Skip to content

subagent-fleet

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

subagent-fleet is a local AI compute control plane for Claude Code and coding agents. It maps coding subagents to the best Ollama model and machine you own, then generates LiteLLM and Claude Code-style agent configuration — with real-time health monitoring, SSE dashboards, execution tracing, and model warmup.

GitHub Repo stars License: MIT Python CLI Ollama LiteLLM GitHub last commit GitHub issues

Quickstart • Configuration • Examples • 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
implementer -> larger coding model on a bigger node
reviewer    -> larger coding model on a bigger node
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
        |
        v
LiteLLM gateway generated by subagent-fleet
        |
        +-- Ollama node: laptop
        +-- Ollama node: Mac mini 64GB
        +-- Ollama node: workstation

Features

  • Monitor node health in real time — unreachable nodes are isolated automatically.
  • Route subagents by role: planner → fast model, implementer → large coding model.
  • Warm models before workflows start, with live dashboard progress.
  • Stream and trace LiteLLM execution logs in real time.
  • Generate LiteLLM and Claude Code agent configuration from fleet.yaml.
  • Validate, discover, and inspect your fleet with a single command.

Status

v0.4.0 — queue-aware scheduler and dynamic routing release.

Interactive Fleet Dashboard

Run subagent-fleet ui to open a live-updating dashboard that monitors your fleet in real time via SSE:

Panel What it does
Node Health Real-time online/offline status per node, with discovered Ollama models and endpoints.
Agent Routing Which agent maps to which model on which node — instantly visible.
Live Trace Stream Tail LiteLLM logs as they happen, colored by severity (routing → success → error).
Model Warmup Progress Track preload status when you run subagent-fleet warmup before a coding session.

Start the dashboard in one command — point it at your fleet config:

subagent-fleet ui --config fleet.yaml
# Opens http://localhost:8080

Here's what the Fleet Dashboard looks like monitoring a 3-node example fleet:

Fleet Dashboard

A responsive screenshot showing node health status, agent routing, trace stream, and warmup progress:

Fleet Dashboard Detail

And it adapts to any screen size — mobile view included:

Mobile View

Available commands:

subagent-fleet init
subagent-fleet validate
subagent-fleet discover
subagent-fleet generate
subagent-fleet warmup
subagent-fleet status
subagent-fleet doctor
subagent-fleet clean
subagent-fleet benchmark
subagent-fleet eval frontier
subagent-fleet classify "implement a feature"
subagent-fleet route "implement a feature"
subagent-fleet routes
subagent-fleet schedule --task-type coding
subagent-fleet ui
subagent-fleet trace
subagent-fleet --version
subagent-fleet skills list
subagent-fleet skills install
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
cd subagent-fleet
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
/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
subagent-fleet skills install

Codex Plugin First

Install this repository as a local Codex marketplace:

codex plugin marketplace add .
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 \
  --config ./litellm_config.yaml \
  --host 127.0.0.1 \
  --port 4000

Point Claude Code at the local gateway:

source .env.subagent-fleet
claude

Configuration

subagent-fleet is driven by fleet.yaml.

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

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

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

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

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

  small-coder:
    node: m4-mini-16gb
    ollama_model: qwen2.5-coder:7b
    litellm_alias: claude-haiku-local
    context: 8192
    timeout: 300
    max_parallel: 1

agents:
  planner:
    model: small-coder
    description: Use for planning, file discovery, task decomposition, and summarization.
    tools: [Read, Grep, Glob]
    prompt: |
      You are a fast local planning agent.
      Do not edit files.
      Return a concise response with:
      - plan
      - relevant files
      - risks
      - next recommended agent

  implementer:
    model: heavy-coder
    description: Use for implementation, bug fixes, refactors, and patch creation.
    tools: [Read, Grep, Glob, Edit, MultiEdit, Bash]

  reviewer:
    model: heavy-coder
    description: Use after implementation to review diffs, tests, regressions, and maintainability.
    tools: [Read, Grep, Glob, Bash]

Generated Files

Running:

subagent-fleet generate

creates:

litellm_config.yaml
.claude/agents/planner.md
.claude/agents/implementer.md
.claude/agents/reviewer.md
.env.subagent-fleet

Example LiteLLM route:

model_list:
  - model_name: claude-sonnet-local
    litellm_params:
      model: ollama_chat/qwen2.5-coder:32b
      api_base: http://192.168.1.50:11434
      api_key: ollama
      timeout: 600
    model_info:
      max_input_tokens: 32768

Example Claude agent:

---
name: planner
description: Use for planning, file discovery, task decomposition, and summarization.
model: claude-haiku-local
tools: Read, Grep, Glob
---

You are a fast local planning agent.
Do not edit files.
Return a concise response with:
- plan
- relevant files
- risks
- next recommended agent

Commands

Command Purpose
subagent-fleet init Create a starter fleet.yaml.
subagent-fleet validate Validate schema, references, URLs, aliases, and agent names.
subagent-fleet discover Query configured Ollama nodes for available models.
subagent-fleet generate Generate LiteLLM config, Claude agents, and env file.
subagent-fleet warmup Preload configured Ollama models with keep_alive.
subagent-fleet status Show node health and agent routing.
subagent-fleet benchmark Benchmark node latency and rank the fleet.
subagent-fleet eval frontier Run the fleet-vs-frontier coding quality/cost comparison.
subagent-fleet classify Classify a message into a task type.
subagent-fleet route Route a message to the best model/node.
subagent-fleet routes Show the full task-type routing table.
subagent-fleet schedule Compute queue-aware scheduling decisions.
subagent-fleet doctor Show validation and local-network safety guidance.
subagent-fleet clean List or remove generated files.
subagent-fleet --version Print the installed CLI version.
subagent-fleet skills list List bundled assistant skills and supported targets.
subagent-fleet skills install Install assistant-facing setup and operations skills.
subagent-fleet plugins install Install Claude Code and Codex plugin marketplace bundles.

JSON output is available for discovery and status:

subagent-fleet discover --json
subagent-fleet status --json

Assistant Skills

subagent-fleet ships assistant-facing skills that teach Claude Code, Codex, OpenCode, and similar tools how to set up and operate the fleet from inside a repository.

List bundled skills and supported targets:

subagent-fleet skills list

Install all bundled skills for all supported targets:

subagent-fleet skills install

This writes:

.claude/skills/subagent-fleet-setup/SKILL.md
.claude/skills/subagent-fleet-operations/SKILL.md
.codex/skills/subagent-fleet-setup/SKILL.md
.codex/skills/subagent-fleet-operations/SKILL.md
.opencode/skills/subagent-fleet-setup/SKILL.md
.opencode/skills/subagent-fleet-operations/SKILL.md

Install for a specific assistant:

subagent-fleet skills install --target codex
subagent-fleet skills install --target claude-code
subagent-fleet skills install --target opencode

Install one bundled skill:

subagent-fleet skills install --skill subagent-fleet-setup

Existing skill files are not overwritten unless you pass --force.

Plugin Marketplaces

This repository also ships plugin marketplace metadata so users can install the assistant skill first, then let that skill install and verify the Python CLI.

Included plugin artifacts:

.claude-plugin/marketplace.json
.agents/plugins/marketplace.json
plugins/subagent-fleet/.claude-plugin/plugin.json
plugins/subagent-fleet/.codex-plugin/plugin.json
plugins/subagent-fleet/skills/subagent-fleet-bootstrap/SKILL.md
plugins/subagent-fleet/skills/subagent-fleet-setup/SKILL.md
plugins/subagent-fleet/skills/subagent-fleet-operations/SKILL.md

The bootstrap skill teaches Claude Code or Codex how to install the CLI:

python -m pip install subagent-fleet

and then install repo-local assistant skills:

subagent-fleet skills install

Claude Code plugin install flow:

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

Codex local marketplace flow:

codex plugin marketplace add .
codex plugin add subagent-fleet@subagent-fleet

To generate the same marketplace/plugin bundle into another directory:

subagent-fleet plugins install --out /path/to/marketplace-root

Install only one target:

subagent-fleet plugins install --target claude-code
subagent-fleet plugins install --target codex

Existing plugin marketplace files are not overwritten unless you pass --force.

Ollama Worker Setup

On each worker machine, run Ollama on a private interface reachable from your controller:

launchctl setenv OLLAMA_HOST "0.0.0.0:11434"
launchctl setenv OLLAMA_KEEP_ALIVE "-1"
launchctl setenv OLLAMA_NUM_PARALLEL "1"
launchctl setenv OLLAMA_MAX_LOADED_MODELS "1"

killall Ollama
open -a Ollama

From the controller:

curl http://NODE_IP:11434/api/tags

Security

subagent-fleet assumes private local networking.

Do:

  • Use LAN, firewall rules, Tailscale, WireGuard, or a private subnet.
  • Keep LITELLM_MASTER_KEY set for LiteLLM access.
  • Treat generated .env.subagent-fleet files as local developer configuration.

Do not:

  • Expose Ollama directly to the public internet.
  • Expose LiteLLM without authentication.
  • Commit real API keys, LAN secrets, or machine-specific private .env files.

Run:

subagent-fleet doctor

for local setup and safety reminders.

Development

Install dev dependencies:

python -m pip install -e ".[dev]"

Run tests:

python -m pytest

Run a focused test:

python -m pytest tests/test_config.py

Check CLI wiring:

python -m subagent_fleet.cli --help

Project Layout

src/subagent_fleet/
  cli.py
  config.py
  discovery.py
  plugins.py
  warmup.py
  status.py
  skills.py
  generators/
  skill_templates/
  templates/

examples/
plugins/
tests/

Examples

See examples/ for complete fleet configurations and generated output:

Directory What it shows
ollama-laptop-only/ Single-machine setup — everything on one laptop running Ollama
multi-node-cluster/ Three-node fleet — laptop + Mac mini (64GB) + GPU workstation
litellm-proxy/ Generated LiteLLM config showing how models route to nodes
claude-agents/ Claude Code agent definitions generated from a fleet YAML

Quick start with the multi-node example:

subagent-fleet validate --config examples/multi-node-cluster/fleet.yaml
subagent-fleet generate --config examples/multi-node-cluster/fleet.yaml
subagent-fleet ui --config examples/multi-node-cluster/fleet.yaml

Roadmap

MVP:

  • [x] fleet.yaml schema
  • [x] Ollama node health checks
  • [x] Ollama model discovery via /api/tags
  • [x] LiteLLM config generation
  • [x] Claude Code agent generation
  • [x] Environment file generation
  • [x] Model warmup with keep_alive
  • [x] Status and routing tables

Next:

  • [x] Real-time SSE dashboard (node health, routing, warmup, trace stream)
  • [x] Execution trace viewer (subagent-fleet trace)
  • [x] Generative UI dashboard (subagent-fleet ui)
  • [ ] Latency benchmarking
  • [ ] Recommended agent-to-node assignment
  • [ ] Role-based routing templates
  • [ ] Tailscale-aware node discovery
  • [ ] OpenAI-compatible harness examples
  • [ ] Release packaging

Later:

  • [ ] Dynamic routing by task type
  • [ ] Fallback model generation
  • [ ] Queue-aware scheduling
  • [ ] Support for vLLM, LM Studio, llama.cpp, OpenRouter, and cloud APIs

Star History

Star History Chart

Contributing

Issues and pull requests are welcome.

Good first areas:

  • More generator tests
  • Additional example fleets
  • Better status formatting
  • More robust Ollama error reporting
  • Documentation for real multi-machine setups

Before opening a PR:

python -m pytest

What This Is Not

subagent-fleet is not:

  • an inference engine
  • a replacement for Ollama
  • a replacement for LiteLLM
  • a model sharding framework
  • Kubernetes for local LLMs
  • a public model hosting platform

It is a small workflow layer for private local subagent orchestration.

License

MIT. See LICENSE.