Control Plane For Your AI Agents

The universal platform for integrating AI agents from any framework with real-time communication and human oversight

50+
GitHub Stars
500+
Monthly PyPI Downloads

The Universal Agent Integration Platform

Connect AI agents from any framework, enable real-time communication, and maintain human oversight - all with mahilo's powerful integration platform.

Universal Agent Integration

Connect AI agents built in any framework - LangGraph, Pydantic AI, and more.

  • Seamless integration with popular agent frameworks
  • Connect proprietary agents via API
  • Framework-agnostic communication protocol

Real-Time Communication

Instant voice and text chat capabilities for any integrated agent.

  • Voice and text chat out of the box
  • Real-time agent-to-agent communication
  • Seamless human-agent interactions

Intelligent Collaboration

AI agents that autonomously share context and information when needed.

  • Smart context sharing between agents
  • Cross-framework information exchange
  • Autonomous agent-to-agent queries

Organization-Wide Policies

Enforce consistent behavior and security across all integrated agents.

  • Centralized policy management
  • Consistent security controls
  • Behavioral guidelines across agents

Human-Centric Design

Keep humans in control while AI agents handle complex interactions.

  • Perfect balance of automation and oversight
  • Humans are only contacted when needed
  • Humans can choose to dictate AI decisions

Multi-Agent Architectures

Build sophisticated agent systems with flexible communication patterns.

  • Hierarchical and peer-to-peer patterns
  • Complex workflow orchestration
  • Scalable agent architectures

True Multi-Player AI

Enable simultaneous interactions between multiple users and AI agents in a shared intelligent space.

  • Multiple users interact with AI agents simultaneously
  • Sophisticated shared context management
  • Configurable communication patterns between agents

Let your agents know they are not alone

Enable your AI agents to collaborate and share information intelligently, just like humans do. Mahilo brings them together while keeping you in control.

Watch Demo
AI Agents Integration Diagram

Supported Frameworks

Connect agents from popular frameworks or bring your own through our standardized API.

LangGraph

Available

Connect agents built with LangChain's LangGraph framework for complex agent workflows and state machines.

Pydantic AI

Available

Integrate agents using Pydantic AI's structured data models and validation system.

Custom API Agents

Available

Build agents through our mahilo's BaseAgent interface over any API.

AutoGen

Coming Soon

Support for Microsoft's AutoGen framework for multi-agent conversations.

CrewAI

Coming Soon

Integration with CrewAI for role-based agent collaboration systems.

More Frameworks and Services

Coming Soon

More frameworks and propreitary services coming soon. Request your preferred integration!

Check out the integrations

Real-World Applications

Discover the diverse range of multi-agents apps that mahilo can help you create

Story Weaver

Collaborative Content Creation

911 Emergency Response

Critical Response Coordination

RentMate AI

Real Estate Matchmaking

Story Weaver

Collaborative Content Creation

Multi-player storytelling game where users create stories while AI agents intelligently blend narratives.

Key Mahilo Features Demonstrated

  • Real-time collaborative content creation with AI
  • Shared context management for enhanced creativity
  • Individual narrative ownership tracking
  • Multi-player AI interaction system

Build Your Multi-Agent System

Define Agents

Use the BaseAgent class or use an integration

Create Agent Manager

Add agents to the AgentManager. Think of it as a team of agents

Start WebSocket Server

Create and run the AgentWebSocketServer

1from mahilo.agent import BaseAgent
2from mahilo.integrations.langgraph.agent import LangGraphAgent
3from mahilo.agent_manager import AgentManager
4from mahilo.server import ServerManager
5
6sales_agent = BaseAgent(
7    type="sales_agent",
8    description=sales_agent_prompt,
9    tools=sales_tools,
10)
11
12marketing_agent = LangGraphAgent(
13    langgraph_agent=graph_builder,
14    name="MarketingAgent",
15    description=marketing_agent_prompt,
16    can_contact=[],
17)
18
19# Create Agent Manager
20manager = AgentManager()
21manager.register_agent(sales_agent)
22manager.register_agent(marketing_agent)
23
24# initialize the server manager
25server = ServerManager(manager)
26# Start WebSocket Server
27server.run()

Client Connection Simulation

Connect Client

$ python client.py --agent-name buyer_agent

Connects to the mahilo WebSocket server for the buyer_agent and starts interaction