oh-my-ag
Earlier name of oh-my-agent; see the current project
5 followers
Earlier name of oh-my-agent; see the current project
5 followers
oh-my-ag is the earlier name of oh-my-agent. This listing covers the project's Antigravity origin. For current setup, use oh-my-agent. Skills-only installs provide guidance; the full harness adds CLI, hooks and workflow verification. Start with one scoped task and inspect its diff and checks. Quick Start: https://firstfluke.com/oh-my-agent/docs/getting-started/quick-start/
Update: oh-my-ag is now oh-my-agent.
Current setup: https://firstfluke.com/oh-my-age...
Skills-only installs provide skills. The full harness provides the CLI, hooks and workflow verification.
AI-native development in 2026 is no longer about writing better prompts. It is about orchestrating agents effectively.
While experimenting with Antigravity and CLI-based agents, I kept running into the same issues:
- Skills ignored mid-conversation
- Rules silently dropped
- Infinite loops
- Agents working hard on the wrong task
It looked like a model problem.
It was actually an orchestration problem.
So instead of endlessly tuning prompts, I built oh-my-ag, a role-based orchestration layer that provides structured collaboration by default.
[What it does]
- Orchestrator controls the overall workflow
- PM decomposes requirements
- Frontend, Backend, and Mobile implementation
- QA validates against requirements
- Debug analyzes failures
- Shared Serena Memory preserves decisions and context
[Why it matters]
- Reduces model volatility risk
- Makes human oversight explicit
- Removes repetitive prompt setup work
- Supports Gemini CLI, Claude CLI, and Codex CLI
This is designed around full-stack development and has been handling 50+ commits per day in real projects.
If you're already using Antigravity, stop fighting prompts. Start orchestrating agents.
Feedback welcome.