Sled lets you run your coding agent from your phone using voice. Coding agents need frequent input, but when you step away from your desk they just sit idle. Sled solves this by giving you a voice interface that connects securely to your local agent over Tailscale. Your code never leaves your machine. You talk, the agent works locally, and you hear the result read back. Works with Claude Code, OpenAI Codex, and Gemini CLI. Fully open source.
Hey Product Hunt 👋
We built Sled because our coding agents kept getting stuck whenever we stepped away from our desks. They need input every 10–60 minutes — and terminals are terrible for that when you’re not sitting in front of them.
Sled gives you a voice interface to your local coding agent. You talk from your phone, the agent runs on your computer, and you hear what it did. No code leaves your machine — everything goes over Tailscale.
It’s fully open source and takes about 5 minutes to set up.
We’d love feedback, questions, or ideas for where this could go next 🛷
Interesting idea! I’ve been thinking for a long time about making something similar, where you could take a walk in a park but complete tasks at the same time. Правда, my idea wasn’t about programming but about controlling phone apps by voice… but technically it turned out to be almost impossible.
This hits a very real technical pain point for local coding agents.
Current agents (Claude Code, Gemini CLI, Codex, etc.) don’t fail because of model quality — they fail because they need frequent, low-latency human steering. Once you step away from the terminal, the feedback loop breaks.
Sled’s approach is clean and opinionated:
Voice as a lightweight control channel
Agent execution stays fully local
Secure networking via Tailscale instead of proxying code or context
That design choice matters. No cloud relay, no prompt mirroring, no hidden data paths.
This feels less like a “voice feature” and more like missing infrastructure for agent orchestration. Especially useful for long-running tasks, iterative refactors, or high-level task decomposition when you already trust your agent.
Very strong foundation — excited to see how review, confirmation, and agent-state inspection evolve next.
Finally, I can code while walking my dog! My dog might not understand what I'm saying, but at least my coding agent does. This product perfectly solves the age-old problem of "I want to keep working but don't want to go back to my desk." Only issue is, if I'm yelling "fix this bug" in the park, people might think I've lost it. But hey, for productivity's sake, totally worth it! HAHAHAHAHA
For longer agentic workflows that require input at irregular intervals, this is definitely the way. I'm interested to see how you guys implemented this.
Is there any latency when commands are sent over Tailscale from mobile to local machine?
Congrats on the launch 👏
Curious when users land on the page, what’s the one action you most want them to take right now?
hey, awesome work! I already heard about at least 3 different projects that let you control your agent using your phone (and even used Omnara before), so I'm curious - what makes your product stand out? the first thing I see is that it is not limited to just Claude code but is there something to it?
I was just thinking about doing something similar, won't need to anymore. Is there an option to connect it through cloudflare?
Congrats on the launch - always appreciate ways to enhance vibe coding productivity, very cool!
What are other future planned integrations down the line? Cursor (fingers crossed)?
@jack_bridger an absolute killer idea… Super excited to mess around with it. Congrats.
why use voice? the agent notifies you these days either cursor or claude code. you can then reply to the agent. I prefer text. also you can queue your messages.
what a great idea , I'm pretty sure it can save so much time! congrats on the launch 👏
The last thing industry needs forcing engineers to work off hours and from their phones. I think even the fact that this solution exists is insane.
Sled is absolutely a cure for most of the vibe builders - human in the loop is necessary! Great launch team!
Hey Jack, that frustration of stepping away and coming back to a stuck agent is so real. Was there a specific time you were out grabbing coffee or taking a break and came back to find your agent had been sitting there waiting for input the whole time?
