Oh My OpenAgent

Active
GitHub TypeScript NOASSERTION

Description

An open-source agent harness platform providing the best agent toolkit, supporting multiple AI coding agents.

Key Features

  • Multi-agent orchestration platform — Supports multiple AI agents like OpenCode and Codex CLI with unified configuration and workflow management
  • Team Mode multi-agent collaboration — Multiple agents working simultaneously on different tasks with Kimi K2.6, GPT-5.5, and other models
  • 54+ lifecycle hooks — Rich lifecycle hooks covering code editing, testing, deployment, and the full development workflow
  • Built-in MCP servers — Integrated LSP and other MCP servers providing language server protocol support for agents
  • ultrawork automation loop — One-click automated development loop where agents work continuously until tasks are complete
  • LazyCodex integration — Lightweight version for Codex CLI supporting rules, comment checking, and code continuation

Use Cases

💡 Use ultrawork to launch automated development workflows with agents coding continuously until tasks are complete
💡 Leverage Team Mode for multiple agents to work in parallel on different modules, accelerating large project development
💡 Configure project rules (.clinerules) to ensure agents follow team coding standards and architecture conventions
💡 Integrate with Slack to interact with agents remotely for code reviews or feature development tasks
💡 Use LazyCodex in Codex CLI for enhanced agent capabilities without a full installation

Strengths & Limitations

Strengths

  • Actively maintained, recent updates
  • High community interest (68.6k stars)

⚠️ Limitations

  • No clear open-source license

Quick Start

# Install oh-my-openagent (Ultimate Edition)
npx oh-my-opencode install

# Or install Light Edition (Codex CLI version)
npx lazycodex-ai install

# Start ultrawork automation loop
ultrawork

# Start Team Mode
cline --team-name my-team "implement user authentication module"

Related Projects

Atomic Agents

6.2k · Python
Active A+

Atomic Agents is a modular AI agent building framework with an atomic design philosophy, providing composable components including tools, pipelines, and memory management for constructing agent systems.

frameworkpythonagent +2
  • · Atomic design philosophy with single-purpose, reusable, composable components
  • · Built on Instructor and Pydantic for type-safe, predictable agent behavior
  • · Multi-provider support including OpenAI, Anthropic, Groq, Gemini, and more