fleet runs on your own machine — the client starts it, so there is no endpoint to ping. 368 installs a week from pypi. Last commit 1 Nov 2026.
Every machine you have, for your agent: free GPUs, jobs, served models, software, over SSH.
Today is the operative word: we check fleet every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add fleet -- uvx agents-fleet
{
"mcpServers": {
"fleet": {
"command": "uvx",
"args": [
"agents-fleet"
]
}
}
}
[mcp_servers.fleet]
command = "uvx"
args = ["agents-fleet"]
{
"mcpServers": {
"fleet": {
"command": "uvx",
"args": [
"agents-fleet"
]
}
}
}
{
"servers": {
"fleet": {
"type": "stdio",
"command": "uvx",
"args": [
"agents-fleet"
]
}
}
}
Every machine you have, for your agent: free GPUs, jobs, served models, software, over SSH.
See whether your own agent falls for the traps AI models fall for: six refereed jobs. No account.
Get a second opinion on your code from every coding agent you have. No API keys.
Free hosted MCP server: new Upwork jobs for your agent and Telegram alerts within a minute.
An AI agent reads your server over the one SSH session you are already watching.
Call every global AI model through one OpenAI-compatible API. One key, all models.
Read your team's hosted journal from an AI agent: every machine's streams, in hub order.
Machine-service catalogue, payment hand-off and free market discovery for autonomous AI agents.
Answers built from our own checks of this server.