LaunchedEditorial Listing

Replicas

Replicas · Replicas: Cloud Coding Agent Platform for Claude Code, Codex, Cursor, and More

Open Replicas

Replicas is a cloud platform that runs coding agents such as Claude Code, Codex, Cursor, Muse Code, OpenCode, and Pi in isolated Linux VMs connected to your repositories. Engineers assign work from Slack, Linear, GitHub, GitLab, the web or mobile app, or the API, and get back pull requests that the agent keeps updating when CI fails or reviewers comment. It suits engineering teams that want background agents without building their own agent infrastructure.

PricingPaid
Setupmedium
Runs onWeb · Desktop · API · Self-hosted
APIYes
DocsYes
CategoryCoding
Cloud AgentsBackground AgentsClaude CodeCodexModel-AgnosticBYOKSlackGitHubGitLabCI/CDAutomationsComputer UseMCPMobile App

Best for

Engineering teams already using Claude Code, Codex, or Cursor who want those agents running in configured cloud VMs, triggered from Slack, Linear, GitHub, GitLab, or automations, with PRs that follow up on CI failures and reviews

Not ideal for

Solo developers happy running agents locally, teams without existing agent subscriptions or API keys, organizations that need a free tier, and teams that need self-hosting without an Enterprise contract

Who it's for

Engineering teams and platform leads at startups and larger companies who want to delegate backlog, review, and maintenance work to cloud coding agents

Capabilities

  • Runs Claude Code, Codex, Cursor, Muse Code, OpenCode, or Pi per task, and chat forking moves a conversation to another harness without losing context
  • Each task gets an isolated Linux VM with the repository, dependencies, services, on-demand Docker, and a full desktop and browser for computer use, screenshots, and recordings
  • Start work from Slack, Linear, GitHub and GitLab mentions, the web dashboard, the desktop app for macOS, Windows, and Linux, the iPhone and iPad app, the CLI, MCP clients, or the REST API
  • Motherships: a long-lived workspace for one area of the codebase splits a request across several ship workspaces, keeps a board of what needs you, and reports when each pull request is ready to merge
  • CI failure response: when a check fails on a linked pull request, the agent reads the logs, pushes a fix, and comments, in a separate fixes chat
  • Automations triggered by schedules, GitHub, GitLab, Linear, Slack, or Sentry events, or custom webhooks, with debounce, workspace size, and lifecycle settings
  • Review page for GitHub and GitLab pull requests: comment on lines, ask the agent for a change, and merge under your repository's rules
  • Environments with variables, files, skills, MCP servers, and plugins, plus warm hooks and warm pools that keep pre-built workspaces ready
  • Bring-your-own credentials: Claude or OpenAI OAuth, Anthropic or OpenAI API keys, AWS Bedrock, Microsoft Foundry, a Cursor API key, OpenRouter, OpenCode Go, or Ollama, at organization or personal scope, with up to 10 Claude or ChatGPT subscriptions that a chat falls back through when one hits its usage limit
  • Plan mode, Goal mode for Claude Code (keeps working until a stated condition holds), and Fast mode
  • Analytics that break down compute minutes by workspace source and seat, rank agent runtime by harness, model, and credential, and count skill and MCP calls
  • Admin controls: security policies that can block agent merges, an audit log, configurable chat history retention, a static egress IP, and short-lived workspace identity tokens for cloud and API access
  • Cloud iOS and Android devices for testing mobile apps, and GPU sandboxes on Modal for CUDA, training, and rendering jobs, both billed at cost against included usage

Limitations

  • Model usage is not included: you need your own coding agent subscriptions or API keys, and at least one coding agent must be configured before creating workspaces
  • No free plan: new organizations get $100 of trial usage with no card and no time limit, and when it runs out new workspaces are blocked and running ones are suspended until you subscribe
  • Each plan includes usage only up to its own price; beyond that, minutes cost 1.5 times the included rate ($0.006, $0.012, or $0.024 per minute for small, large, or ultra) and are charged whenever $50 is unpaid, so heavy automation can lift the bill well past the plan price unless admins set a usage limit
  • Organization-level coding agent credentials are injected into workspaces, where members can retrieve them through the agent or terminal
  • Workspaces left asleep for seven days are archived and then deleted soon after (archived workspaces are deleted after three days, or sooner once they have been inactive for seven), so idle work does not persist for long
  • Self-hosted and dedicated single-tenant deployment are Enterprise-only, and Replicas lists SOC 2 Type I with Type II in progress
  • There is no Android app; the mobile app needs iOS 26 or later on iPhone or iPad

Use cases

  • Assigning a Linear issue to Replicas and receiving a pull request built and tested in a cloud VM
  • Tagging Replicas on a failing pull request or letting CI failure response push the fix automatically
  • Running a nightly automation that updates dependencies or audits code across repositories
  • Firing an agent from a Sentry alert to investigate a new production error
  • Starting and steering an agent from Slack or the iOS app while away from a laptop
  • Handing a multi-part feature to a Mothership that spreads it across several workspaces and reports when each pull request is ready to merge
  • Comparing Claude Code, Codex, and Cursor on the same task in the same environment

Our take

Replicas makes most sense for teams that have already chosen their coding agents and now want them running in the background, with proper environments, triggers from the tools engineers live in, and pull requests that follow up on CI on their own. Because you bring the harness and the credentials, you can switch between Claude Code, Codex, and Cursor as models change, but you pay twice: once to your model providers and once for VM minutes. Model the automation volume before rolling it out widely, since minutes beyond the plan's included usage cost 1.5 times the included rate (admins can set alerts and a hard usage limit), and check how shared organization credentials are exposed inside workspaces.

Who should use it

Engineering teams already paying for Claude, OpenAI, or Cursor who want background agents in configured cloud VMs, platform teams standardizing environments and credentials for agents, and teams that want agent work triggered from Linear, Slack, GitHub, GitLab, or Sentry.

Who should skip it

Individual developers who are happy running agents locally, teams without existing agent subscriptions or API keys, and organizations that need a free plan, and teams that need self-hosting without an Enterprise contract.

Strengths

  • Runs the coding agents your team already uses instead of a proprietary one
  • Each task gets its own configured Linux VM with computer use
  • Starts work from Slack, Linear, GitHub, GitLab, mobile, or the API
  • Pull requests follow up on CI failures and review bots automatically
  • Detailed usage analytics and admin controls

Weaknesses

  • Model costs come on top, through your own subscriptions or keys
  • No free plan, only $100 of trial usage
  • Usage past the plan's included amount costs 1.5 times as much per minute
  • Self-hosting requires an Enterprise contract

Replicas pricing

Developer

$50

Billed monthly

  • $50 of included workspace usage each month
  • Usage beyond that at the overage rate (1.5x)
  • Small, Large, and Ultra workspaces
  • Unlimited repositories, environments, and automations
  • Warm pools and warm hooks, API access, mobile app

Team

From $200

Billed monthly

  • Included usage equal to the monthly price, in $100 steps
  • Usage beyond that at the overage rate (1.5x)
  • Seats do not affect the bill
  • Higher API rate limits and a static egress IP
  • Shared Slack support channel

Enterprise

Custom

  • Unlimited manual and automated workspace minutes
  • Custom warm pools, API rates, and rate limits
  • SOC 2, DPA, HIPAA BAA, and SCIM provisioning
  • Cloud, dedicated single-tenant, or self-hosted deployment

Free tier limits: No free plan. New organizations get $100 of trial usage with no card and no time limit; when it runs out, new workspaces are blocked and running ones are suspended (not deleted) until you subscribe.

Note: Workspaces are billed per minute only while awake: $0.004 (small, 2 vCPU/8 GB), $0.008 (large, 4 vCPU/16 GB), or $0.016 (ultra, 8 vCPU/32 GB) within included usage, and 1.5 times that beyond it, with a one-minute minimum per session. The default Auto size starts small and resizes with load, billed at the size it ran at. Every workspace counts the same, whether started from the app, an integration, the API, or an automation. Overage is charged once $50 is unpaid, and admins can set usage alerts and a hard usage limit. Mobile testing devices and GPU sandboxes are billed at cost against included usage, and dedicated static IP traffic at $0.15/GB. Model usage is billed separately by the providers whose credentials you connect. Checked against Replicas' pricing page, billing and credentials docs, and changelog on 2026-11-13.

Technical specs

API pricing

Per minute of workspace runtime, the same as any other workspace: $0.004/min small (2 vCPU, 8 GB), $0.008/min large (4 vCPU, 16 GB), $0.016/min ultra (8 vCPU, 32 GB) within included usage, 1.5x beyond it, one-minute minimum per session

Where Replicas excels

Turning Linear issues into pull requests

Assigning an issue to Replicas starts an agent in a configured VM that reads the ticket, implements the change, runs the app and tests, and opens a PR, so small backlog items get done without an engineer starting a local session.

Keeping pull requests green

CI failure response reads the failed check's logs, pushes a fix, and comments on the PR in a separate chat, which removes a common round trip between authors and CI.

Scheduled maintenance across repositories

Automations can run an agent nightly or on GitHub, Sentry, or webhook events with a fixed environment and workspace size, and each run's minutes are tracked in analytics.

Replicas vs. competitors

Replicas vs. Devin

Devin is Cognition's own autonomous software engineer: you assign it tickets from Slack, Teams, Linear, Jira, the web app, or the API, and it works in its own cloud VM. Replicas runs third-party harnesses (Claude Code, Codex, Cursor, Muse Code, OpenCode, Pi) on your credentials and charges for VM minutes. Devin fits teams that want one integrated agent product, and Replicas fits teams that want to keep their chosen agents and switch between them.

Replicas vs. Factory Droid

Factory's Droids are its own multi-model agents, used from a desktop app, CLI, IDEs, CI, and Slack, with Missions and persistent Droid Computers. Replicas does not ship an agent: it hosts other vendors' harnesses, each task in its own Linux VM with warm pools, and bills VM minutes while model costs stay on your own credentials. Factory fits teams standardizing on one agent and its plans, and Replicas fits teams that want to keep Claude Code, Codex, or Cursor and run them in a harness-agnostic cloud runtime.

Frequently asked questions

What is Replicas?

Replicas is a cloud coding agent platform. It runs agents such as Claude Code, Codex, Cursor, Muse Code, OpenCode, and Pi inside isolated cloud Linux VMs connected to your GitHub or GitLab repositories, takes tasks from Slack, Linear, GitHub, GitLab, its apps, or its API, and returns pull requests, commits, or replies for review.

How much does Replicas cost?

Developer costs $50 a month and Team starts at $200 a month in $100 steps. Each includes usage equal to its price, billed per minute while workspaces are awake: $0.004 (small), $0.008 (large), or $0.016 (ultra), and 1.5 times that once included usage runs out. Every workspace counts the same, including API and automation runs, and seats do not change the price. Enterprise pricing is custom. New organizations get $100 of trial usage with no card and no time limit. Model usage is billed separately by your own providers.

Do I need my own Claude or OpenAI subscription?

Yes. Replicas charges for workspace runtime, not model usage. You connect credentials such as a Claude or OpenAI sign-in, Anthropic or OpenAI API keys, AWS Bedrock, Microsoft Foundry, a Cursor API key, OpenCode Go, OpenRouter, or Ollama, and at least one coding agent must be configured before creating workspaces.

Can Replicas fix failing CI automatically?

Yes. When a CI check fails on a pull request linked to a Replicas workspace, the agent is notified, reads the failure logs, pushes a fix, and comments on the PR. This runs in a separate fixes chat, and it wakes a sleeping workspace when needed.

Can Replicas be self-hosted?

Only on Enterprise. Replicas says Enterprise customers can run it in Replicas' cloud, in a dedicated single-tenant deployment, or self-hosted in their own infrastructure.

Replicas vs Devin: what is the difference?

Devin is Cognition's own autonomous software engineer running in its own VM. Replicas runs third-party harnesses such as Claude Code, Codex, and Cursor using your existing credentials, and bills for workspace runtime rather than agent usage.

Integrations & fit

Claude CodeCodexCursorMuse CodeOpenCodePiGitHubGitLabLinearSlackSentryModalInfisicalDopplerAWS BedrockMicrosoft FoundryOpenRouterOllamaMCPREST API
Good fit forSolo / individual, Startup / small team, Enterprise
Pricing modelPaid· Paid subscription required
See pricing on Replicas →

Alternatives to consider

About Replicas

Replicas does not ship its own coding model or agent. It hosts the harnesses your team already uses and gives each task its own cloud machine. A workspace is an isolated Linux VM with your repository, dependencies, and services, where the agent can install packages, run the app, use Docker, drive a desktop and browser, start GPU sandboxes on Modal, and test on cloud iOS and Android devices, then hand back screenshots or recordings. Admins configure environments once (variables, files, skills, MCP servers, plugins, and warm hooks that pre-build images), or let a setup agent propose them, and warm pools keep ready workspaces waiting. Work can start from a Slack message, a Linear issue, a tag on a GitHub or GitLab issue or pull request, the dashboard, the desktop app for macOS, Windows, and Linux, the iPhone and iPad app, the CLI, an MCP client, or the API. Automations fire agents on schedules, on GitHub, GitLab, Linear, Slack, or Sentry events, or from custom webhooks. A Mothership, a long-lived workspace for one area such as billing, splits a request across several ship workspaces and follows each pull request through CI and review. Once a pull request is open, Replicas watches it: when a CI check fails, the agent reads the logs, pushes a fix, and comments, in a separate fixes chat so your main conversation is not interrupted, and allowlisted review bots can trigger follow-ups the same way. The built-in Review page lets you comment on the diff, ask the agent for changes, and merge. Teams bring their own credentials (Claude or ChatGPT sign-ins, provider API keys, AWS Bedrock, Microsoft Foundry, a Cursor API key, OpenCode Go, OpenRouter, or Ollama), so model costs stay with your existing subscriptions, while Replicas charges only for workspace minutes. Developer is $50 a month and Team starts at $200 in $100 steps, each including usage equal to its price, and usage beyond that costs 1.5 times the included rate. Seats do not affect the bill. Enterprise adds SCIM, a DPA, a HIPAA BAA, and dedicated or self-hosted deployment. The tradeoffs are that you still need your own agent subscriptions or keys, heavy automation can push you past the included usage, shared organization credentials can be read by members from inside a workspace, idle workspaces are archived and then deleted within days, and there is no free plan, only $100 of trial usage.

Updates from Replicas

New FeatureWorkspaces size themselves

A new Auto size, now the default, starts workspaces small and grows them when the agent needs more CPU or memory, then shrinks them after 10 quiet minutes, billing each minute at the size it ran at. Motherships also gained a live board of what needs you, what is ready to review, and what is in progress.

New FeatureMotherships for every organization

Motherships, long-lived workspaces for one area of work, opened to everyone. One agent splits a request across as many ship workspaces as it needs, follows each pull request through CI and review, and can take work from its own Slack channel or matching Linear tickets.

PricingUsage-based plans replace seats

Developer ($50) and Team (from $200, in $100 steps) now include usage equal to their monthly price, billed per workspace minute, with overage at 1.5 times the included rate. Seats no longer affect the bill, and the free trial became $100 of usage with no time limit.

LaunchReplicas for iOS

Replicas released an iOS app for starting cloud coding agents, steering them mid-run, and reviewing their pull requests. It works with existing Developer, Team, and Enterprise accounts and the environments, credentials, and integrations configured on the web.

New FeatureGoal mode for Claude Code and separate CI-fix chats

Claude Code workspaces can now work toward a stated goal with /goal, and CI failures and review-bot comments fork a separate PR fixes chat instead of interrupting the main conversation. Opus 5.5, GPT-6 Sol, and GPT-6 Luna became available in new workspaces.

PricingFull and Flex seats with lower prices

Replicas moved to Full seats at $50 a month on Developer and $200 on Team, added pay-as-you-go Flex seats for manual minutes, and began billing API and automation runtime per minute on both plans.

Are you the founder? Claim this listing →