Openbase - Manage your team of AI agents by voice, from anywhere
by•
Openbase lets you manage a team of AI coding agents by voice, from anywhere; no screen, no desk.
AI agents can work async, but supervising them still pulls you back to a laptop. OpenBase fixes that. Dispatch tasks, steer agents mid-work, and approve changes just by talking. The agents write code, control your computer, open PRs, commit and push; you stay in control from your phone.
Works across providers and syncs to your machine, so you pick up at your desk right where you left off.
Replies
PopPop AI Vocal Remover
This is a smart solution — finally a way to supervise AI coding agents by voice from your phone without being glued to a laptop.
Macaly
managing agent fleets by voice is kinda wild 👏 do teams run them fully async yet?
Openbase
@petrkovacik currently our app is meant for a singular operator controlling multiple teams of agents, but we are looking to create more of that multiplayer compatibility within orgs!
Dial
the safety word answer above covers accidental triggers, but what about a garbled connection mid-approval, like walking through a spot with bad signal while saying yes to a PR merge? if the transcription comes back partial or mangled, does it fail closed and ask you to repeat, or is there any path where a mis-heard word could get treated as an approval for something you didn't actually confirm
@omri_ben_shoham1 It fails closed. A partial or garbled transcription is not treated as approval, so the action stays paused and Openbase asks you to repeat. We’d rather re-ask than guess on something like a PR merge.
Congrats on the launch. The voice layer feels strongest as a triage/approval surface, not a replacement for review. One thing I’d want to see in the flow is a review-at-desk escape hatch: before any multi-file change, the agent summarizes files touched, tests run, risky operations, and what still needs a screen. Then approving later should be as easy as approving now.
@zoky_zhou
Congrats on the launch! I already manage Codex from my phone, so the voice control is the part that interests me here. How well does Openbase handle longer instructions or corrections when you change your mind halfway through speaking?
Meridian
The voice-first workflow is compelling, especially for starting tasks or checking progress away from a desk. Where would you personally draw the line between actions that can be approved by voice and changes that should always require reviewing the diff on screen first?
Meridian
The approval flow is strong, especially pausing sensitive actions and failing closed when voice input is unclear.
How does Openbase handle two agents trying to change the same files at once? Does it detect conflicts before either agent commits or pushes?