npx claudepluginhub first-fluke/oh-my-agentPortable multi-agent harness for .agents-based skills and workflows across Claude Code, Codex, Gemini, and more
Share bugs, ideas, or general feedback.
한국어 | 中文 | Português | 日本語 | Français | Español | Nederlands | Polski | Русский | Deutsch | Tiếng Việt
Ever wished your AI assistant had coworkers? That's what oh-my-agent does.
Instead of one AI doing everything (and getting confused halfway through), oh-my-agent splits work across specialized agents — frontend, backend, QA, PM, DB, mobile, infra, debug, design, and more. Each one knows its domain deeply, has its own tools and checklists, and stays in its lane.
Works with all major AI IDEs: Antigravity, Claude Code, Cursor, Gemini CLI, Codex CLI, OpenCode, and more.
# One-liner (auto-installs bun & uv if missing)
curl -fsSL https://raw.githubusercontent.com/first-fluke/oh-my-agent/main/cli/install.sh | bash
# Or manual
bunx oh-my-agent@latest
install.sh supports macOS/Linux only. On Windows, install bun and uv manually, then run bunx oh-my-agent@latest.
Pick a preset and you're ready:
| Preset | What You Get |
|---|---|
| ✨ All | Every agent and skill |
| 🌐 Fullstack | frontend + backend + db + pm + qa + debug + brainstorm + commit |
| 🎨 Frontend | frontend + pm + qa + debug + brainstorm + commit |
| ⚙️ Backend | backend + db + pm + qa + debug + brainstorm + commit |
| 📱 Mobile | mobile + pm + qa + debug + brainstorm + commit |
| 🚀 DevOps | tf-infra + dev-workflow + pm + qa + debug + brainstorm + commit |
| Agent | What They Do |
|---|---|
| oma-brainstorm | Explores ideas before you commit to building |
| oma-pm | Plans tasks, breaks down requirements, defines API contracts |
| oma-frontend | React/Next.js, TypeScript, Tailwind CSS v4, shadcn/ui |
| oma-backend | APIs in Python, Node.js, or Rust |
| oma-db | Schema design, migrations, indexing, vector DB |
| oma-mobile | Flutter cross-platform apps |
| oma-design | Design systems, tokens, accessibility, responsive |
| oma-qa | OWASP security, performance, accessibility review |
| oma-debug | Root cause analysis, fixes, regression tests |
| oma-tf-infra | Multi-cloud Terraform IaC |
| oma-dev-workflow | CI/CD, releases, monorepo automation |
| oma-translator | Natural multilingual translation |
| oma-orchestrator | Parallel agent execution via CLI |
| oma-commit | Clean conventional commits |
| oma-pdf | PDF to Markdown conversion |
Just chat. Describe what you want and oh-my-agent figures out which agents to use.
You: "Build a TODO app with user authentication"
→ PM plans the work
→ Backend builds auth API
→ Frontend builds React UI
→ DB designs schema
→ QA reviews everything
→ Done: coordinated, reviewed code
Or use slash commands for structured workflows:
| Command | What It Does |
|---|---|
/plan | PM breaks down your feature into tasks |
/coordinate | Step-by-step multi-agent execution |
/orchestrate | Automated parallel agent spawning |
/ultrawork | 5-phase quality workflow with 11 review gates |
/review | Security + performance + accessibility audit |
/debug | Structured root-cause debugging |
/design | 7-phase design system workflow |
/brainstorm | Free-form ideation |
/commit | Conventional commit with type/scope analysis |
Auto-detection: You don't even need slash commands — keywords like "plan", "review", "debug" in your message (in 11 languages!) auto-activate the right workflow.
# Install globally
bun install --global oh-my-agent # or: brew install oh-my-agent
# Use anywhere
oma doctor # Health check
oma dashboard # Real-time agent monitoring
oma agent:spawn backend "Build auth API" session-01
oma agent:parallel -i backend:"Auth API" frontend:"Login form"