platoseed
Run any coding agent harness in the cloud
Replicas is a background coding agent that allows you to delegate tasks to Claude Code or Codex from Slack, Linear, GitHub, and more. Each task works inside of a sandboxed virtual machine, allowing teams to heavily parallelize work and burn through tickets. Replicas agents output higher quality PRs via feedback loops - each task automatically is notified and fixes CI failures and reads all code reviews. With Environments, engineering teams can configure agents to run their entire codebase locally, verify its work, and provide preview URLs.
Replicas provides background coding agents that run in sandboxed development environments for engineering teams. It enables delegation from tools like Slack, Linear, and GitHub to spawn coding agents (Claude Code or Codex) and manage tasks from a centralized dashboard.
Run background coding agents in a sandboxed dev environment. Spawn coding agents (e.g., Claude Code or Codex) with preloaded code and tooling. Trigger and hand off tasks from Slack, Linear, and GitHub integrations, and manage agent work via a dashboard.
Who itβs for: engineering teams, software organizations, development teams seeking automation for code tasks
Backed by Y Combinator; Product Hunt launch with integrations and sandboxed agents
CTO @replicas, Prev: Ramp, General Context, Shopify, IBM and Autotrader CS Uwaterloo
Building the best way to use background coding agents ;) prev helicone, td bank, and cohere :)
Background coding agents for engineering teams
Replicas is a background coding agent that runs locally on a developer's codebase in a sandbox VM, installs dependencies, spins up infrastructure, verifies work, and opens PRs for review.
β² 86

Sandboxed coding agents for everyone on your team.

Real-world sandboxes to test agents and agent-facing software