English | 한국어 | 中文 | 日本語 | Español | Tiếng Việt | Português

For Codex users: Check out oh-my-codex — the same orchestration experience for OpenAI Codex CLI.

Multi-agent orchestration for Gemini Code. Zero learning curve.

Don't learn Gemini Code. Just use OMC.

Get Started • Documentation • CLI Reference • Workflows • Migration Guide • Discord

Step 1: Install

/plugin marketplace add https://github.com/Yeachan-Heo/oh-my-gemini-cli
/plugin install oh-my-gemini-cli

Step 2: Setup

/setup
/omg-setup

Step 3: Build something

autopilot: build a REST API for managing tasks

That's it. Everything else is automatic.

If you're uncertain about requirements, have a vague idea, or want to micromanage the design:

/deep-interview "I want to build a task management app"

The deep interview uses Socratic questioning to clarify your thinking before any code is written. It exposes hidden assumptions and measures clarity across weighted dimensions, ensuring you know exactly what to build before execution begins.

Starting in v4.1.7, Team is the canonical orchestration surface in OMC. The legacy swarm keyword/skill has been removed; use team directly.

/team 3:executor "fix all TypeScript errors"

Team runs as a staged pipeline:

team-plan → team-prd → team-exec → team-verify → team-fix (loop)

Enable Gemini Code native teams in ~/.gemini/settings.json:

{
  "env": {
    "CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1"
  }
}

If teams are disabled, OMC will warn you and fall back to non-team execution where possible.

v4.4.0 removes the Codex/Gemini MCP servers (x, g providers). Use the CLI-first Team runtime (omg team ...) to spawn real tmux worker panes:

omg team 2:codex "review auth module for security issues"
omg team 2:gemini "redesign UI components for accessibility"
omg team 1:gemini "implement the payment flow"
omg team status auth-review
omg team shutdown auth-review

/omg-teams remains as a legacy compatibility skill and now routes to omg team ....

For mixed Codex + Gemini work in one command, use the /ccg skill (routes via /ask codex + /ask gemini, then Gemini synthesizes):

/ccg Review this PR — architecture (Codex) and UI components (Gemini)

Workers spawn on-demand and die when their task completes — no idle resource usage. Requires codex / gemini CLIs installed and an active tmux session.

Note: Package naming — The project is branded as oh-my-gemini-cli (repo, plugin, commands), but the npm package is published as oh-my-gemini-sisyphus. If you install or upgrade the CLI tools via npm/bun, use npm i -g oh-my-gemini-sisyphus@latest.

If you installed OMC via npm, upgrade with the published package name:

npm i -g oh-my-gemini-sisyphus@latest

Package naming note: the repo, plugin, and commands are branded oh-my-gemini-cli, but the published npm package name remains oh-my-gemini-sisyphus.

If you installed OMC via the Gemini Code marketplace/plugin flow, update with:

# 1. Update the marketplace clone
/plugin marketplace update omg

# 2. Re-run setup to refresh configuration
/omg-setup

Note: If marketplace auto-update is not enabled, you must manually run /plugin marketplace update omg to sync the latest version before running setup.

If you experience issues after updating, clear the old plugin cache:

/omg-doctor

• Zero configuration required - Works out of the box with intelligent defaults
• Team-first orchestration - Team is the canonical multi-agent surface
• Natural language interface - No commands to memorize, just describe what you want
• Automatic parallelization - Complex tasks distributed across specialized agents
• Persistent execution - Won't give up until the job is verified complete
• Cost optimization - Smart model routing saves 30-50% on tokens
• Learn from experience - Automatically extracts and reuses problem-solving patterns
• Real-time visibility - HUD statusline shows what's happening under the hood

Multiple strategies for different use cases — from Team-backed orchestration to token-efficient refactoring. Learn more →

• 32 specialized agents for architecture, research, design, testing, data science
• Smart model routing - Haiku for simple tasks, Opus for complex reasoning
• Automatic delegation - Right agent for the job, every time

• Magic keywords - ralph, ulw, ralplan; Team stays explicit via /team
• HUD statusline - Real-time orchestration metrics in your status bar
• Skill learning - Extract reusable patterns from your sessions
• Analytics & cost tracking - Understand token usage across all sessions

Learn once, reuse forever. OMC extracts hard-won debugging knowledge into portable skill files that auto-inject when relevant.

# .omg/skills/fix-proxy-crash.md
---
name: Fix Proxy Crash
description: aiohttp proxy crashes on ClientDisconnectedError
triggers: ["proxy", "aiohttp", "disconnected"]
source: extracted
---
Wrap handler at server.py:42 in try/except ClientDisconnectedError...

Manage skills: /skill list | add | remove | edit | search Auto-learn: /learner extracts reusable patterns with strict quality gates Auto-inject: Matching skills load into context automatically — no manual recall needed

Full feature list →

Optional shortcuts for power users. Natural language works fine without them. Team mode is explicit: use /team ... or omg team ... rather than a keyword trigger.

Notes:

• ralph includes ultrawork: when you activate ralph mode, it automatically includes ultrawork's parallel execution.
• swarm compatibility alias has been removed; migrate existing prompts to /team syntax.
• plan this / plan the keyword triggers were removed; use ralplan or explicit /oh-my-gemini-cli:omg-plan.

Run local provider CLIs and save a markdown artifact under .omg/artifacts/ask/:

omg ask gemini "review this migration plan"
omg ask codex --prompt "identify architecture risks"
omg ask gemini --prompt "propose UI polish ideas"
omg ask gemini --agent-prompt executor --prompt "draft implementation steps"

Canonical env vars:

• OMC_ASK_ADVISOR_SCRIPT
• OMC_ASK_ORIGINAL_TASK

Phase-1 aliases OMX_ASK_ADVISOR_SCRIPT and OMX_ASK_ORIGINAL_TASK are accepted with deprecation warnings.

Auto-resume Gemini Code sessions when rate limits reset.

omg wait          # Check status, get guidance
omg wait --start  # Enable auto-resume daemon
omg wait --stop   # Disable daemon

Requires: tmux (for session detection)

Use the HUD for live observability and the current session/replay artifacts for post-session inspection:

• HUD preset: /oh-my-gemini-cli:hud setup then use a supported preset such as "omgHud": { "preset": "focused" }
• Session summaries: .omg/sessions/*.json
• Replay logs: .omg/state/agent-replay-*.jsonl
• Live HUD rendering: omg hud

You can configure who gets tagged when stop callbacks send session summaries.

# Set/replace tag list
omg config-stop-callback telegram --enable --token <bot_token> --chat <chat_id> --tag-list "@alice,bob"
omg config-stop-callback discord --enable --webhook <url> --tag-list "@here,123456789012345678,role:987654321098765432"
omg config-stop-callback slack --enable --webhook <url> --tag-list "<!here>,<@U1234567890>"

# Incremental updates
omg config-stop-callback telegram --add-tag charlie
omg config-stop-callback discord --remove-tag @here
omg config-stop-callback discord --clear-tags

Tag behavior:

• Telegram: alice becomes @alice
• Discord: supports @here, @everyone, numeric user IDs, and role:<id>
• Slack: supports <@MEMBER_ID>, <!channel>, <!here>, <!everyone>, <!subteam^GROUP_ID>
• file callbacks ignore tag options

Forward Gemini Code session events to an OpenClaw gateway to enable automated responses and workflows via your OpenClaw agent.

Quick setup (recommended):

/oh-my-gemini-cli:configure-notifications
# → When prompted, type "openclaw" → choose "OpenClaw Gateway"

Manual setup: create ~/.gemini/omg_config.openclaw.json:

{
  "enabled": true,
  "gateways": {
    "my-gateway": {
      "url": "https://your-gateway.example.com/wake",
      "headers": { "Authorization": "Bearer YOUR_TOKEN" },
      "method": "POST",
      "timeout": 10000
    }
  },
  "hooks": {
    "session-start": { "gateway": "my-gateway", "instruction": "Session started for {{projectName}}", "enabled": true },
    "stop":          { "gateway": "my-gateway", "instruction": "Session stopping for {{projectName}}", "enabled": true }
  }
}

Environment variables:

Supported hook events (6 active in bridge.ts):

Reply channel environment variables:

See scripts/openclaw-gateway-demo.mjs for a reference gateway that relays OpenClaw payloads to Discord via ClawdBot.

• Full Reference - Complete feature documentation
• CLI Reference - All omg commands, flags, and tools
• Notifications Guide - Discord, Telegram, Slack, and webhook setup
• Recommended Workflows - Battle-tested skill chains for common tasks
• Release Notes - What's new in each version
• Website - Interactive guides and examples
• Migration Guide - Upgrade from v2.x
• Architecture - How it works under the hood
• Performance Monitoring - Agent tracking, debugging, and optimization

• Gemini Code CLI
• Gemini Max/Pro subscription OR Anthropic API key

OMC features like omg team and rate-limit detection require tmux:

Windows users: psmux provides a native tmux binary for Windows with 76 tmux-compatible commands. No WSL required.

OMC can optionally orchestrate external AI providers for cross-validation and design consistency. These are not required — OMC works fully without them.

Cost: 3 Pro plans (Gemini + Gemini + ChatGPT) cover everything for ~$60/month.

MIT

Top personal non-fork, non-archived repos from all-time OMC contributors (100+ GitHub stars).

• @Yeachan-Heo — oh-my-gemini-cli (⭐ 11k)
• @junhoyeo — tokscale (⭐ 1.3k)
• @psmux — psmux (⭐ 695)
• @BowTiedSwan — buildflow (⭐ 284)
• @alohays — awesome-visual-representation-learning-with-transformers (⭐ 268)
• @jcwleo — random-network-distillation-pytorch (⭐ 260)
• @emgeee — mean-tutorial (⭐ 200)
• @anduinnn — HiFiNi-Auto-CheckIn (⭐ 172)
• @Znuff — consolas-powerline (⭐ 145)
• @shaun0927 — openchrome (⭐ 144)

If Oh-My-GeminiCLI helps your workflow, consider sponsoring:

• Keep development active
• Priority support for sponsors
• Influence roadmap & features
• Help maintain free & open source

• ⭐ Star the repo
• 🐛 Report bugs
• 💡 Suggest features
• 📝 Contribute code