Agentverse manage
Agent skills for interacting with Fetch.ai's Agentverse — portable SKILL.md format for Claude Code, Codex, Copilot, Cursor, Gemini CLI
npx -y skills add fetchai/agentverse-skills --skill agentverse-manageAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Manage hosted agents on Fetch.ai's Agentverse: list, start, stop, view logs, and delete agents. Provides operational control over your deployed agents. Requires AGENTVERSE_API_KEY env var. Use when asked to list agents, check agent status, view logs, start/stop agents, or clean up.
The file declares its own license as Apache-2.0. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
2.9 KB, as published. Nobody here has run it
Agentverse Manage
Overview
Manage your hosted agents on Agentverse. List all agents, start/stop them, read their logs, and delete agents you no longer need.
When to Use
- User asks "list my agents" or "what agents do I have"
- User asks to "start/stop/restart" an agent
- User asks to "show agent logs" or "what is my agent doing"
- User asks to "delete" or "remove" an agent
- You need to check agent status after deploying
Prerequisites
AGENTVERSE_API_KEYenvironment variable set- Python 3.8+ with
requests
Quick Steps
List all agents
python3 scripts/manage_agents.py list
Start an agent
python3 scripts/manage_agents.py start --agent agent1q...
Stop an agent
python3 scripts/manage_agents.py stop --agent agent1q...
View logs
python3 scripts/manage_agents.py logs --agent agent1q...
Delete an agent
python3 scripts/manage_agents.py delete --agent agent1q...
Output Examples
List
{
"status": "success",
"total": 3,
"agents": [
{
"name": "my-image-relay",
"address": "agent1q...",
"running": true,
"compiled": true,
"domain": "",
"wallet_address": "fetch1...",
"created": "2026-04-20T10:00:00Z",
"updated": "2026-04-20T15:30:00Z"
}
]
}
Logs
{
"status": "success",
"agent": "agent1q...",
"total_entries": 15,
"showing": 3,
"logs": [
{"timestamp": "2026-04-20T15:30:00Z", "message": "Agent started", "level": "info"},
{"timestamp": "2026-04-20T15:30:01Z", "message": "Sending message...", "level": "info"},
{"timestamp": "2026-04-20T15:30:35Z", "message": "RESULT:{...}", "level": "info"}
]
}
API Reference
| Action | Method | Endpoint |
|---|---|---|
| List agents | GET | /v1/hosting/agents |
| Get agent | GET | /v1/hosting/agents/{address} |
| Start | POST | /v1/hosting/agents/{address}/start |
| Stop | POST | /v1/hosting/agents/{address}/stop |
| Delete | DELETE | /v1/hosting/agents/{address} |
| Get logs | GET | /v1/hosting/agents/{address}/logs/latest |
Edge Cases
- Agent already running: Starting a running agent is safe (no-op or restarts)
- Agent already stopped: Stopping a stopped agent is safe (no-op)
- Delete running agent: Stop it first, then delete
- Empty logs: Agent hasn't produced output yet, or was just started