​
Configuration Example

Agents are configured via JSON5 files in the /config directory.

The configuration file is used to define the LLM system prompt, agent’s inputs, LLM configuration, and actions etc.

Here is an example of the configuration file:

Configuration
{
  "hertz": 0.5,
  "name": "agent_name",
  "api_key": "openmind_free",
  "URID": "default",
  "system_prompt_base": "...",
  "system_governance": "...",
  "system_prompt_examples": "...",
  "agent_inputs": [
    {
      "type": "GovernanceEthereum"
    },
    {
      "type": "VLM_COCO_Local",
      "config": {
        "camera_index": 0
      }
    }
  ],
  "cortex_llm": {
    "type": "OpenAILLM",
    "config": {
      "base_url": "", // Optional: URL of the LLM endpoint
      "agent_name": "Iris", // Optional: Name of the agent
      "history_length": 10
    }
  },
  "simulators": [
    {
      "type": "WebSim",
      "config": {
        "host": "0.0.0.0",
        "port": 8000,
        "tick_rate": 100,
        "auto_reconnect": true,
        "debug_mode": false
      }
    }
  ],
  "agent_actions": [
    {
      "name": "move",
      "llm_label": "move",
      "implementation": "passthrough",
      "connector": "ros2"
    },
    {
      "name": "speak",
      "llm_label": "speak",
      "implementation": "passthrough",
      "connector": "ros2"
    }
  ]
}

​
Common Configuration Elements

  • hertz Defines the base tick rate of the agent. This rate can be overridden to allow the agent to respond quickly to changing environments using event-triggered callbacks through real-time middleware.

  • name A unique identifier for the agent.

  • api_key The API key for the agent. You can get your API key from the OpenMind Portal.

  • URID The Universal Robot ID for the robot. Used to join a decentralized machine-to-machine coordination and communication system (FABRIC).

  • system_prompt_base Defines the agent’s personality and behavior. This acts as the system prompt for the agent’s operations.

  • system_governance Defines the agent’s governance. This acts as the governance prompt for the agent’s operations.

  • system_prompt_examples Defines the agent’s examples. This acts as the examples prompt for the agent’s operations.

​
agent_inputs

Example configuration for the agent_inputs section:

agent_inputs
"agent_inputs": [
    {
      "type": "GovernanceEthereum"
    },
    {
      "type": "VLM_COCO_Local",
      "config": {
        "camera_index": 0
      }
    }
  ]

The agent_inputs section defines the inputs for the agent. The input might include a camera, a LiDAR, a microphone, or governance information.
OM1 implemented the following input types as reference:

  • GovernanceEthereum
  • GoogleASRInput
  • VLMVila
  • VLM_COCO_Local
  • RPLidar
  • TurtleBot4Batt
  • UnitreeG1Basic
  • UnitreeGo2Lowstate
  • more is coming soon…

Definitely you can implement your own input by following the Input Plugin

​
agent_inputs config section

The config section is specific to the input type. For example, the VLM_COCO_Local input type has a config section that includes a camera_index parameter.

​
cortex_llm

cortex_llm is for the Large Language Model (LLM) used by the agent.

Example configuration for the cortex_llm section:

cortex_llm
"cortex_llm": {
    "type": "OpenAILLM",
    "config": {
      "base_url": "", // Optional: URL of the LLM endpoint
      "api_key": "...",   // Optional: Override the default API key
      "agent_name": "Iris", // Optional: Name of the agent
      "history_length": 10
    }
  }

  • type: Specifies the LLM plugin.

  • config: Configuration for the LLM, including the API endpoint (base_url), agent_name, and history_length.

Read more information about Openmind API Reference.

You can directly access other OpenAI style endpoints by specifying a custom API endpoint in your configuration file. To do this, provide a suitable base_url and the api_key for OpenAI, DeepSeek, or other providers. Possible base_url choices are:

​
simulators

Lists the simulation modules used by the agent. These define the simulated environment or entities the agent interacts with.

Example configuration for the simulators section:

Simulators Configuration
"simulators": [
    {
      "type": "WebSim",
      "config": {
        "host": "0.0.0.0",
        "port": 8000,
        "tick_rate": 100,
        "auto_reconnect": true,
        "debug_mode": false
      }
    }
  ]

​
agent_actions

Defines the agent’s available capabilities, including action names, their implementation, and the connector used to execute them.

Example configuration for the agent_actions section:

Agent Actions Configuration
"agent_actions": [
    {
      "name": "move",
      "llm_label": "move",
      "implementation": "passthrough",
      "connector": "ros2"
    },
    {
      "name": "speak",
      "llm_label": "speak",
      "implementation": "passthrough",
      "connector": "ros2"
    }
  ]

  • name: The name of the action.

  • llm_label: The label of the action.

  • implementation: The implementation of the action.

  • connector: The connector of the action.

You can customize the action by following the Action Plugin