AB
AiBoss
project

Mahilo is an AI multi-agent framework that supports the creation of multi-agent systems that interact with humans.

Mahilo is a flexible multi-agent framework that supports the creation of multi-agent systems that interact with humans. Mahilo supports real-time voice and text communication, allowing agents to autonomously share context and information while maintaining human oversight of the interactions...

What is Mahilo?

Mahilo is a flexible multi-agent framework that supports the creation of multi-agent systems that interact with humans. Mahilo supports real-time voice and text communication, allowing agents to autonomously share context and information while maintaining human oversight and control over the interaction. Mahilo provides robust organizational-level policy management capabilities, ensuring consistent behavior and security across all agents. Mahilo supports complex multi-agent architectures and is suitable for a variety of applications, from customer service to emergency response. Based on easy-to-use development interfaces and real-time communication capabilities, Mahilo supports the efficient coordination of interactions between multiple agents and human users, improving collaboration efficiency and decision-making capabilities.

Mahilo's main functions

  • Multi-agent integrationSupports the integration of intelligent agents from different frameworks (such as LangGraph, Pydantic AI, etc.).
  • Real-time communicationIt provides text and voice chat functionality, supporting multiple users to interact with the intelligent agent simultaneously.
  • Shared ContextIntelligent agents can automatically share contextual information, enhancing their collaborative capabilities.
  • Human oversightIt supports real-time human participation, providing decision support or correcting the behavior of intelligent agents.
  • Flexible communication modesIt supports point-to-point and hierarchical communication modes to adapt to different scenarios.
  • Session ManagementSupports persistent conversations, ensuring session continuity.
  • Message tracking and monitoringSupports message lifecycle tracking, message signing, and retry mechanisms.
  • Voice interactionIt supports OpenAI's Realtime API, providing smooth voice interaction.

Mahilo's technical principles

  • AgentManagerAs a "team" of intelligent agents, it is responsible for managing communication and context sharing among intelligent agents.
  • Real-time communicationIt provides real-time communication support based on WebSocket, ensuring instant interaction between the agent and the user.
  • Message protocols and message agentsIt introduces a standardized messaging protocol to support message signing, tracking, and persistent storage.
  • Human integrationBased on the WebSocket real-time chat interface, human experts can intervene in the decision-making process of intelligent agents when needed.
  • Flexible communication modesIt supports point-to-point and hierarchical communication modes, adapting to different scenarios ranging from complex collaboration to centralized control.
  • Context sharing and intelligent information retrievalIntelligent agents can access the conversation history of other intelligent agents and request specific information based on the chat_with_agent function.
  • ScalabilityProvides the BaseAgent class, which makes it easy for developers to create custom smart agents and supports integration with multiple frameworks.

Mahilo's project address

Application scenarios of Mahilo

  • Collaborative content creationUsed for collaborative content creation among multiple users, interacting with intelligent agents to co-create stories.
  • Emergency Response CoordinationIn a 911 emergency response scenario, coordinate multiple response agents, such as medical, logistics, and communication agents, to ensure rapid and effective resource allocation in emergency situations.
  • Real Estate MatchingReal estate rental matching: Buyer and seller agents share context and communicate in real time to optimize the rental process.
  • Team collaboration and project managementIt supports real-time interaction between multiple users and intelligent agents, making it suitable for team collaboration scenarios, such as multi-user development projects where the intelligent agent provides guidance to each developer while maintaining overall project consistency.
  • Medical and health coordinationIn healthcare settings, intelligent agents such as medical advisors, logistics coordinators, and public communications specialists are connected to enable information sharing and collaborative decision-making, thereby improving the efficiency of healthcare services.