OpenCode Orchestrator

Multi-Agent Plugin for OpenCode

What is this?

A 6-agent collaborative system that turns any LLM into a reliable coding team.

Core idea: Break complex tasks into atomic units, verify each step, fix errors automatically.

Why Orchestrator?

Traditional	With Orchestrator
One big prompt → Hope it works	Atomic tasks → Verified every step
Expensive model required	Any model works
Errors compound silently	Self-correcting loop
Unpredictable results	Relentless execution until success

Features

🦀 Rust Core — Fast, memory-safe search and analysis tools
🧠 Micro-Task Architecture — Atomic task decomposition for reliability
🔄 Self-Correcting Loop — Every change reviewed, errors auto-fixed
👥 6-Agent Team — Specialized roles working together
🛡️ Resilient Execution — Never stops on errors. Pivots strategy (Plan/Search) until success.
⚡ Full Autonomy — /auto is all you need. Relentless execution until 100% complete.
🏗️ Rust-Powered Core — Critical logic written in Rust for peak performance and memory efficiency.
🪶 Thin TS Wrapper — Minimal JavaScript overhead. The heavy lifting happens in the native binary.

How It Works

User Request
     │
     ▼
┌─────────┐
│ PLANNER │ → Break into atomic tasks
└────┬────┘
     │
     ▼
┌──────────────────────────────────────────┐
│  For each task:                          │
│                                          │
│   Search → Code → Review → Fix           │
│       ↑                      │           │
│       └──────────────────────┘           │
│           (Never gives up)               │
└──────────────────────────────────────────┘
     │
     ▼
✅ Done

Install

npm install opencode-orchestrator

Auto-registers with OpenCode. Just restart.

Usage

/auto implement user authentication with JWT

Commands

Command	Description
`/auto`	Autonomous execution until complete
`/plan`	Decompose into atomic tasks
`/review`	Quality check
`/fix`	Fix specific error
`/search`	Find patterns in codebase

Agents

Agent	Role
Orchestrator	Team leader — coordinates, decides, adapts
Planner	Breaks work into atomic tasks
Coder	Implements one task at a time
Reviewer	Quality gate — catches all errors
Fixer	Targeted error resolution
Searcher	Finds context before coding

Documentation

Architecture — Detailed workflow
Configuration — Customize settings

Open Source

MIT License. No telemetry. No backdoors.

github.com/agnusdei1207/opencode-orchestrator

Author's Note

My goal is to prove that affordable models like GLM-4.7 can produce results as good as expensive APIs — when you structure the work right.

Break tasks down, verify every step, fix errors automatically. The model doesn't need to be smart. The process needs to be disciplined.

— @agnusdei1207

License

MIT