NucleicAgents
Agents

Three great agents.
One cockpit.

Claude Code, Codex, and Grok, side by side — started, watched, and approved exactly the same way. Plus any agent that speaks the open Agent Client Protocol.

Claude CodeCodexGrokOne cockpit
Scroll
What it does

Pick the agent
per task.

Choose right from the model picker — a Claude model runs Claude Code, a GPT or Codex model runs Codex, a Grok model runs Grok. Run them at the same time, on the same project, and compare their work in one review surface.

Claude CodeCodexGrokOne cockpit
three backends, one flow
Open by protocol

The roster grows
without you waiting.

Nucleic speaks the Agent Client Protocol — an open, standard way for editors and agents to talk. Any ACP agent joins your fleet behind the same approvals and review. The newest capable agent can slot in without changing how you work.

Why it matters

One thing to learn. Every agent, consistent.

Right tool for the job

Some tasks suit one agent better — pick per task instead of committing to one.

No lock-in

Your workflow, approvals, and review stay the same as agents come and go.

Your own accounts

Each agent authenticates with your credentials — nothing sits between you and your providers.

One surface

Same statuses, same approvals, same merge flow, whichever agent is working.

Keep exploring
Open beta

Bring your agents. All of them.

Nucleic is in open beta. All it asks is macOS 27 on Apple Silicon.

No account required · private by design · runs offline