Open Source · MIT License Zero Dependencies Cross-Platform .NET 10

One developer.
An entire fleet.

Armada orchestrates multiple AI coding agents working in parallel on your codebase. Dispatch tasks, isolate work in git worktrees, and merge safely — all from a single command.

Get Started View on GitHub
# One command to dispatch a fleet of agents
$ armada go "Harden the API: 1) Add rate limiting 2) Add input validation 3) Add request logging"

Admiral Initializing fleet...
Admiral ✓ Vessel detected: task-api (~/projects/task-api)
Admiral ✓ 3 missions created, dispatching captains
Captain-1 [msn_1] Add rate-limiting middleware
Captain-2 [msn_2] Add input validation to POST /tasks
Captain-3 [msn_3] Add request logging with correlation IDs

Admiral ✓ Voyage complete: 3/3 missions succeeded (7m 22s)
$ _
The Killer Feature

Your AI agent becomes the orchestrator

Chat with your favorite AI assistant and have it command an entire fleet of agents under your fingertips. Armada's MCP server exposes numerous tools that let any MCP-capable AI decompose work, dispatch parallel missions, monitor progress, handle failures, and merge results — autonomously.

You describe what you want in natural language. Your AI orchestrator figures out the plan and executes it through Armada. One conversation, multiple agents, zero manual coordination.

◆ Claude Code ◆ Codex ◆ Gemini ◆ Cursor
Set Up AI Orchestration
  AI Orchestrator Session
/* You chat naturally — your AI handles the rest */ You: "Harden the task API with validation, rate limiting, and request logging." AI: I'll create a voyage with 3 missions and dispatch them in parallel... ▶ armada_voyage_create ▶ armada_voyage_dispatch ▶ armada_voyage_status ... ✓ All 3 missions complete. Branches merged to main. Ready for your review.
Capabilities

Everything you need to orchestrate at scale

Multi-agent coordination, built from the ground up, with AI, for AI.

⚙

Zero-Config Startup

Run armada go and everything auto-initializes: runtime detection, repo registration, captain provisioning, worktree creation. No setup files or configuration needed.

⚖

Git Worktree Isolation

Every agent works in its own isolated git worktree. No interference between parallel agents. Broad-scope conflict detection prevents concurrent mutations to the same files.

♻

Auto-Recovery

Crashed agents are automatically detected, repaired, and relaunched with configurable retry limits. Stall detection catches agents that stop making progress.

⚗

Merge Queue

Bors-style merge queue with batch testing and binary bisection on failure. Safely merge parallel work with confidence. Optional auto-push, auto-PR, and auto-merge.

⇄

REST API

Full CRUD API on port 7890 for programmatic control. Create fleets, dispatch voyages, monitor missions, query events — integrate Armada into any workflow.

⚡

Real-Time WebSocket

Live event streaming on port 7892. Subscribe to mission updates, captain status changes, and system snapshots for dashboards and reactive workflows.

☍

Numerous MCP Tools

Standards-compliant Model Context Protocol server with numerous tools covering the full surface area. Any MCP-capable AI can orchestrate Armada programmatically.

▣

Desktop Application

Cross-platform Avalonia desktop app with real-time dashboard, mission viewer, log tail, diff viewer, dispatch interface, and system diagnostics.

☑

Web Dashboard

Built-in HTML5 dashboard with live WebSocket updates. Monitor captains, missions, voyages, signals, and merge queue from your browser. Zero setup.

Architecture

Built for reliability, not complexity

Zero external dependencies. Pure .NET with embedded SQLite. Runs anywhere .NET 10 runs.

You
CLI / AI Chat / API
↓
Coordinator
Admiral
↓    ↓    ↓
REST API
Port 7890
MCP Server
Port 7891
WebSocket
Port 7892
↓    ↓    ↓
Agent
Captain 1
Agent
Captain 2
Agent
Captain 3
↓    ↓    ↓
Isolated
Worktree 1
Isolated
Worktree 2
Isolated
Worktree 3
See It In Action

Web dashboard & desktop application

Monitor your fleet in real time through the built-in web dashboard or cross-platform desktop app.

Armada Web Dashboard - System Status
Web Dashboard — System status with captains, missions, and real-time signals
Armada Voyage Detail
Voyage Detail — Track batched missions with progress and branch info
Armada Mission Detail
Mission Detail — Full context including diff, status, and timing
Armada Desktop Application
Desktop App — Cross-platform Avalonia GUI with real-time updates
Armada Desktop - Mission Log and Diff
Desktop App — Mission list with log viewer and code diff
Use Cases

Scale how you work

From solo developers to teams, Armada multiplies your throughput.

Parallel Feature Development

Decompose a feature into non-overlapping tasks and dispatch agents to work on all of them simultaneously. Merge when done.

Codebase-Wide Refactoring

Fan out mechanical changes across your codebase — rename patterns, update imports, migrate APIs — all in parallel.

Bug Triage at Scale

Dispatch investigation and fixes across multiple reported issues simultaneously. Each agent works in isolation with full context.

Multi-Repo Coordination

Register multiple repositories as vessels in a fleet. Dispatch related work across repos in a single voyage.

Explore Multiple Approaches

Prototype different solutions to the same problem in parallel worktrees. Compare results and pick the winner.

CI/CD Prep & Hardening

Batch security hardening, test coverage improvements, and documentation updates as parallel missions before a release.

Command Line

Powerful CLI, intuitive commands

Everything you need from your terminal. Rich output powered by Spectre.Console.

armada go "<prompt>"
Auto-init, detect runtime, spawn captain, dispatch task. The one command to rule them all.
armada status
Dashboard scoped to current repo. Add --all for global view across all vessels.
armada watch
Live auto-refreshing dashboard with desktop notifications on mission completion or failure.
armada voyage create
Create a batch of related missions with description, vessel targeting, and priority control.
armada log <captain> -f
Tail a specific agent's output in real time. Like tail -f for your AI agents.
armada mcp install
Auto-install MCP server + custom orchestrator agent. Enable AI-as-orchestrator in one command.
armada doctor
System health check. Validates runtimes, connectivity, git state, and configuration.
armada config init
Interactive setup wizard for all settings. MaxCaptains, auto-push, notifications, and more.
Quick Start

Up and running in minutes

Just .NET 10+ SDK and an AI coding agent. That's all you need.

1

Install Armada

Clone the repo and install as a global .NET tool:

git clone https://github.com/jchristn/armada cd armada/src dotnet tool install -g Armada.Helm
2

Dispatch Your First Task

Navigate to any git repo and go:

cd ~/projects/my-api armada go "Add input validation to the signup form"
3

Enable AI Orchestration

Let your AI assistant control the fleet:

armada mcp install claude --agent armada
Documentation

Extensively documented

Comprehensive guides, API references, and orchestrator setup instructions for every supported runtime.

📑

REST API Reference

Full CRUD endpoints, authentication, pagination, and filtering.
⚙

MCP API Reference

All MCP tools with parameters, examples, and usage patterns.
⚡

WebSocket API

Real-time event streaming, subscriptions, and commands.
🤖

Orchestrator Guides

Setup instructions for Claude Code, Codex, Gemini, and Cursor.
🚀

Postman Collection

Ready-to-import collection for testing the full REST API surface.

Ready to scale yourself?

Install Armada, run armada go, and let your fleet handle the rest.

Get Started Star on GitHub