Run background coding agents from anywhere. Spawn Claude Code or Codex in a VM with code and tooling ready to go. Hand off tasks from Slack, Linear, or GitHub Replicas runs Claude Code, Codex, or any coding agent in the cloud. Agents run in isolated VMs with real dev environments, and you can bring your own subscriptions and API keys. Trigger tasks from Slack, Linear, or GitHub and come back to a PR ready to review.
Hey Product Hunt! 👋
I'm Connor, CEO of Replicas, here with my co-founder Saai. We're super excited to finally share Replicas with this community.
Why we built this
Like many of you, we think the future of software engineering is delegating to fleets of cloud agents. Engineers are already using their preferred harnesses: Claude Code, Codex, Opencode, Pi, and others everyday. But back then, no one had made a good way to use them on cloud.
Every existing solution either locks you into one specific harness, or forces you to run agents locally on your machine. That means your agent stops the moment you close your laptop. And if you want multiple agents running at once, you're left wrangling git worktrees, hoping your computer doesn't crash, and buying a clamp to keep your computer open.
What Replicas does
Replicas runs your agents in isolated cloud VMs. Each one gets its own full dev environment, installs your dependencies, spins up your database, and runs your actual codebase locally inside the sandbox. It works with Claude Code, Codex, OpenCode, and more. You bring your own API keys or subscriptions, so you only pay for the infrastructure.
Trigger it from wherever you already live: mention @replicas in a GitHub PR, ping it in Slack, assign a Linear issue, or hit the API. You come back to a PR ready to review.
What we've seen
We dogfood this hard: 95% of our own lifetime PRs were shipped with Replicas, and we haven't opened a single one without it in the last 3 months. Our customers average 30% of PRs through it too; teams like Mintlify, Knowunity, and Composio.
The use cases have gone way beyond what we initially imagined: personalized code review, automated code quality checks in CI, security reviews and pentests, auto-triaging issues, and teams running around-the-clock on-call support engineers.
This is just the beginning of what's possible when you can run agents in parallel, in the background, around the clock.
We'd love to hear how you're thinking about AI agents in your stack! Drop a comment or just come say hi, we're here all day. 🙏
Been using this CONSTANTLY since it dropped. Mintlify gets a huge amount of shipped volume w/ Replicas.
Thanks Connor and Saai <3
Oh, so excited to see you guys launching!
I’ve been using replicas for all my PR reviews. They have a great set of automations and my agent auto resolves.
Not to meant really frictionless integrations with Linear and Slack. I do most a lot of coding tasks from Slack now.
Been using Replicas for months and love it. This has let me kick off multiple changes and bug fixes in parallel without worrying about managing or coordinating test environments.
I am incredibly bullish on any product which is both harness and model agnostic. Been awesome to use Replicas and am excited to see how it keeps getting better.
Do you support switching models per task, like Claude for refactors and Codex for quick fixes?
Spawn Claude Code in a VM with tooling ready to go, this is genuinely what I keep wishing existed when I'm
delegating background tasks. I build entirely through Claude Code today and the friction is exactly what
Replicas is solving, I guess.
How do you handle long-running agent sessions that need to wait for human input (a question that needs answering
mid-task)? Does the VM pause and resume, or does the agent post the question and continue with what it can?
Congrats on the launch.
We’ve been using it and loving it! We kick off the cloud agents via Linear and Slack and it’s been seamless. The warming is key, we can run the app to test and full integration tests before it commits.
Congratulations on the launch!
We use replicas in our day-to-day work to develop multiple features in parallel. It also enables us to do multiplayer, where the product and engineering teams hand off the session back and forth as the development progresses.
We absolutely love the fact that it doesn't lock us into a bad in-house harness, since they just allow us to use the ones from big AI labs. This is a huge benefit, because it means the features that the labs come up with are available right away — we don't have to wait months for the in-house harness to catch up. Another super nice thing is that we're able to preview the work live directly in Replicas via remote desktop or use SSH.
Cloud agents are the next big thing in the AI coding world, and Replicas is the best one out there right now. Excited to see where it ends up!
Isolated VMs per agent run is the right model for correctness. It eliminates state bleed between runs and makes failures clean to recover from. We've hit friction with stateful runners where a mid-task failure left dirty workspaces that blocked the next run entirely. How do you handle dependency caching across VM instances when agents need to install packages mid-task?
The idea of agents continuing to work after I close my laptop is surprisingly compelling. Feels like a natural next step beyond local AI coding tools. Congrats on the launch!
The cloud VM approach makes sense especially when multiple agents need to run in the background without depending on someone's laptop. How does Replicas handle conflicts when two agents are working on related parts of the same codebase?
About Replicas on Product Hunt
“Run Claude Code and Codex in the cloud”
Replicas launched on Product Hunt on June 3rd, 2026 and earned 164 upvotes and 23 comments, placing #5 on the daily leaderboard. Run background coding agents from anywhere. Spawn Claude Code or Codex in a VM with code and tooling ready to go. Hand off tasks from Slack, Linear, or GitHub Replicas runs Claude Code, Codex, or any coding agent in the cloud. Agents run in isolated VMs with real dev environments, and you can bring your own subscriptions and API keys. Trigger tasks from Slack, Linear, or GitHub and come back to a PR ready to review.
Replicas was featured in Software Engineering (42.5k followers), Developer Tools (513.4k followers) and Artificial Intelligence (470k followers) on Product Hunt. Together, these topics include over 174.6k products, making this a competitive space to launch in.
Who hunted Replicas?
Replicas was hunted by Garry Tan and Connor Loi. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how Replicas stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Garry Tan,
Connor Loi