I’m building Agentic Control Freak (ACF): a local control plane for Codex CLI, Claude Code, Antigravity CLI, and Ollama. With ACF, you can build local projects ranging from Next.js apps to training ML models all via your browser on your local machine.
The agents still do the coding. ACF owns the outer loop:
"task -> plan -> approve -> execute -> verify -> preview -> handoff"
It keeps durable state outside any one agent session: plans, tasks, filesystem diffs, checkpoints, undos, forks, verification runs, previews, memory, skills, and handoff briefs. That means you can switch providers mid-project without starting from zero.
It also does not trust the agent’s final message. The filesystem diff is truth; verification and live preview are owned by the control plane.
The orchestration, workspaces, previews, and state are local: localhost-only, workspace-confined under .workspace/<project>, and not meant for hosting. Provider CLIs may still call their model services. Optional Telegram control lets you approve or steer runs from your phone through a token-gated local worker.
Repo: https://github.com/Antibody/Agentic-Control-Freak
Video intro: https://youtu.be/1fRH-XQrgkY
ML model design and training video: https://youtu.be/KdiiU4RIfFU
P.S. I’d love feedback, especially on whether the app works on Mac or Linux (I tested only on Win11).
I also found that using agents to write code for you leaves you with unintelligible code that you have to reverse engineer.
I found it useful for PoCs, but not for something that goes into production unless I want to spend the same amount of time it would have taken me to write the code myself understanding and detangling the generated code.
Exactly. It takes the fun part and does it too quickly, in a bad way, leaving you to review and fix everything, the boring part.
In the end you've spent the same amount of time either way but only done the soul-crushing part.
No thanks.
💯