Show HN: Subagent-fleet – AI coding subagents across local Ollama machines

akarnam371 pts0 comments

subagent-fleet · PyPI

Skip to main content<br>Switch to mobile version

Warning

You are using an unsupported browser, upgrade to a newer version.

Warning

Some features may not work without JavaScript. Please try enabling it if you encounter problems.

Search PyPI

Search

subagent-fleet 0.0.1

pip install subagent-fleet

Copy PIP instructions

Latest release

Released:<br>Jun 15, 2026

Run Claude Code-style subagents across your local model fleet.

Navigation

Verified details

These details have been verified by PyPI<br>Maintainers

adityak74

Unverified details

These details have not been verified by PyPI

Meta

License Expression: MIT

SPDX<br>License Expression

Author: Aditya Karnam

Requires: Python >=3.10

Provides-Extra:<br>dev

Report project as malware

Project description

subagent-fleet

Run Claude Code-style subagents across your local model fleet.

subagent-fleet is a config-first Python CLI for mapping coding subagents to the best Ollama model and machine you own, then generating LiteLLM and Claude Code-style agent configuration.

Quickstart • Configuration • Generated Files • Security • Roadmap

Overview

Local model users often have more than one useful machine: a laptop, a Mac mini, a workstation, a home server, or a spare GPU box. Most coding harnesses still point at one model endpoint.

subagent-fleet turns that setup into a private local subagent fleet:

planner -> small fast model on a lightweight node<br>implementer -> larger coding model on a bigger node<br>reviewer -> larger coding model on a bigger node<br>summarizer -> small local model on the controller

It does not replace Ollama, LiteLLM, or Claude Code. It generates the glue between them:

Claude Code / coding harness<br>LiteLLM gateway generated by subagent-fleet<br>+-- Ollama node: laptop<br>+-- Ollama node: Mac mini 64GB<br>+-- Ollama node: workstation

Features

Validate a declarative fleet.yaml.

Discover models from configured Ollama nodes via /api/tags.

Generate litellm_config.yaml with ollama_chat/ routes.

Generate Claude Code-style .claude/agents/*.md files.

Generate .env.subagent-fleet for Claude Code/LiteLLM environment variables.

Warm configured Ollama models with keep_alive.

Show node health and agent routing tables.

Keep unreachable nodes isolated so one offline machine does not crash the whole workflow.

Status

MVP CLI implemented.

Available commands:

subagent-fleet init<br>subagent-fleet validate<br>subagent-fleet discover<br>subagent-fleet generate<br>subagent-fleet warmup<br>subagent-fleet status<br>subagent-fleet doctor<br>subagent-fleet clean<br>subagent-fleet skills list<br>subagent-fleet skills install<br>subagent-fleet plugins install

Install

Choose one of the install paths below.

CLI from GitHub

Install the CLI directly from PyPI:

python -m pip install subagent-fleet

Or install it as an isolated command with pipx:

pipx install subagent-fleet

Verify:

subagent-fleet --help

Development Checkout

Use this when contributing to the project:

git clone https://github.com/adityak74/subagent-fleet.git<br>cd subagent-fleet<br>python -m pip install -e ".[dev]"

Run tests:

python -m pytest

Claude Code Plugin First

Install the plugin first from Claude Code, then let the bundled bootstrap skill install the CLI:

/plugin marketplace add https://github.com/adityak74/subagent-fleet<br>/plugin install subagent-fleet

After install, ask Claude Code:

Use the subagent-fleet bootstrap skill to install the CLI and set up this repo.

The bootstrap skill will run or recommend:

python -m pip install subagent-fleet<br>subagent-fleet skills install

Codex Plugin First

Install this repository as a local Codex marketplace:

codex plugin marketplace add .<br>codex plugin add subagent-fleet@subagent-fleet

Then ask Codex:

Use the subagent-fleet bootstrap skill to install the CLI and set up this repo.

Quickstart

Create a starter config:

subagent-fleet init

Edit fleet.yaml with your Ollama node endpoints and model names, then validate it:

subagent-fleet validate

Check which nodes are reachable:

subagent-fleet discover

Generate LiteLLM, Claude agent, and environment files:

subagent-fleet generate

Start LiteLLM:

export LITELLM_MASTER_KEY="sk-local-dev"

litellm \<br>--config ./litellm_config.yaml \<br>--host 127.0.0.1 \<br>--port 4000

Point Claude Code at the local gateway:

source .env.subagent-fleet<br>claude

Configuration

subagent-fleet is driven by fleet.yaml.

project:<br>name: local-dev<br>gateway:<br>provider: litellm<br>host: 127.0.0.1<br>port: 4000<br>master_key_env: LITELLM_MASTER_KEY

nodes:<br>m5-local:<br>endpoint: http://localhost:11434<br>tags: [controller, local, fast]

m4-mini-64gb:<br>endpoint: http://192.168.1.50:11434<br>tags: [heavy, coder, reviewer]

m4-mini-16gb:<br>endpoint: http://192.168.1.51:11434<br>tags: [small, planner, summarizer]

models:<br>heavy-coder:<br>node: m4-mini-64gb<br>ollama_model: qwen2.5-coder:32b<br>litellm_alias: claude-sonnet-local<br>context: 32768<br>timeout: 600<br>max_parallel: 1

small-coder:<br>node: m4-mini-16gb<br>ollama_model: qwen2.5-coder:7b<br>litellm_alias: claude-haiku-local<br>context:...

fleet subagent install claude local code

Related Articles