.

GPT-4o (“o” for “omni”) is a step towards much more natural human-computer interaction—it accepts as input any combination of text, audio, image, and video and generates any combination of text, audio, and image outputs. It can respond to audio inputs in as little as 232 milliseconds, with an average of 320 milliseconds, which is similar to human response time (opens in a new window) in a conversation. It matches GPT-4 Turbo performance on text in English and code, with significant improvement on text in non-English languages, while also being much faster and 50% cheaper in the API. GPT-4o is especially better at vision and audio understanding compared to existing models.

TypeScript adds additional syntax to JavaScript to support a tighter integration with your editor. Catch errors early in your editor. TypeScript code converts to JavaScript, which runs anywhere JavaScript runs: In a browser, on Node.js or Deno and in your apps. TypeScript understands JavaScript and uses type inference to give you great tooling without additional code. TypeScript was used by 78% of the 2020 State of JS respondents, with 93% saying they would use it again. The most common kinds of errors that programmers write can be described as type errors: a certain kind of value was used where a different kind of value was expected. This could be due to simple typos, a failure to understand the API surface of a library, incorrect assumptions about runtime behavior, or other errors.

Model Context Protocol (MCP) is an open protocol designed to standardize how applications provide context to large language models (LLMs). It acts as a universal connector, similar to a USB-C port, allowing LLMs to seamlessly integrate with various data sources and tools. MCP supports a client-server architecture, enabling programs (clients) to interact with lightweight servers that expose specific capabilities. With growing pre-built integrations and flexibility to switch between LLM vendors, MCP helps users build complex workflows and AI agents while ensuring secure data management within their infrastructure.

Gemini Enterprise app is an advanced AI-powered platform that brings Google’s AI capabilities to every employee, enabling organizations to automate workflows, analyze data, and create high-quality content across multiple business functions. It securely connects to tools like Microsoft 365, Google Workspace, HubSpot, and Jira, allowing users to search and interact with their business data using natural language. The platform supports prebuilt agents such as NotebookLM and Deep Research, helping teams quickly extract insights and streamline tasks. It also allows users to build custom no-code agents to automate multi-step workflows across different applications. With centralized management, organizations can deploy and monitor all agents from a single interface. Built-in security and governance features ensure data privacy and compliance with enterprise standards. Overall, Gemini Enterprise app enhances productivity by combining AI automation with secure data integration.

AG-UI is an open, lightweight, event-based protocol that standardizes how AI agents connect to user-facing applications. Built for simplicity and flexibility, it enables seamless integration between AI agents, real-time user context, and user interfaces. AG-UI is designed for agent-human interaction: during agent executions, backends emit events compatible with standard AG-UI event types, and agent backends can accept simple AG-UI-compatible inputs as arguments. It works with any event transport, including SSE, WebSockets, webhooks, and other streaming systems, while providing a flexible middleware layer that ensures compatibility across diverse environments. AG-UI brings agents into user-facing applications and complements the wider agentic protocol stack: MCP gives agents tools, A2A allows agents to communicate with other agents, and AG-UI connects agents directly to the user interface.

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.

Ejentum is a reasoning harness for agentic AI, built as a structured reasoning layer that makes LLM agents more reliable, auditable, and disciplined during long or complex tasks. It works as a tool that an agent can call mid-task, returning the exact cognitive operation matched to the problem in front of it, so the agent can correct reasoning at inference time instead of relying only on static prompts. Ejentum is designed to stop AI agents from drifting, flattering, fabricating, locking into false hypotheses, stopping at shallow answers, or losing important context after several steps. It provides 679 abilities across four cognitive harnesses: reasoning, code, anti-deception, and memory. The reasoning harness channels analytical power across causality, time, space, simulation, abstraction, and metacognition, helping agents avoid surface-level pattern matching.

JavaScript is a scripting language and programming language for the web that enables developers to build dynamic elements on the web. Over 97% of the websites in the world use client-side JavaScript. JavaScript is one of the most important scripting languages on the web. Strings in JavaScript are contained within a pair of either single quotation marks '' or double quotation marks "". Both quotes represent Strings but be sure to choose one and STICK WITH IT. If you start with a single quote, you need to end with a single quote. There are pros and cons to using both IE single quotes tend to make it easier to write HTML within Javascript as you don’t have to escape the line with a double quote. Let’s say you’re trying to use quotation marks inside a string. You’ll need to use opposite quotation marks inside and outside of JavaScript single or double quotes.

GroqCloud is a high-performance AI inference platform built specifically for developers who need speed, scale, and predictable costs. It delivers ultra-fast responses for leading generative AI models across text, audio, and vision workloads. Powered by Groq’s purpose-built LPU (Language Processing Unit), the platform is designed for inference from the ground up, not adapted from training hardware. GroqCloud supports popular LLMs, speech-to-text, text-to-speech, and image-to-text models through industry-standard APIs. Developers can start for free and scale seamlessly as usage grows, with clear usage-based pricing. The platform is available in public, private, or co-cloud deployments to match different security and performance needs. GroqCloud combines consistent low latency with enterprise-grade reliability.

Alkemi’s flagship product, DataLab, is a secure AI-native workspace that connects directly to your company’s governed data from sources like Snowflake, BigQuery, Databricks, or simple CSV uploads and lets users ask questions in plain English to get instant, transparent answers, charts, and recommendations with no SQL or analysts required. DataLab indexes and analyzes your data inside a private, secure environment so every insight is traceable and verifiable, and your data never leaves your control, protecting intellectual property and governance. It bridges the gap between complex data stores and everyday decision-making by combining the clarity of business intelligence with conversational AI to reduce BI backlogs and speed decisions for marketing, finance, product, sales, operations, and more. DataLab also enables data providers to turn datasets into interactive, AI-ready experiences that buyers can explore securely without exposing raw data, and accelerating data discovery.

We’ve built the fastest AI accelerator, based on the largest processor in the industry, and made it easy to use. With Cerebras, blazing fast training, ultra low latency inference, and record-breaking time-to-solution enable you to achieve your most ambitious AI goals. How ambitious? We make it not just possible, but easy to continuously train language models with billions or even trillions of parameters – with near-perfect scaling from a single CS-2 system to massive Cerebras Wafer-Scale Clusters such as Andromeda, one of the largest AI supercomputers ever built.

Llama (Large Language Model Meta AI) is a state-of-the-art foundational large language model designed to help researchers advance their work in this subfield of AI. Smaller, more performant models such as Llama enable others in the research community who don’t have access to large amounts of infrastructure to study these models, further democratizing access in this important, fast-changing field. Training smaller foundation models like Llama is desirable in the large language model space because it requires far less computing power and resources to test new approaches, validate others’ work, and explore new use cases. Foundation models train on a large set of unlabeled data, which makes them ideal for fine-tuning for a variety of tasks. We are making Llama available at several sizes (7B, 13B, 33B, and 65B parameters) and also sharing a Llama model card that details how we built the model in keeping with our approach to Responsible AI practices.