Launching today
KarmaBox
Run your own Claude Code in your pocket.
222 followers
Run your own Claude Code in your pocket.
222 followers
Run hundreds of AI agents from your phone. Turn your devices into a private compute pool, route every task to the best AI, and use Claude, Codex, Gemini and more — no infra, no lock-in.
KarmaBox
This looks different, great work Team
Does it work if some devices are offline or low battery, or does the whole pool need to be active for tasks to route properly?
KarmaBox
@boyuan_deng1
KarmaBox continuously monitors device status (online/offline, battery, load). When routing tasks, it only uses available devices:
The system is designed to be resilient — devices can come and go without breaking anything.
KarmaBox
@boyuan_deng1 Great question — and thanks!
It doesn’t require all devices to be online. We separate compute and state:
Compute is stateless (VPS / sandbox / laptop), so tasks can run on whatever is available.
State is persisted separately, so progress isn’t tied to any single machine.
If a device goes offline or runs low on battery, the system just routes work to others. No need for the whole pool to stay active.
Well done, Viveka! This feels huge. How do you handle API costs does it get expensive if agents run 24/7 on my device?
KarmaBox
@barnaby_lloyd Appreciate it 🙌 great question.
KarmaBox
@barnaby_lloyd Running 24/7 doesn’t mean it’s constantly burning tokens — agents are mostly event-driven and only call APIs when there’s actual work to do.
On top of that, we route tasks across different models depending on the job, so you’re not always hitting the most expensive one.
Since compute runs on your own devices, you also avoid a lot of the infra cost you’d normally have.
So it’s pretty controllable in practice — and we’re adding more knobs for users to tune cost vs quality as well.
So cool congrats on the launch! Most annoying part for me is logging into 5 different AI tools every morning. Does KarmaBox handle auth across them automatically?
KarmaBox
@antonio_manuel1 Totally feel that — it adds up fast.
KarmaBox
@antonio_manuel1 KarmaBox doesn’t auto-log into everything, but once you connect your models/services, everything runs through one system.
So you’re not jumping between tools or re-authing every time.
Huge congrats! Typiest is so real lol. Quick question: can I run this on an old phone or does it need beefy hardware?
KarmaBox
@xavier_hernandez2 Haha appreciate it 🙌 Typiest is very real 😄
You don’t need a beefy phone. The phone is mainly the control center — sending tasks, monitoring, and continuing workflows.
The actual heavy lifting runs across your other devices (laptop, workstation, servers, etc.), so even an older phone works fine.
wow interesting, Ill give it a try......
How are you different from Claude's Remote Control?
KarmaBox
@achuth_noob Great question! Claude Remote Control lets you run Claude Code on a remote machine — it's essentially a terminal in the cloud. Karma goes further in a few key ways:
1. Mobile-native, not mobile-adapted
Karma is built from the ground up for your phone. Full conversation history, streaming responses, tool call visualization, voice input — all designed as a mobile-first experience, not a ported terminal.
2. Your machine, your data
Karma runs on your KarmaBox (Mac/Linux). The AI executes on hardware you own. E2E encrypted. Nothing goes through Anthropic's servers except the LLM call itself.
3. Persistent AI teammates, not sessions
Avatars with skills, memory, and personalities that persist across conversations. Think less "remote terminal" and more "AI coworker you can reach from your phone at 2am."
4. Orchestration layer
Multi-agent coordination, skill marketplace, project-level context — built for teams running parallel workstreams, not just a single dev querying Claude.
In short: Claude Remote Control is a power tool. Karma is the operating system around it.
KarmaBox
@achuth_noob Great question — and excited for you to try it out 🙌
Claude’s Remote Control is mainly about accessing and running Claude across devices.
KarmaBox is a bit different — it’s not tied to a single model or a single machine.
It coordinates multiple models and agents, runs them across all your devices as one system, and keeps tasks moving even if you step away or switch devices.
So instead of controlling one AI remotely, you’re essentially running a whole system of them together.
HeyForm
This is brilliant!
The biggest difference for me is the parallel execution. Things that used to take multiple steps now just happen at once.
KarmaBox
@itsluo Love hearing that — that shift is exactly what we were aiming for.
Once things start running in parallel, it really changes how you approach work altogether.
KarmaBox
@itsluo Thanks so much for the support!
You've hit the nail on the head — parallel execution is exactly what we set out to solve. Instead of waiting for one AI task to finish before starting the next, KarmaBox lets multiple agents work simultaneously on your device.