fleet

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/lion-zhang-fleet

About

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 26, 2026.

Tools

5 read · 5 write · 0 delete · 1 not yet classified

Secrets

None asked for

Install scripts

None found

Runs as

Python package

Tools (11)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

• add_machine

  Add a machine from how the user connects to it: an ssh command such as `ssh -p 40001 root@1.2.3.4`, or a name from discover_machines. Ask for it if the user did not give one. If the machine refuses, the result has `why` and `fix` -- the one thing the user does to let fleet in. Never ask for a password.

• discover_machines

  Machines the user can already reach that are not added yet: the Host entries of their ~/.ssh/config, and the machines on their tailnet. Offer the ones that look relevant; add one with add_machine(ssh_command=its name) once the user agrees.

• doctor_machine

  Why a machine will not let fleet in, and the exact fix for it: the key line to run there, the provider account to add the key to, or the Tailscale SSH rule. Changes nothing; tell the user what it says -- access is theirs to grant.

• edit_machine

  Label a machine, or change what it costs per hour (for the $/HR column and burn rate), how it is reached, or which disks to watch for free space: disk_paths means exactly these paths from now on -- for a container or rental whose `/` is not where the space is -- and autodetect_disks goes back. rename gives it a new name, alias a short one (empty clears it). Tags, cost and note are written to the machine's own machine.yaml, so everyone who looks at it reads them; local=True keeps tags and cost in this machine's list instead (for a machine you cannot or should not write to). Measured facts such …

• list_gpu_jobs

  Every job on every GPU across the fleet -- who runs it, how much VRAM, for how long, the command -- and which GPUs are idle. A GPU with jobs is someone's: ask before using it.

• list_machines

  Every machine, with what is free right now. Filter with `tag` to pick by capability -- repeated tags must all match. Facts include gpu, cuda, rocm, metal, multi-gpu, vram-NNg, linux/macos/windows, x86_64/arm64, cores-NN, ram-NNg, storage-NNt, public-ip/mesh/lan, rental/shared/appliance, plus any tag a human set.

• list_models

  Every model being served across the fleet: machine, server, url, and for a server that only listens on its own machine a `tunnel` command to reach it; plus the folders each machine keeps models in. Check this before downloading a model: one already served or on disk need not be fetched.

• run_on_machine

  Run one command on a machine and return its output and exit code. This is how work actually gets started -- fleet resolves the address and connects as the user does, so never build an ssh command by hand. Returns within 120 seconds: start long jobs detached (nohup ... > log 2>&1 &).

• set_machine_endpoint

  Declare a model server the probe would not find by itself (an unusual port, a program it does not recognise), in the machine's own machine.yaml: port, and a base path if it is not /v1. port=None removes it. Never pass an API key; a server that wants one is shown as wanting one.

• set_machine_paths

  Record where a machine keeps things, in its own machine.yaml: kind is models, datasets, media, scratch, envs or one of your own; paths replace that kind's folders, and an empty list clears it. Ask the user where before recording a folder they did not name.

• show_machine

  Full detail for one machine: CPU, RAM, every GPU and its jobs, mounts, listening services, the models its servers serve, its software (cuda, python, and each Python environment's torch/vllm/mlx/... versions), the folders it keeps models, datasets and media in, tags and facts. No name means the machine fleet is running on.

Signals

Stars

0

Forks

0

Open issues

0

Weekly downloads

133

Last commit

Oct 24, 2026 (5 days ago)

Last release

Oct 14, 2026 (15 days ago)

Last package publish

Oct 14, 2026 (15 days ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name

io.github.lion-zhang/fleet

Version

0.5.2

Auth

No auth

Packages

pypi agents-fleet

License

MIT

Repository

github.com/lion-zhang/fleet

Website

github.com/lion-zhang/fleet

First seen

Oct 24, 2026

Last checked

Oct 24, 2026

Source

Official MCP Registrygithub-graphql