Full comparison
Cloud coding agents, criterion by criterion
What each product does, taken from its own docs and pricing pages as of November 9, 2026. Green is a yes, amber is partial support, red is a no, and grey means we couldn't confirm it from public sources.
| Criterion | Replicas | Devin | Cursor | Claude Code | Codex | OpenCode |
|---|---|---|---|---|---|---|
| Agents | ||||||
| Multi-harness support | YesClaude Code, Codex, Cursor, OpenCode, Pi and Muse Code; pick the agent per task | NoDevin's own agent; you choose models inside it, not other agents | NoThe Cursor agent with a curated set of models | NoClaude Code only | NoCodex only | NoOpenCode only, but with 75+ model providers |
| Environment | ||||||
| Isolated cloud VM per task | YesEach workspace is its own isolated Linux VM (2, 4 or 8 vCPU) | YesEach session boots a fresh copy of the organization's snapshot in a Linux VM | YesCloud Agents run in isolated VMs with full development environments | YesClaude Code on the web runs each session in an Anthropic-managed Ubuntu VM (about 4 vCPU, 16 GB) | YesCodex cloud runs tasks in OpenAI VMs (2 vCPU/8 GiB on Plus, 4 vCPU/16 GiB on Pro and Business) | PartlyRuns wherever you put it; you provide and isolate the VM or container |
| Workflow | ||||||
| Pull request output | YesThe agent opens the pull request (GitHub) or merge request (GitLab) | YesReturns pull requests for review | YesCloud Agents push a branch and open pull requests with screenshots, videos and logs | PartlyCloud sessions push a branch; you create the PR from the session | PartlyYou open the PR from the finished task | Partly/oc comments through its GitHub integration; otherwise you script it |
| Local IDE workflow | NoAgents run only in the cloud; the desktop app and CLI connect to cloud workspaces and can open one in VS Code | YesDevin Desktop and Devin CLI | YesThe Cursor editor and CLI | YesTerminal CLI and IDE extensions; --teleport pulls a cloud session into your terminal | YesCLI, IDE extension and ChatGPT desktop app | YesTerminal, desktop app and IDE integrations |
| Where work starts | ||||||
| Start from Slack | YesMentions, DMs and threads | YesSlack and Microsoft Teams | Yes@cursor in Slack | CheckConfirm current Slack support with Anthropic | CheckConfirm current Slack support with OpenAI | CheckNot part of the core tool; confirm or build it |
| Start from Linear | YesAssign or mention on an issue | YesListed as an integration | Yes@cursor in Linear | CheckConfirm with Anthropic | CheckConfirm with OpenAI | CheckNot part of the core tool; confirm or build it |
| Start from GitHub | YesMention on issues and PRs; can act on failed checks and reviews | YesA PR comment starting with /devin starts a session | Yes@cursor on a GitHub PR or issue | YesGitHub repositories; @claude in issues and PRs through claude-code-action | YesGitHub repositories; @codex review on pull requests | Yes/oc comments on GitHub issues and PRs |
| Start from GitLab | YesIssues and merge requests; one workspace can span GitHub and GitLab | YesGitLab and Bitbucket; self-managed GitLab on Enterprise | PartlyWorks on GitLab repositories; @cursor comments are documented for GitHub and Bitbucket | PartlyGitLab repos can be sent as a bundle, but cloud sessions can't push back | NoGitHub only for now; GitLab is on OpenAI's roadmap | CheckConfirm with the OpenCode project |
| Start from Jira | NoAgents can use Jira through a plugin, but a Jira issue can't start a task | YesStarts work from Jira issues | CheckConfirm with Cursor | CheckConfirm with Anthropic | CheckConfirm with OpenAI | CheckNot part of the core tool |
| Models and billing | ||||||
| Bring your own model keys | YesAnthropic, OpenAI, AWS Bedrock, Microsoft Foundry, OpenRouter, Cursor and OpenAI-compatible keys | PartlyA ChatGPT plan can pay for GPT usage; no API-key option is documented | NoCloud Agents bill your Cursor plan's usage at model rates | PartlyCloud sessions need a Claude plan; API keys and Bedrock aren't supported there (the CLI takes them) | PartlyCodex cloud requires a ChatGPT sign-in; API keys work only in the CLI | Yes75+ providers through your own keys, plus local models |
| Use your Claude or ChatGPT plan | YesClaude and ChatGPT subscriptions | PartlyChatGPT plans only | NoUses Cursor's own plans | YesPro, Max, Team and eligible Enterprise seats | YesChatGPT Plus, Pro, Business, Enterprise and Edu | YesChatGPT Plus or Pro, GitHub Copilot and GitLab Duo sign-ins |
| Usage-based compute pricing | YesBilled per workspace minute by VM size; sleeping and archived workspaces cost nothing; seats are free | PartlyUsage quota plus credits; Teams adds $40 per seat | PartlyPlan usage at model rates; Cloud Agents need a Premium, Teams or Enterprise plan | NoSeat-based plans from $20/mo; no separate VM charge | NoSeat-based ChatGPT plans from $20/mo | PartlyThe software is free; your servers cost whatever you pay for them, idle or not |
| Security and governance | ||||||
| SOC 2 report | YesSOC 2 Type I | YesSOC 2 Type II | YesSOC 2 Type II, ISO 27001 and ISO 42001 | CheckCheck Anthropic's Trust Center | CheckCheck OpenAI's Trust Portal | PartlyCompliance is your infrastructure's; there is no vendor service to audit |
| SOC 2 Type II today | NoSOC 2 Type II is in progress | YesSOC 2 Type II since September 2024 | YesSOC 2 Type II attestation | CheckCheck Anthropic's Trust Center | CheckCheck OpenAI's Trust Portal | PartlyCompliance is your infrastructure's |
| SCIM provisioning | YesSCIM provisioning on Enterprise | CheckSAML and OIDC SSO on Enterprise; confirm SCIM with Cognition | YesSSO and SCIM | CheckCheck the Claude Enterprise plan | CheckCheck the ChatGPT Enterprise plan | NoNo hosted user management |
| Audit log | YesAudit log of every configuration change | YesAudit logs on Enterprise | YesCompliance and audit logs on Enterprise | CheckCheck the Claude Enterprise plan | CheckCheck the ChatGPT Enterprise plan | PartlyWhatever logging you build around it |
| Self-hosted or dedicated deployment | YesSelf-hosted or dedicated single-tenant deployment on Enterprise | PartlyA dedicated VPC run by Cognition; Outposts move command execution to your machines | PartlySelf-hosted machines for tool execution; the service itself is Cursor-hosted | PartlyCloud sessions are Anthropic-hosted; the CLI can run on servers you control | PartlyCodex cloud is OpenAI-hosted; the Apache-2.0 CLI runs anywhere | YesRuns entirely on your own machines |
| HIPAA BAA | YesHIPAA BAA on Enterprise | CheckConfirm with Cognition | CheckConfirm with Cursor | CheckConfirm with Anthropic | CheckConfirm with OpenAI | PartlyDepends on where you run it and which model provider you use |
| Scale | ||||||
| Parallel runs | YesRun many workspaces at once and compare them side by side | YesUp to 10 concurrent sessions on Pro, unlimited on Max and Teams | YesAs many Cloud Agents in parallel as you want | YesSeveral cloud sessions at once | YesSeveral cloud tasks at once | PartlyAs many copies as you run |
| Scheduled and event-driven runs | YesSchedules and GitHub, GitLab, Slack, Sentry and webhook events | YesScheduled sessions (presets or cron) | YesCloud Agent automations | PartlyThrough GitHub Actions or your own scheduler | PartlyThrough codex-action in GitHub workflows | PartlyThrough cron or CI you set up |
Spotted something out of date? Vendors ship fast. Use the form on any page and we'll correct it.
The products
Replicas by Replicas Group Inc.
A cloud coding-agent platform that runs Claude Code, Codex, Cursor, OpenCode, Pi and Muse Code in isolated cloud VMs, started from Slack, Linear, GitHub, GitLab or the dashboard, and hands back pull requests.
Best for: Teams that want several agents working in parallel in the cloud, on their own model accounts, started from the tools they already use.
Sources: Replicas facts, Replicas pricing, Replicas enterprise, Replicas docs
Devin by Cognition
Cognition's autonomous software engineer: its own agent, cloud sessions in a VM, an editor (Devin Desktop, formerly Windsurf), a CLI and a codebase wiki.
Best for: Teams that want one vendor's agent end to end, start work from Jira, or need a SOC 2 Type II report today.
Sources: Devin pricing, Devin docs, Replicas vs Devin source list · Replicas vs Devin
Cursor by Anysphere
An AI code editor whose Cloud Agents run the Cursor agent in isolated cloud VMs and return pull requests, started from the editor, the web, Slack, Linear, GitHub or the API.
Best for: Teams whose engineers live in the Cursor editor and want cloud runs connected to that local workflow.
Sources: Cursor Cloud Agents docs, Cursor security, Cursor pricing · Replicas vs Cursor
Claude Code by Anthropic
Anthropic's coding agent: a terminal CLI and IDE extensions, plus Claude Code on the web, which runs sessions in an Anthropic-managed VM.
Best for: Teams standardised on Claude Code, on GitHub, who already pay for Claude plans and mostly pair with the agent locally.
Sources: Claude Code on the web, Claude Code GitHub Actions, Claude pricing · Replicas vs Claude Code on the web
Codex by OpenAI
OpenAI's coding agent: an open-source CLI, IDE extension and SDK, plus Codex cloud, which runs tasks in OpenAI-hosted environments from ChatGPT.
Best for: Teams standardised on Codex and ChatGPT plans, working in GitHub.
Sources: Codex cloud, Codex pricing, Codex authentication · Replicas vs Codex cloud
OpenCode by OpenCode (open source)
An MIT-licensed terminal coding agent that works with 75+ model providers and local models. Run it yourself on a laptop, a server or CI.
Best for: Teams that want an open-source agent on any model and are happy to run and secure the infrastructure themselves.
Sources: OpenCode docs, OpenCode providers, OpenCode GitHub integration · Replicas vs running OpenCode yourself