A desktop dashboard for managing Claude agent sessions.
Less noise. More visibility. Full control.
Otto is a desktop dashboard for professional developers who run multiple Claude agents simultaneously. It replaces noisy terminal logs with a clean, real-time overview — session status, file diffs, costs, and tasks all visible at a glance. Less scrolling, more doing.
It's built around GitHub. Launch agents from issues, PRs, and discussions, manage worktrees, and automate sessions with webhooks and cron triggers — so your agents can respond to events without you being there.
Otto works with the Anthropic API, Amazon Bedrock, Google Vertex AI, and Azure AI Foundry. If you're on Bedrock, Vertex, or Azure and don't have access to Claude's native apps, Otto gives you a first-class experience regardless of your provider.
- Launch and monitor multiple agent sessions simultaneously from a single dashboard
- Stage overview with tiered session grouping: Needs Attention, Working, Idle, and Inactive
- Stage cards show a thumbnail of the agent's most recent browser capture, so you can spot who's driving a page without opening each session
- Stage cards show Otto and each running sub-agent as small figures along the bottom edge, the same cast Centre Ring uses, so you can see who's active in a session at a glance
- Sessions requiring human input are surfaced at the top automatically
- Session pinning, forking, renaming, and history replay
- Filter and search across all sessions
- Agent orchestration — agents can spawn child sessions to delegate work, send messages between sessions to coordinate, and check what a session has cost so far to judge whether more work is worth it. A bundled Orchestrator agent type ships out of the box — pick it as a session's main agent to have it delegate work to sub-agents itself while it stays focused on synthesising the result
- Live streaming transcripts with rich content types — code, files, tool calls, thinking blocks, memory recalls
- "Now Playing" header showing the agent's current activity at a glance
- File checkpoint and rewind system with visual diff preview before confirming
- Transcript annotations — highlight text and attach comments as context for the next prompt
- Chat — a conventional top-to-bottom conversation, the default view for every session. Your prompts sit on the right, Claude's replies on the left, with the tools, sub-agents, and thinking that happened in between collapsed into a working card that expands in place — no separate dialogs. Sub-agents get a card of their own showing which one ran, on what model, and what it cost. Permission, question, and plan prompts appear inline as an ask card in place of the composer until you answer
- Centre Ring — an alternative view built around a single spotlight. Otto stands in it with a line showing what he's doing right now; sub-agents walk into view as crew when they start work and take a bow when they finish; each turn becomes a bar in a strip along the bottom, sized by how long it took. The house behind the beam lights up seat by seat as a turn's prompt fills the context window Claude will compact at, and goes dark again after compaction. The spotlight turns gold whenever the session needs a decision from you, with permission, question, and plan prompts stepping into it to ask. Click any bar in the turn strip to open that turn full-page — full prompt and full response, like a page in a printed programme — step to neighbouring turns with the arrows, and pull the hem across the top at any time to return to the live turn. When Claude has a page open, it plays out right there on the stage at the page's own device size while Claude is driving it — step away or ask a question and it shrinks back out of the way, and it's yours to take over or close only once the turn is done. Once a turn closes and nothing else needs your attention, Otto turns to you with a speech-bubble suggestion for what to do next — accept it to send it as-is, edit it first, or wave it away
- Route Book — a third view for going through the whole session in detail rather than watching it live: every agent, every event, nothing summarised away. A roster lists each agent with its status, tools, tokens, cost, and elapsed time — click one to filter down to just its work. A searchable, filterable ledger lists every event in order, grouped into acts, and expands inline for the full detail: prompts, tool calls with their output, diffs, questions and answers, sub-agent summaries. Alongside it, a rail breaks down cost by model and act, tools used, files touched, crew, and notable signals. Switch between Chat, Ring, and Route Book from the session header — your choice is remembered
- Granular session configuration: permission modes, thinking budgets, cost limits, turn limits, sandbox mode, tool restrictions, structured output, auto-compaction, and more
- Container sessions — give a session its own isolated environment with its own ports and dependencies, so two agents can run dev servers side by side without colliding. macOS only; requires a one-off
container system start - Interactive permission and plan approval with visual previews
- Auto-approval mode — safe tool requests are approved automatically; risky or uncertain requests still surface for manual review, and any request the automatic check blocks is recorded in the transcript so you can see what was denied and why
- Follow-up message queueing while agents are working
- Prompt suggestions, slash command autocomplete, and drag-and-drop file attachments — any file type, not just images; attach when creating a session or any time after, and Otto reads the file where it lives, no copying required
- Provider profiles — configure and switch between API providers, with environment isolation and auto-detection of existing credentials
- Change model, permission mode, reasoning effort, thinking on/off, output style, and auto-compaction on/off mid-session
- Review a plan right where you read it — highlight any passage to leave a note pinned beside it, instead of a separate review dialog. When approving, pick the implementation permission mode, reasoning effort, output style, and (optionally) a different model — so you can plan with Opus and build with Sonnet on a fresh context window. Clear context is also available mid-session from the sidebar.
- When Claude presents options or asks questions, Otto renders fully interactive HTML previews directly in the dashboard
- See UI mockups, architecture diagrams, and design options as actual rendered visuals — not markdown descriptions
- Options and their preview sit side by side, so you can compare choices and the mockup at once without scrolling
- Quickly verify your agent understands the task before it starts building
- Agents can open web pages directly inside the session panel for you to review — no separate window needed
- Resizable browser panel with device viewport presets (mobile, tablet, desktop), fullscreen expand, and toolbar controls
- Annotation overlay lets you highlight elements on the page, add comments, and send structured feedback back to the agent
- Element screenshots and selectors are included in the feedback so the agent knows exactly what you're referring to
- Agents can browse autonomously — when an agent drives the browser itself, the panel minimises to an "Agent browsing" indicator you can expand to watch the page live, then collapse again when you're done
- Worktree overview showing linked agent sessions per worktree
- GitHub panel with Issues, Pull Requests, Discussions, CI Runs, and Tags
- One-click "Launch Agent" from any GitHub item — automatically creates a worktree
- Full worktree lifecycle management with batch operations and safety checks
- Self-assignment on issues, label filtering, fuzzy search
- Conflicted PRs are flagged in the list, with a one-click Resolve conflicts action that spins up a worktree agent to merge the base branch in safely (no force-pushes)
- Branch changes panel — a live diffstat of your branch against main, with a slide-over showing branch and push state, your linked pull request (review and CI status), the branch's own commits, and every changed file grouped as Staged / Unstaged / Untracked — click any file for its diff. Commits expand in place to show the files they touched, each opening its diff at that commit. Available from every session view: as a tile in Chat and Dashboard, or via the sidebar's file-count stat elsewhere
- Dedicated Automations tab with structured editors for cron schedules and GitHub webhook rules — no need to hand-edit files
- Cron editor with schedule presets and a live next-fires preview, so you can see when your automation will actually run
- Webhook match builder with event/action chips, repo/sender/label filters, and payload matchers — plus a Form/Raw toggle for power users
- Live event feed and Insights panel showing top event types, recent volume patterns, and one-click "Create automation" suggestions for frequent events
- Per-automation session configuration (model, reasoning effort, permissions, worktree, sandbox, budget, and more)
- Per-repo on/off toggles in the header for crons and webhooks — automations are off by default for each repo, so nothing fires until you explicitly enable it, and your choice is remembered across restarts
- Dedicated Hooks tab with structured editors for command, prompt, agent, and HTTP hooks across user, project, and local settings
- Test panel — run any hook against a synthesised payload, see exit code, stdout, and stderr without leaving the dashboard
- Recent-fires strip per hook showing the last execution outcomes from live sessions, so you can spot misbehaving hooks at a glance
- Enable or disable hooks without deleting them — Otto stashes disabled hooks safely so Claude never sees them
- Inline rename with Otto-managed metadata, plus a Form/Raw toggle for power users
- Dedicated Memory tab unifying both Claude memory systems — Instructions (CLAUDE.md hierarchy) and Learned (auto-memory) — in one place
- View, edit, create, and delete entries at every level you own, across user and project scopes
- Header stat line shows entry counts and approximate token usage at a glance
- Memory behaviour settings tucked into a collapsible section so the main view stays focused on content
- Dream now button opens a pre-filled session that reviews and consolidates your learned memories on demand
- Auto-dream toggle schedules nightly consolidation itself, so it works reliably on every supported provider — not just when signed in directly with Claude
- Five brand themes, each available in dark and light — switch from a picker in the header
- Every theme re-tints the whole interface, not just the accent colour, while keeping the same contrast and legibility
- Your choice persists across reloads, with no flash of the wrong theme on startup
- Project picker with automatic git repository scanning
- Searchable project/repo switcher (⌘P) — jump straight to any project or repo in your workspace
- Multi-repo projects — a single project can contain multiple git repositories; repos show as pills that fold into an overflow menu once there are too many to fit
- Live session chips — a project you're not currently viewing shows a chip with its session count if it has an active session, so you can spot activity across your whole workspace at a glance
- Reorder and remove projects from the switcher — your preferred ordering is remembered across reloads
- Unified browse view across all configured marketplaces — installed and available plugins side by side, no dropdown prerequisite
- See what each plugin ships before installing — skill, agent, command, hook, MCP, and LSP counts on every card, with a full named breakdown and descriptions on the detail page
- Dedicated plugin detail pages with author, repository, licence, and keywords surfaced from marketplace manifests
- Enable, disable, and configure plugins at user, project, or local level — inline from the detail page
- Add marketplace sources from GitHub, npm, git, URL, file, or directory
- Trust and security controls: strict mode, blocked sources, and custom trust messages
- In-app feedback tool — annotate UI elements and submit bug reports directly from the dashboard
- Automatic updates with in-app download and restart
- Detailed context usage breakdown with token counts by category
- Live cost and token tracking across sessions, with a cost detail view showing total tokens, cache hit rate, and exact counts — spend survives reconnects, reloads, and restarts
- SDK recording and debugging tools
- Mobile-responsive layout
Coming soon. Otto is currently in development. Watch this repo to be notified when downloads are available.
- Download and install Otto from the links above
- Open Otto — the dashboard opens automatically
- Select a project — Otto scans for git repositories and lets you pick one
- Create a session — configure permissions, thinking budget, and tools, then launch your first agent
- Watch it work — follow the real-time transcript, approve permissions when asked, and queue follow-up messages
Otto is currently in closed beta. You can download and install it, but you'll need a licence key to use it.
If you'd like to try Otto, open a discussion or reach out directly to request access.
Note: Otto is the dashboard. You bring your own API access — Anthropic API, Amazon Bedrock, Google Vertex AI, or Azure AI Foundry.
- macOS 12 or later (Apple Silicon or Intel)
- One of the following:
- An Anthropic API key
- Amazon Bedrock access with Claude enabled
- Google Vertex AI access with Claude enabled
- Azure AI Foundry access with Claude enabled
- Bug reports — Open an issue
- Feature requests — Open an issue
- Questions & discussion — Start a discussion
Made by m2de