orch

npm install -g @oxgeneral/orch      # Install
cd ~/your-project && orch           # Launch TUI

You hired AI agents. Now you're managing them full-time.

You bought Claude, Codex, maybe Cursor. Each one is powerful alone. But your actual job isn't "use AI tools" — it's ship a product at the speed of a full team, while being one person.

Here's what that looks like today:

• You open 3 terminals. Copy-paste context between them. Forget which agent is doing what.
• One agent edits a file another is working on. Merge conflict. You fix it manually.
• An agent crashes at 2am. You don't notice until morning. Half a night wasted.
• You spend 40-60% of your time routing agents instead of building your product.

You're not the founder. You're the bottleneck.

What if your agents coordinated themselves?

$ orch org deploy startup-mvp --goal "Implement user auth with OAuth2"

  ✓ Deployed team "platform" — 5 agents
    CTO (claude)       → Decomposing goal into tasks...
    Backend A (claude)  → Waiting for tasks
    Backend B (codex)   → Waiting for tasks
    QA (codex)          → Waiting for tasks
    Reviewer (claude)   → Waiting for reviews

  ✓ CTO created 6 tasks from goal

$ orch run --all --watch

  22:03  ▶ Backend A    → "Implement OAuth2 flow"         [feature/oauth]
  22:03  ▶ Backend B    → "JWT token service"              [feature/jwt]
  22:03  ▶ QA           → waiting for implementations...
  22:15  ✓ Backend B    DONE  (12m · 4,200 tokens)
  22:15  ▶ QA           → "Test JWT service"               [test/jwt]
  22:22  ✓ Backend A    DONE  (19m · 8,100 tokens)
  22:24  ↻ QA           RETRY  attempt 2/3
  22:28  ✓ QA           DONE  (6m · 2,800 tokens)
  22:29  ▶ Reviewer     → "Review OAuth2 implementation"
  22:33  ✓ Reviewer     DONE  → all tasks in review

  → You went to sleep at 22:05.
  → You wake up to 6 tasks in review. Approve. Merge. Ship.

Start coordinating agents in 30 seconds

That's it. ORCH auto-initializes and opens the TUI dashboard. Add agents, set goals, and run — right from there.

Claude Code integration

After install, the /orch skill is automatically available in Claude Code. Just type /orch and describe what you need in natural language:

/orch deploy a team to refactor the auth module and add tests

Claude will translate your intent into the right orch commands — create agents, tasks, goals, and run the orchestration. No need to memorize CLI flags.

Or deploy a pre-built team:

orch org deploy startup-mvp --goal "Build invoicing SaaS with Stripe"
orch run --all --watch

System requirements

Minimum 1-2 agents

OS	macOS, Linux, WSL2
CPU	2 cores
RAM	4 GB
Disk	300 MB
Node.js	>= 20

Recommended — full department 4-6 agents

OS	macOS, Linux, WSL2
CPU	4+ cores
RAM	8 GB
Disk	1 GB
Node.js	>= 20

Your code is safe

Every agent works in an isolated git worktree. Your main branch is never touched until you explicitly approve and merge. Mandatory review step in the state machine — no code ships without your OK. Agents can't overwrite each other's work.

ORCH itself is lightweight (~120 MB). The RAM goes to the agent CLI processes that ORCH spawns — each is a separate Node.js/Python runtime:

Agent process	RAM per instance	Why
Claude Code CLI	200-400 MB	Full Node.js runtime + context window
OpenCode	200-400 MB	Node.js + provider SDK
Codex CLI	150-300 MB	Python runtime + OpenAI SDK
Pi coding agent	200-400 MB	Node.js runtime + Pi tools/extensions
Cursor CLI	200-400 MB	Electron-based agent
Shell scripts	10-50 MB	Depends on the tool

Formula: 120 MB (ORCH) + N × ~300 MB per concurrent agent. 2 agents ≈ 0.7 GB, 4 agents ≈ 1.3 GB, 6 agents ≈ 2 GB.

How your AI team works

CTO — strategic decomposition

Set a high-level goal. Your CTO agent decomposes it into concrete tasks, assigns priorities, and delegates to the right departments. You set strategy — AI executes.

Engineering Department — parallel execution

Backend A, Backend B, Frontend — each agent gets its own git worktree (isolated branch). They work in parallel without file conflicts. Failed? Auto-retry with exponential backoff. Stalled? Zombie detection kills and re-queues.

QA Department — automated verification

QA agents pick up completed work, run tests, validate contracts. Reject with feedback → task goes back to engineering with your notes. The loop closes automatically.

Inter-department communication

Agents talk to each other — direct messages, team broadcasts, shared context store. Backend finishes auth module → sends message to QA → QA starts testing. No copy-paste. No manual routing.

Code Review — mandatory quality gate

Nothing touches main until reviewed. Every task flows through the state machine:

Every transition validated. No task gets lost. No code merges without approval.

Not just engineering

ORCH orchestrates any process — not just code. The shell adapter runs any CLI tool, which means any workflow becomes an automated pipeline:

Department	Agents	What they do
Engineering	Claude, Codex, Pi, Cursor	Write code, fix bugs, refactor
Editorial	Claude (writer), Claude (editor), Shell (grammarly)	Write articles, edit, check grammar, publish
Sales Ops	Shell (CRM scripts), Claude (copywriter), Shell (email sender)	Generate leads, write sequences, send outreach
Analytics	Shell (pandas, duckdb), Claude (analyst), Shell (matplotlib)	Clean data, compute KPIs, generate reports
Content Factory	Claude (strategist), Claude (writer x2), Claude (SEO)	Plan content calendar, write posts, optimize
Security	Shell (Semgrep, Trivy, Gitleaks), Claude (hunter)	Scan code, correlate findings, auto-fix
DevOps	Shell (terraform, kubectl), Claude (architect)	Plan infra changes, apply, verify

Every department gets the same superpowers: state machine governance, retry, messaging, isolation, review gate.

Why founders choose ORCH

Works with every tool — AI or not