Skip to main content
Replicas runs Claude Code inside isolated workspace VMs, with access to your repository, environment configuration, and integrations.

Setup

Choose one authentication method:
  • Ollama: Add an API key and base URL under Ollama in Coding Agents. See Ollama setup.
  • Claude subscription: In Coding Agents, click Connect Claude subscription, run claude setup-token on your computer, and paste the sk-ant-oat01- token it prints. Replicas checks the token with one short request before saving it. Or run replicas claude-auth. The login lasts one year, and its expiry date appears in Coding Agents. Paste a new token under the same label, or run the command again, to renew it.
  • Anthropic API key: Add a key under Organization → Coding Agents.
  • Anthropic-compatible endpoint: Add a gateway’s base URL and API key under Anthropic Compatible in Coding Agents. See Anthropic-compatible setup.
  • Microsoft Foundry: Add a Foundry API key, resource name, and optional Claude deployment names under Organization → Coding Agents.
  • AWS Bedrock: Add AWS credentials and a region under Organization → Coding Agents.
A token pasted in Personal → Coding Agents or saved by replicas claude-auth belongs to your personal account, which works in every organization you belong to and takes priority over organization defaults. Admins can pass --org to share one Claude subscription with every member of the active organization. See Credentials for details, and replicas org to check which organization is active.

Models

Replicas supports Claude Fable, Opus, Sonnet, and Haiku models. Set the organization default under Organization → Settings → Preferences, or choose a model for an individual chat. Claude Fable 5.2 is available as claude-fable-5-2. Claude Sonnet 5.5 is available as claude-sonnet-5-5. Claude Haiku 5.5 is available as claude-haiku-5-5. The available models depend on the authentication method and model access on the connected Anthropic or Bedrock account. On AWS Bedrock, Claude Code uses the inference profile for the credential’s region (for example us.anthropic.claude-sonnet-5-5 in us-east-1). If a model isn’t available there, the turn falls back to the model it replaced, such as Sonnet 5 for Sonnet 5.5. Every Claude model Replicas supports appears in the workspace, automation, and default-setting pickers, including models added later. Organization admins can hide individual models under Claude → Models in Coding Agents settings; a hidden model disappears for everyone in the organization, and at least one must stay visible. A workspace runs the Claude Code build its sandbox image shipped with, so one created before a model was released does not offer that model. Start a new workspace to use it.

Using Claude Code in Workspaces

In a workspace, use the composer’s harness/model picker to choose Claude Code and start or continue a session. Claude Code can:
  • Read and edit files and run shell commands
  • Use environment skills and MCP servers
  • Create branches, commits, and pull requests
  • Run background Bash, Agent, and Monitor tasks
  • Accept queued messages steered into an active turn, which Claude reads at its next tool call
Background task status and output appear in the transcript and can continue across turns. See Workspace background tasks.

Fast Mode

Fast Mode is available for Claude Opus models. Start a message with /fast or use the lightning toggle in the composer.

Goal Mode

Use /goal <condition> or the goal toggle in the composer to keep Claude working until a condition holds. After each turn, Claude Code checks the condition with a small, fast model and starts another turn if it is not met. The goal appears above the composer until it is met or you remove it with /goal clear. Goals cannot be paused or edited, and Stop keeps the goal, so your next message continues it. See Claude Code goals for writing conditions.

Thinking levels

Use Ultracode in the thinking picker to combine xhigh effort with Claude Code dynamic workflows when supported by the connected model and plan. Ultracode workflow subagents appear in the workspace’s Subagents agent tree, where you can inspect each child transcript.

Chat history

Claude Code sessions persist across turns and workspace sleep. Claude Code compacts automatically near the end of the context window; set an Auto-compact limit in your preferences to compact sooner. Send /compact to compact the active session without starting a new one, or use replicas read from the CLI to inspect transcript history.

Programmatic Use

Select Claude Code anywhere Replicas accepts a coding agent:

When to Use Claude Code

Claude Code is a strong fit when you want Anthropic-native agent behavior, long-running background tasks, or Claude skills and commands. Use Codex when you need pausable goals or OpenAI-native models; use Cursor or Opencode when you prefer their model and authentication ecosystems.