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. 🙏
About Replicas on Product Hunt
“Run Claude Code and Codex in the cloud”
Replicas launched on Product Hunt on June 3rd, 2026 and earned 154 upvotes and 21 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.
On the analytics side, Replicas competes within Software Engineering, Developer Tools and Artificial Intelligence — topics that collectively have 1M followers on Product Hunt. The dashboard above tracks how Replicas performed against the three products that launched closest to it on the same day.
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.
For a complete overview of Replicas including community comment highlights and product details, visit the product overview.
Garry Tan,
Connor Loi