> For the complete documentation index, see [llms.txt](https://dar-open-network.gitbook.io/developers/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://dar-open-network.gitbook.io/developers/deai/multi-agent-framework.md). # Multi-Agent Framework **The DeAI Multi-Agent Framework** is an advanced modular platform designed to empower developers to build, deploy, and orchestrate collaborative AI agents. It supports multiple large language models (LLMs) and offers flexibility to create specialized agents optimized for a variety of applications, from customer support to gaming and beyond. By integrating tools, APIs, and inter-agent communication protocols, DeAI creates a robust environment for intelligent and scalable solutions. ### **Key Features** * **Multi-Agent Collaboration** Define agents with distinct functions that can work together to solve complex tasks. Agents can communicate, share context, and delegate tasks efficiently to ensure optimal workflow. * **Extensible LLM Support** Integrate various LLMs, such as OpenAI, Anthropic, or open-source models, into your agents. This flexibility allows you to tailor agent performance for specific workloads. * **Tool Integration** Enable agents to interact with external systems like Twitter, Discord, or blockchain platforms such as Uniswap. Add functionality dynamically based on your application needs. * **Inter-Agent Communication** Built-in protocols ensure agents can communicate and share context while maintaining isolation for security and efficiency. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://dar-open-network.gitbook.io/developers/deai/multi-agent-framework.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.