MaxHermes
MaxHermes is MiniMax’s cloud-hosted AI assistant built on Hermes Agent and powered by MiniMax M2.7, designed as a self-evolving agent that grows with the user. It removes the technical setup required by self-hosted agents, so users can start a personal AI agent in the cloud without configuring servers, Docker, API keys, or local environments. MaxHermes is always online, can go live in about 10 seconds, and runs 24/7 in the cloud, making it suitable for long-running tasks, scheduled monitoring, recurring workflows, and real-time assistance through everyday chat tools. Its defining feature is self-evolving intelligence: after completing complex tasks, MaxHermes can identify reusable patterns, extract them into new skills, and use those skills in future sessions so it becomes more aligned with the user’s habits, projects, and workflows over time. Each completion of a complex task can unlock a brand-new skill, turning work history into procedural memory rather than disposable chat history.
Learn more
MiniMax
MiniMax is a global AI technology company that develops advanced multimodal foundation models and AI-powered products for individuals, developers, and enterprises. Its flagship model, MiniMax M3, combines frontier-level coding capabilities, agentic task execution, native multimodal understanding, and support for up to 1 million tokens of context through its proprietary MiniMax Sparse Attention (MSA) architecture. The company offers a comprehensive ecosystem that includes coding assistants, AI agents, video generation, speech synthesis, music generation, and developer APIs. Through products such as MiniMax Code, Hailuo AI, MiniMax Audio, Talkie, and its enterprise platform, users can automate workflows, generate content, build applications, and deploy AI-powered solutions at scale. MiniMax helps organizations and developers improve productivity, accelerate software development, and create intelligent experiences across text, audio, image, video, and music.
Learn more
MiniMax M3
MiniMax M3 is an open-weight multimodal AI model designed for coding, agentic workflows, long-context reasoning, and complex automation tasks. The model combines frontier-level coding performance, native multimodal understanding, and a context window of up to 1 million tokens. MiniMax M3 uses MiniMax Sparse Attention to improve long-context efficiency while reducing compute requirements for large-scale inputs. It supports text, image, and video understanding, making it useful for workflows that combine code, documents, visual references, and tool-driven tasks. The model is built for repository-scale reasoning, software engineering, autonomous task execution, tool calling, and multi-step agent workflows. MiniMax M3 helps developers, AI teams, and enterprises build capable agents that can reason across large contexts and work with multimodal information.
Learn more
Mavy
Mavy, your personal AI executive assistant, can help with all your tasks, from scheduling and calendar management to email drafting and beyond. Your AI executive assistant is designed to manage and execute all repetitive tasks related to work so that you can focus on what you're good at. Mavy can help you draft email replies as well as compose new ones. Access all your tools and apps seamlessly through Mavy's unified interface and spotlight search bar. No more juggling between multiple applications. Mavy integrates with your favorite apps and tools, enabling seamless data exchange and task execution across platforms. Mavy can be accessed from anywhere using keyboard shortcuts allowing you to accomplish tasks efficiently. Let Mavy take care of your calendar, schedule meetings, set reminders, and manage meetings effortlessly, all in one place. Draft LinkedIn posts, brainstorm ideas, prepare documents and everything text.
Learn more
