Run all your coding agents at once and talk to them. They ask out loud, you answer by voice, nothing merges without your review. Works with Claude Code, Codex, Cursor and more, on the plans you already have.
This is the 2nd launch from SKI. View more
SKI
Launched this week
Talk to your coding agents and hear them talk back. SKI runs Claude Code, Codex, Cursor, OpenCode, Antigravity and pi side by side on your Mac, and tells you the moment one needs you.
Free Options
Launch Team / Built With
CloudflareStill paying to deploy your apps? Try Cloudflare Workers for free
Promoted
I dictate a lot of what I ask Claude already. When I say stop, does it kill a command that's already running, a git push say, or just the agent's next step?
@julien_zammit Thank you for checking out SKI
It stops the ongoing process step of the agent, like when you press the stop button on claude code.
It would be great if you could take a look into our product and try it. As you dictate a lot, we would absolutely love to hear your feedback or any issues that you face, so that we could improve our product.
@julien_zammit Thanks Julien! Since you dictate a lot already, you might like undo: undo a turn and the agent forgets it ever happened, so a misheard instruction is easy to take back.
@anand_balakrishnan5 undo is the one I'd use most, dictation gets a word wrong often enough that our agents are told to go by what I meant and not what got typed
Good to see SKI at #1 today. Running Claude Code, Codex and Cursor by voice is useful, and review before merge is important. Can one voice session pass context from one agent to another?
@modiyilreji Thank you for checking out SKI.
Yes. In normal voice mode, a session, for instance, running on Opus 5.5 can run the plan or maybe part of a code, and hand over the session to maybe Sonnet or GLM 5.3 Flash or others, as you request. If the models are from the same provider, they can carry over the conversation as well. If not, they carry over the intelligence.
Please try it out and let us know your feedback on the product. Happy to help!
@johnkg003 Thanks, John. The cross-model handoff is useful to know.
@rahul_saji007 In normal mode, each agent will have their own distinct voice. The session name will also be spoken if needed. In one-agent mode, the agent will tell you the name and details of the session which needs your attention.
Please try out SKI and let us know your feedback.
The per-chat git worktree detail is what caught my eye — running Claude Code, Codex, and Cursor side by side only works if they never step on each other. With voice as the input, the review-before-anything-goes-anywhere step feels essential, not optional. Does saying “stop” pause just the chat I’m talking to, or all of them at once?
@jcbuilds Thanks a lot for checking out SKI
The review before send feels like a second check, just in case the user wants something to be corrected. Saying "stop" just stops the chat that you are in, and not all of them. SKI is relatively seamless and hands-free, designed to work with voice or multi-modal inputs whenever possible.
Please try it out, and we believe that you will feel it very comfortable and fast to build.
@jcbuilds Thanks JC! One small addition: voice is the default, but you can type in any chat whenever you'd rather not talk. Stop only affects the chat you're in, so the others keep going.
Congrats on the launch. When an agent asks for a yes or no by voice, is the diff still shown on screen before anything is applied to the worktree? And in one-voice mode, how does it tell you which agent is asking when two are waiting at once?
@akarsh_hegde Thank you for checking out SKI
The agent will explain the changes if required and show it up in a html file in Chrome visually, or you could also see it in the SKI hub as diff, just like the normal coding agents. The voice is intelligent enough to adapt according to your preferences.
In one-voice for all agents mode, when there are two agents, it will mention the branch name and project name to identify. In normal mode, each agent has its own voice and the selected session will be shown in the notch.
Please try out SKI and let us know your feedback too.
@akarsh_hegde Thanks Akarsh. To be clear on the main point: nothing gets applied without you seeing it first. Voice is just how you talk to the agents, and the review step stays the same.
Another quick demo: designing in Figma by talking.
I asked for a delivery app for small towns, with customer, shop and rider apps. Claude Code drew lo-fi wireframes in Figma, then hi-fi, then a v2, then built the apps and wired them together.
Does it work with repos on a remote machine over SSH
@basil_lenin Yes, it works.