</>MCP Agents Market
Plugin

oh-my-openagent

by code-yeongyu68kTypeScriptUpdated 2026-08-16

omo/lazycodex: The coding agent for tokenmaxxers;the one and only agent harness for complex codebases. For your Codex, for your OpenCode

OpenCodeCodex

oh-my-openagent is a multi-agent orchestration plugin for AI coding assistants that coordinates specialized agents across multiple LLM providers (Anthropic, OpenAI, Kimi, GLM, and others) to handle complex codebases. It ships in three editions: Ultimate (for OpenCode with 11 agents and full orchestration), Light (for Codex CLI with portable components), and Senpi (standalone beta). The tool automates task delegation, provides hash-anchored edits to prevent stale-line errors, and includes LSP integration, AST-grep pattern search, tmux terminal control, and built-in MCP servers for web/docs/code search.

Key Features

Multi-agent orchestration with 11 specialized discipline agents (Sisyphus, Hephaestus, Prometheus, Oracle, etc.) that auto-route tasks to the best model
Three editions: Ultimate plugin for OpenCode, Light plugin for Codex CLI, and standalone Senpi beta (omo-ai@beta)
Hash-anchored edit tool (Hashline) validates every change with content hashes to eliminate stale-line errors
Team Mode with up to 8 parallel agents, real-time tmux visualization, and dedicated team_* coordination tools
Built-in MCP servers for Exa web search, Context7 official docs, Grep.app GitHub search, plus LSP and AST-grep integration
ultrawork/ulw command activates all agents and runs continuously with goal enforcement and todo auditing
IntentGate analyzes true user intent before classification; comment-checker prevents AI-generated comment slop
Full Claude Code compatibility including hooks, commands, skills, and plugins

Use Cases

  • 01Orchestrating multiple LLM providers (Claude Opus, GPT-5.6 Sol, Kimi K3, GLM-5) without manual model switching
  • 02Running parallel specialist agents for large refactors, migrations, or codebase-wide changes
  • 03Autonomous deep work with Hephaestus agent exploring patterns and executing end-to-end without step-by-step guidance
  • 04Team-based security research with 3 vulnerability hunters and 2 PoC engineers working simultaneously
  • 05Strategic planning with Prometheus interview-mode before code execution
  • 06Converting large legacy codebases with LSP diagnostics, AST-grep rewrites, and persistent goal tracking

Related Plugins

View more

oh-my-openagent — FAQ

What is oh-my-openagent?+

oh-my-openagent is a multi-agent orchestration plugin that coordinates specialized AI coding agents across multiple LLM providers (Anthropic, OpenAI, Kimi, GLM). It automates task delegation, provides advanced editing tools, and ships in three editions: Ultimate for OpenCode, Light for Codex CLI, and standalone Senpi beta.

How do I install oh-my-openagent?+

For Ultimate edition on OpenCode, run `bunx oh-my-openagent install`. For Light edition on Codex CLI, run `npx lazycodex-ai install`. For standalone Senpi beta, run `npm i -g omo-ai@beta`. The installer recommends letting an LLM agent handle setup by pasting the installation guide URL.

Which AI clients does oh-my-openagent work with?+

oh-my-openagent works with OpenCode (Ultimate edition), Codex CLI (Light edition), and as a standalone tool (Senpi beta). It maintains full compatibility with Claude Code hooks, commands, skills, MCPs, and plugins.

Do I need API keys or subscriptions?+

Yes, oh-my-openagent requires API keys or subscriptions for the LLM providers you want to use. The installer prompts for provider authentication (Anthropic, OpenAI/GitHub Copilot, Gemini, Kimi, GLM/Z.ai). The project documentation recommends ChatGPT ($20), Kimi Code ($19), and GLM Coding Plan ($10) subscriptions.

Is oh-my-openagent free?+

The oh-my-openagent plugin itself is open source under the SUL-1.0 license, but it requires paid subscriptions or API access to LLM providers (Anthropic, OpenAI, Kimi, GLM, etc.) to function. Anonymous telemetry is enabled by default but can be disabled via environment variables.

What is ultrawork mode?+

ultrawork (or ulw) is a command that activates all agents and runs continuously until the task is complete. It includes goal enforcement, todo auditing, and automatically orchestrates specialist agents in parallel without requiring manual intervention or configuration.

How do I install oh-my-openagent?+

Open the source repository on GitHub and follow its README. oh-my-openagent is a plugin — MCP Agents Market links you directly to the official repo.

Is oh-my-openagent free?+

oh-my-openagent is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.

Related searches