nero_spawn
Create a persistent LLM agent that stays alive in memory with full conversation history until killed, defined by a role and system prompt.
Instructions
Create a new named persistent agent. The agent stays alive in memory with full conversation history until killed.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"name": "<name>",
"role": "<role>",
"system_prompt": "<system_prompt>"
},
"name": "nero_spawn"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Unique agent name (lowercase alphanumeric + hyphens) | |
| role | Yes | Short description of the agent's role (e.g., 'code researcher', 'test writer') | |
| system_prompt | Yes | System prompt defining the agent's persona and instructions | |
| model | No | LLM model: 'opus' for complex tasks, 'sonnet' for general work | sonnet |
| tags | No | Optional tags for filtering with nero_broadcast | |
| max_history | No | Maximum conversation messages to keep (default: 50) | |
| max_tokens | No | Maximum tokens per response (default: 8192) |