oh-my-agent

oh-my-agent: The Multi-Agent Harness That Checks the Work

한국어 | 中文 | Português | 日本語 | Français | Español | Nederlands | Polski | Русский | Deutsch | Tiếng Việt | ภาษาไทย

Agents narrate success. oh-my-agent checks the artifacts.

Spawning parallel agents is the easy part. The hard part is knowing whether they actually did the work. "Tests pass, all criteria met" costs an agent nothing to say, and nothing inside that same session can contradict it.

oh-my-agent makes the claim falsifiable. A Stop hook refuses to end your session until your project's own typecheck / test / lint script exits 0. A gate command decides whether a workflow really ran by looking for the artifacts it must have left behind — and its JSON verdict, not the agent's summary, is the result. An independent judge with a fresh context re-verifies every criterion each round, including the ones that already passed. Every gate decision lands on an append-only event log you can read after the fact. Then it runs that same discipline across a dozen agent runtimes from one portable .agents/ directory.

Watch the full video (35s)

Quick Start

The install scripts below auto-install bun, uv, and serena if they're missing.

# macOS / Linux — auto-installs bun, uv & serena if missing
curl -fsSL https://raw.githubusercontent.com/first-fluke/oh-my-agent/main/cli/install.sh | bash

# Windows (PowerShell) — auto-installs bun, uv & serena if missing
irm https://raw.githubusercontent.com/first-fluke/oh-my-agent/main/cli/install.ps1 | iex

# Or manual (any OS, requires bun + uv + serena)
bunx oh-my-agent@latest

Or install skills with Microsoft's Agent Package Manager (APM). Click to expand.

Not to be confused with oma-observability's APM (Application Performance Monitoring).

# All skills, deployed to every detected runtime
# (.claude, .cursor, .codex, .opencode, .github, .agents)
apm install first-fluke/oh-my-agent

# A single skill
apm install first-fluke/oh-my-agent/.agents/skills/oma-frontend

APM ships skills only. For workflows, rules, oma-config.yaml, keyword-detection hooks, and the oma agent spawn CLI, use bunx oh-my-agent@latest. Pick one distribution per project to avoid drift.

Pick a preset and you're ready:

Preset	What You Get
All	Every agent and skill
Backend	architecture + backend + brainstorm + db + debug + dev-workflow + pm + qa + scm
Content	academic-writer + design + image + scm + translator + voice
DevOps	architecture + brainstorm + debug + dev-workflow + observability + pm + qa + scm + tf-infra
Frontend	architecture + brainstorm + debug + design + frontend + pm + qa + scm
Fullstack	architecture + backend + brainstorm + db + debug + design + dev-workflow + frontend + mobile + pm + qa + scm + tf-infra
Fullstack Mobile	architecture + backend + brainstorm + db + debug + design + dev-workflow + mobile + pm + qa + scm
Fullstack Web	architecture + backend + brainstorm + db + debug + design + dev-workflow + frontend + pm + qa + scm
Mobile	architecture + brainstorm + debug + mobile + pm + qa + scm
Research	academic-writer + hwp + market + pdf + scholar + scm + search + translator

Works With Every Agent

Verification is worth little if it's locked to one vendor. oh-my-agent keeps .agents/ as the single source of truth and projects it into each runtime's native layout, so every supported tool shares the same skills, workflows, rules, and gates — and switching vendors is a config change, not a migration.

Claude Code

native + adapter

Codex CLI

native + adapter

Antigravity

native SSOT

Cursor

native + adapter

Qwen Code

native dispatch

Reasonix

native-compatible

Pi

native-compatible

OpenCode

native-compatible

Amp

native-compatible

GitHub Copilot

symlinked skills

Grok Build

native hooks

Kiro CLI

native hooks + agents

& more

Your Engineering Team

Instead of one AI doing everything (and getting confused halfway through), oh-my-agent splits work across specialized agents. Each one knows its domain deeply, has its own tools and checklists, and stays in its lane.

Agent	What They Do
oma-architecture	Weighs architecture tradeoffs and draws module boundaries, with ADR/ATAM/CBAM analysis.
oma-backend	Builds and secures your APIs in Python, Node.js, or Rust.
oma-brainstorm	Explores ideas with you before you commit to building.
oma-db	Designs your schema, migrations, indexes, and vector stores.
oma-debug	Finds the root cause, fixes the bug, and writes a regression test.
oma-deepsec	Scans your code for security holes and blocks risky pull requests.
oma-design	Builds design systems with tokens, accessibility, and responsive layouts.
oma-dev-workflow	Automates your CI/CD, releases, and monorepo tasks.
oma-docs	Checks your docs for broken references and flags ones a code change touched.
oma-explanation	Turns a diff, PR, or branch into a self-contained interactive HTML explainer with a quiz.
oma-frontend	Builds your UI with React/Next.js, TypeScript, Tailwind CSS v4, and shadcn/ui.
oma-mobile	Builds cross-platform mobile apps with Flutter.
oma-observability	Routes observability work across metrics, logs, traces, SLOs, and incident forensics.
oma-orchestration	Runs multiple agents in parallel from the CLI.
oma-pm	Plans tasks, breaks down requirements, and defines API contracts.
oma-qa	Reviews your code for OWASP security, performance, and accessibility issues.
oma-refactor	Refactors code without changing its behavior, using hotspot targeting, characterization-test safety nets, and refactor-only commits.
oma-scm	Manages your branches, merges, worktrees, and Conventional Commits.
oma-search	Routes each query to the best source and scores how much you can trust the result.
oma-tf-infra	Provisions multi-cloud infrastructure with Terraform.

Internal & meta tools

Agent	What They Do
oma-coordination	Guides manual step-by-step coordination of PM, frontend, backend, mobile, and QA agents.
oma-skill-creation	Writes and audits new OMA skills in the SSL-lite format.

Beyond Code: Content & Research Pipelines

Separate from the engineering team, oma ships content and research pipelines built to the same engineering discipline: deterministic replay from fixtures, manifests for reproducibility, and honest degradation reporting when a source or vendor key is unavailable rather than a silently thinner result.

Agent	What They Do
oma-academic-writing	Drafts, revises, and audits academic prose to publication quality.
oma-hwp	Converts HWP, HWPX, and HWPML files to Markdown.
oma-image	Generates images through several AI providers at once.
oma-market	Researches your market from community signals and frames it with SWOT, 5F, and PESTEL.
oma-pdf	Converts PDF files to Markdown.
oma-recap	Recaps your conversation history into themed work summaries.
oma-scholar	Searches academic literature and helps you run peer review.
oma-slide	Generates distinctive, animation-rich HTML presentation decks and exports to PDF/PNG/PPTX.
oma-translation	Translates between languages so it reads like a native wrote it.
oma-video	Generates short-form, explainer, and demo videos through a key-optional Remotion pipeline.
oma-voice	Generates voiceovers and transcribes audio on-device, no cloud needed.

Orca IDE

OMA for Orca adds a sidebar panel and command-palette actions for project setup, review, debugging, verification, and local results. It uses your existing Orca agent terminal and project OMA installation. Requires Orca 1.4.197+ with experimental plugins enabled.

How It Works

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:

Step	Command	What It Does
0	/deepinit	Maps your existing codebase into AGENTS.md, ARCHITECTURE.md, and docs
1	/brainstorm	Explores ideas with you before you commit to building
2	/architecture	Weighs your design tradeoffs and draws clean module boundaries
2	/design	Builds your design system with tokens, accessibility, and responsive layouts
2	/plan	Breaks your feature down into prioritized tasks
3	/work	Builds your feature step by step across multiple agents
3	/orchestrate	Runs multiple agents in parallel to build your feature faster
3	/ultrawork	Builds your feature through five gated quality phases; every review runs in a fresh, isolated reviewer session (cross-context review)
3	/ralph	Repeats /ultrawork until an independent verifier passes every criterion
4	/review	Reviews your code for security, performance, and accessibility issues
4	/deepsec	Runs a deep security scan and blocks risky pull requests
5	/debug	Finds the root cause, fixes the bug, and writes a regression test
5	/docs	Checks your docs for broken references and patches the ones your code changes touched
6	/scm	Manages your branches, merges, and Conventional Commits
-	/schedule	Schedules an agent job to run on a recurring interval

Auto-detection: You don't even need slash commands — keywords like "architecture", "plan", "review", and "debug" in your message (in 11 languages!) auto-activate the right workflow. Detection accuracy is measured, not assumed: oma verify triggers scores the detector against a labeled 171-prompt corpus (currently 0% missed-fire, under 10% false-fire) and gates CI on it.

Per-Agent Models

Set model_preset in .agents/oma-config.yaml to choose which AI models each agent uses:

language: en
model_preset: mixed   # antigravity | claude | codex | cursor | kiro | mixed | qwen

# Optional per-agent overrides
agents:
  backend: { model: openai/gpt-5.5, effort: high }

• oma doctor --profile — prints the per-role resolved model matrix
• Full guide: web/docs/guide/per-agent-models.md

Verification, Not Narration

Each mechanism below is mechanical: a command exits 0 or it doesn't, a file is on disk or it isn't. No LLM is asked whether the work "looks correct."

Mechanism	What it mechanically checks	Where it lives
Stop-hook gate	Blocks session termination while a persistent workflow is active, and runs the configured gate script before allowing a stop. Only typecheck, test, and lint are executable — an agent that writes anything else into the state file gets it ignored, never run. Capped at 5 reinforcements so a permanently red gate can't trap you.	.agents/hooks/core/persistent-mode.ts