by ifelseend · v0.0.1
AgentCube is designed to extend Volcano's capabilities to natively support and manage AI Agent workloads.
This community listing does not yet include every recommended support, privacy, pricing, and permission disclosure. Review the available package permissions before installing.
Available inside your emploidai workspace after installation.
Available inside your emploidai workspace after installation.
AgentCube is designed to extend Volcano's capabilities to natively support and manage AI Agent workloads. This plugin integrates AgentCube with Dify, providing a powerful and isolated code execution sandbox.
The Agentcube Code Interpreter tool offers an isolated code execution sandbox based on Volcano AgentCube. It allows you to perform various code interpreter actions within a secure environment.
session_id.| Parameter | Type | Required | Description |
|---|---|---|---|
router_url | String | Yes | The AgentCube router URL for data plane communication. |
workload_manager_url | String | Yes | The AgentCube workload manager URL for control plane operations. |
language | Select | Yes | Programming language of the code. AgentCube includes a built-in Python interpreter. To use custom Python environments or other languages, you must upload and configure a custom code interpreter in AgentCube. |
code | String | Yes | The source code to be executed. |
command | String | No | Terminal command to be executed. If provided, it will be executed before the code. |
session_id | String | No | Unique identifier of the code interpreter session to use. If not provided, a new session is created. |
session_reuse | Boolean | No | Whether to reuse the session for next invocation. If true, the session will not be stopped after execution. |
code_interpreter_id | String | No | ID of the AgentCube code interpreter to use. If not set, it defaults to the built-in Python code interpreter. |
router_url and workload_manager_url. These are typically provided by your system administrator or AgentCube deployment.python as the language and input your code in the code field.command field.