Mrrlin
Orchestrates Claude Code, Codex and other AI agents, pausing for human approval.
Mrrlin takes one goal, plans it into tasks, and coordinates existing coding agents — Claude Code, Codex CLI, Gemini — to execute them, stopping at each step that needs a human decision or approval. It runs on the Claude Code and Codex CLI subscriptions you already pay for rather than metered API bills, and routes cheap work to free-tier models like Gemini or Grok so paid agents only handle calls that need them. Users report it cutting a week of cross-agent coordination down to an afternoon.
What holds up
- +Runs on your existing Claude Code and Codex CLI subscriptions — no metered API bills
- +Routes routine work to free-tier models like Gemini and Grok, saving paid-agent calls
- +Stops at every step that needs a human decision instead of running fully autonomous
- +Shows which model did each task and why it was accepted or rejected, as an audit trail
Mind the limits
- −Only useful if you already run Claude Code and Codex CLI — it coordinates them, not stand-ins
- −No pricing or signup flow shown on the page — only a 'map my first workflow' CTA
Featured here? Take the badge
Put it on your site — it links back to this review. Free for every listed product, always.
<a href="https://stillworks.dev/products/p/mrrlin/"><img src="https://stillworks.dev/badge/mrrlin.svg" alt="Picked by StillWorks" width="250" height="54"></a>