How workspaces run
Each workspace runs the Replicas Engine, which manages agent sessions, queued messages, git operations, previews, and workspace tools. The engine keeps the agent session and branch available while the workspace is awake. Messages sent while an agent is busy are queued in order. You can edit or remove a queued message before it starts. Supported agents also let you steer an active turn with a queued message. Clearing the queue removes waiting messages without adding them to chat history or interrupting the active turn. Messages from any source also wait in order while a workspace prepares or wakes, then run when it is ready.Background tasks
Claude background tasks appear in the transcript with their status, latest activity, output path, and resource usage. They can continue after the turn that created them, and you can send another message while they run. Stop ends the active Claude session and its background tasks; your next message resumes the conversation. Workspace lifecycle actions such as Archive when done wait for background work and Claude’s completion response. If a finished task does not wake Claude, Replicas tries one recovery prompt. A watchdog cancels ordinary background tasks after one hour by default, excluding paused work and persistent Monitor watches. If cancellation fails, Replicas stops the Claude session and shows an error. Failed or stopped tasks remain visible in the transcript. To change the limit, addREPLICAS_CLAUDE_BACKGROUND_TASK_TIMEOUT_MS to your environment’s variables before creating a workspace. Set an integer number of milliseconds, such as 7200000 for two hours. Supported values are 1000–2147483647; invalid values use one hour.
Workspace tools
Changes and files
Use the provenance pane to review changed files, browse the repository, and open files mentioned by the agent. In Changes, you can mark files as viewed and attach line comments to send with your next message. Compatible files opened from the repository browser open directly in edit mode, while files opened from Changes open as a read-only diff; select Edit to modify the file in place. On workspaces created before in-place editing shipped, Changes opens a read-only diff with highlighted additions and deletions instead. Select Save or pressCmd/Ctrl + S to write the draft. Markdown files also offer a rendered Formatted view. Agent changes are folded into an open draft automatically; all-changes and completed turn diffs remain read-only review surfaces.
A file opened from Changes shows its changed hunks with surrounding context. Select a collapsed region to expand it in place, or Show full file to render the whole file; Show changes returns to the hunk view.
Hover a code symbol to inspect its type and documentation. Cmd/Ctrl-click opens its definition, including definitions in another file; add Shift to list references. Replicas uses the repository’s language server when available and falls back to workspace symbol search.
When a chat turn finishes with workspace changes, the chat view shows a workspace-level summary with the changed file count and total additions and deletions. Select a file to open its diff, or select Review to open all workspace changes. The summary shows three files initially; select Show more files to expand the full list.
To comment on a range, drag across line numbers or select the first line and Shift-click the last, then use + to attach the selected range and code to your next message. In split view, keep the selection on one side of the diff. Without a range selected, + attaches a single-line comment.
Files attached to chat and files the agent places in ~/.replicas/canvas/ appear in Canvas. Images, video, audio, PDFs, Markdown, Mermaid, HTML, and common text formats have inline viewers.
Click an image attached to a user message to inspect it at full size.
On the web, select, drag and drop, or paste up to five images of 20 MB each into a new task or existing chat. JPG, PNG, WebP, GIF, HEIC, and HEIF are supported; Replicas converts HEIC and HEIF photos to JPEG before sending.
Desktop tab
Every workspace includes a Linux desktop with Chrome. Open Desktop in the provenance pane to watch the screen, then select Interact for mouse, keyboard, scrolling, and audio. The desktop and its processes continue running when you close the viewer. They also survive sleep on the default pause mode. Only authenticated Replicas users can open its viewer URL. The desktop follows your dashboard theme, so switching between light and dark also switches its wallpaper, dock, and windows. Chrome switches with the desktop while its tabs remain open; other applications may need to be relaunched. The stream settings menu in the viewer header chooses the transport (WebRTC by default, with automatic WebSocket fallback), a Balanced or Text quality profile, adaptive or pinned quality, and how the 1920×1080 picture is shown: fitted to the panel, at native size (one source pixel per CSS pixel), or at device pixels. Show diagnostics overlay displays the live transport and route, negotiated codec profile, source, decoded, CSS and device dimensions, displayed and decoded frame rates, bitrate, latency, loss, server load, and the latest server and viewer events, such as a WebSocket fallback and its reason or a quality change and the signals behind it. Open stream telemetry opens the same snapshot as JSON with the last five minutes of one-second samples and events. Settings are stored in your browser and also apply when you open the viewer in a new tab. Existing transport preferences are preserved; you can select WebSocket manually. Use the CLI computer commands when an agent needs to capture screenshots, interact with the browser, or record the screen.Terminal and Docker
Open Terminal beside Canvas to run an interactive shell. Use + to create independent terminal sessions. Docker is installed but starts on demand. To make it available during every workspace setup, add this command to a start hook:replicas.yaml
Chats and collaboration
- Create multiple chats to separate workstreams. Each chat keeps its own agent, model, effort, and history.
- New chats start with your resolved personal or organization defaults, then retain their selected agent and model across follow-ups and workspace wakeups until you change them.
- Drag chat tabs to reorder them. Delete a chat from its context menu; deleting an active chat stops its turn.
- Long chats open at the newest messages and load older history on demand as you scroll. A loading state appears while newer messages refresh.
- Live tool calls appear in an expanded, scrollable Working for … section. It follows new activity until you scroll up. When the assistant replies, it collapses into Worked for …; select it to inspect the activity.
- Completed turns show their total elapsed time below the response.
- On the web, an unconfirmed send times out after 60 seconds, keeping your draft and unlocking the composer. Check the conversation before retrying; the message may already have arrived.
- Share workspaces with teammates to add them to the teammate’s Shared view. Organization members already have access; opening the link automatically switches to the organization that owns it.
- Recent activity on Home lists workspaces strictly by last interaction: messages sent and agent turns completed. Opening or waking a workspace does not reorder it. Each row shows the creator, contributors, and the state of any linked pull request. Rows group under Today, Yesterday, Last week, and Older, and pinned workspaces list above in their own section. Each date group initially shows five workspaces, with Show more revealing the rest. The activity list scrolls independently while the composer and selectors remain fixed. Select a heading to collapse or expand that group.
- Home visibility is independent of sidebar Owner selections: with Workspace Visibility disabled, it lists only workspaces you own; when enabled, it also lists shared and team workspaces. Ownerless API and automation workspaces stay out of Home.
- Use split view on desktop to compare multiple workspaces side by side.
- The workspace header shows linked pull requests and their checks. Eligible reviewers can approve, and standalone mergeable pull requests can be merged from the checks popover even while the workspace is sleeping. Merging uses the GitHub integration directly and does not wake the workspace.
- Use
Cmd/Ctrl+Kto search pages, environments, automations, and workspaces. See Keyboard shortcuts for prompt controls and the full in-app reference.
Keyboard shortcuts
While the prompt input is focused, useCmd+Shift+Option+H, Cmd+Shift+Option+M, or Cmd+Shift+Option+E to cycle the harness, model, or effort. On Windows and Linux, use Ctrl+Shift+Alt+H, Ctrl+Shift+Alt+M, or Ctrl+Shift+Alt+E instead.
Press Cmd/Ctrl + / to open the full keyboard shortcut reference.
Chat commands
Type/ in the composer to see commands supported by the selected agent. The menu also opens on a / typed after existing text, and closes once you type a space. Picking a command replaces only the / word you are typing, leaving the rest of your draft untouched.
/planasks the agent to propose a plan before editing. See Plan mode./fastenables a faster service tier where supported. See Fast mode./compactcompacts the active Claude Code, Codex, or Muse session./goal <objective>creates a persistent goal for a Codex chat.
Repository targeting
A workspace can use one repository or a repository set. Repository sets save combinations of repositories for tasks that span services. Every workspace uses one environment. The environment provides its repositories, variables, files, skills, MCP servers, system prompt, and setup hooks. Values from the organization-wide Global environment are merged into it. Before creating a task from Home, the starting point control sets the branch each repository starts on. A single-repository environment opens its branch list directly; otherwise every repository is listed so you can choose a branch for each. Repositories without an override use their configured default branch.Sleep and wake
Workspaces sleep after one hour without activity. Sending a message wakes a sleeping workspace automatically and resumes its previous branch and agent session. Archived workspaces stay paused until you explicitly restore them; messages, integration events, and API reads do not restore them.
Selecting a sleeping workspace from Home starts waking it before navigation, so startup is already in progress when the workspace opens.
Sleeping workspaces with no activity for seven days are archived. Archived workspaces with no activity for 30 days are deleted. Waking a sleeping workspace, restoring an archived workspace, or sending a message resets its activity window; viewing an archived workspace does not. See Data retention for organization controls.
You can force sleep, archive, restore, or permanently delete a workspace from its sidebar actions menu. These actions are also available in bulk-selection mode.