Omniscio

Omniscio does…
a lot.

Watch the short tutorials, start with the features people use most, then browse the full list.

Tutorial videos

Short videos that show Omniscio in action. Press play on any of them.

Top features

The ones people reach for first, in order.

  1. 1

    Concurrent Multi-Session Orchestration

    Run many Claude Code sessions at once across your projects, and mix in Codex, Gemini and other engines side by side. Sessions that need you show up in an inbox, so you respond and move on.

  2. 2

    Unified Inbox

    See sessions, texts, Gmail and other channels together in one triage view, with tabs and unread counts. Clicking a row opens the right viewer, and reading a text clears it from the inbox.

  3. 3

    Session Statuses & Attention-First Design

    Every session shows a clear status with its own color, and the ones that need you float to the top with the reason, such as a question or a plan to approve. You get an alert when one needs you.

  4. 4

    Web Remote Access

    Control Omniscio from your phone's browser or as an installed home-screen app. Pair by scanning a QR code, see and revoke connected devices, and reach it only through your own Tailscale network unless you switch on public access.

  5. 5

    AI Manager (Plain Speak)

    Plain Speak rewrites each finished agent reply into a short plain-language card you can read at a glance, with a toggle back to the original. You can turn it on per session or pause it everywhere.

  6. 6

    Auto-Run (Away Mode)

    Set rules that reply to, retitle, archive or triage sessions that finish while you are away, based on keywords, project, tag or time of day. Loop and spend limits prevent runaway replies, and automatic replies carry a green badge.

  7. 7

    Git Worktree Isolation

    Each session can work in its own separate copy of the project on its own branch, so parallel sessions do not trample each other. Finished work merges back to your main copy, and unfinished work is never destroyed.

  8. 8

    Auto-Lander

    When you mark finished work ready, Auto-Lander merges it into your main copy on your own computer, one branch at a time, and never uploads anything. If a merge keeps getting sent back, it reopens the session to fix it.

  9. 9

    Voice Conversation & Report-Back

    Have a spoken back-and-forth: hear replies read back, ask questions about the open session, or ask a running agent and hear its answer. Off by default, with separate daily spending limits and a saved history.

  10. 10

    FlowVoice — OS-Wide Dictation

    Dictate into any app on your computer: hold a global hotkey, speak, and the cleaned-up text is typed at your cursor. Audio is saved as you speak and failed transcriptions are retried, so a dictation is not lost.

  11. 11

    Record for Agent

    Record your screen while you talk and mark key moments by hotkey, note, voice or a drawn box. Then send the take to an agent that reviews it and works through the task list with you. It builds on the Screen Recorder.

  12. 12

    Recipes (Multi-Step Playbooks)

    Save multi-step playbooks you can reuse across projects, or describe one in plain English and let AI draft it. Runs show live progress and cost, honor spend and time limits, can pause for your approval, and resume from where they failed.

  13. 13

    Budget Caps (Soft & Hard)

    Set a hard spending limit that stops a session when its cost crosses it, plus an earlier one-time warning. Sessions on a subscription plan are never capped.

  14. 14

    The Vault (KMS)

    A private knowledge base your agents can search, read, write and cite. Capture notes once and every session can use them. It is off by default, and you turn it on in Settings.

  15. 15

    Artifact Sharing (Omniscio Shares)

    Publish a session, message or selection as a single web page with a link. Protect it with a password, set an expiry, update it in place, revoke it, allow comments, and track views.

Core Session Orchestration 21

Concurrent Multi-Session Orchestration

Run many Claude Code sessions at once across your projects, and mix in Codex, Gemini and other engines side by side. Sessions that need you show up in an inbox, so you respond and move on.

What's inside (9)
  • Concurrent sessions — run many Claude Code sessions in parallel, across as many projects as your plan allows.
  • Background process management — each session runs as a managed child process, spawned, monitored, and reaped by the app.
  • Multi-provider sessions — run sessions on Claude, Codex, Gemini, and other engines side by side, each isolated.
  • Auto vendor routing — pick a model once and never touch the underlying company: every non-Claude session is served by the first service in that model family's provider list that can run it — your own account with the maker or a reseller, or Omniscio credits — set in Settings → Accounts → Who pays & who serves.
  • Real-time status dashboard — every session's live state shown at a glance in the sidebar and inbox.
  • Attention-first inbox — sessions needing you surface to an inbox; you respond and move on, no babysitting.
  • Per-session live output stream — watch the agent's output stream into each panel in real time.
  • Keep-alive panel pool — recently-viewed panels stay mounted so switching back is instant.
  • Invisible concurrency pacing — starting sessions, searching and version-control work are spaced out across the whole computer to protect it, never to slow you down.

Session Statuses & Attention-First Design

Every session shows a clear status with its own color, and the ones that need you float to the top with the reason, such as a question or a plan to approve. You get an alert when one needs you.

What's inside (6)
  • Eleven session statuses — running, needs-you, error, stalled, starting, ready, terminating, ended, archived, paused, waiting.
  • Color coding — Running green, Needs-You amber, Error/Stalled red, Waiting ember-orange (capacity park), Primary accent.
  • Pending-action detail — the attention state carries why: question, plan approval, permission, rate-limited, suspended.
  • Needs You floats to top — needs-you sessions sort first; error and stalled ones group in an Interrupted section above the live ones.
  • "Stay on it" during revival — a session you're watching come back to life isn't yanked away.
  • Status-driven notifications — OS + in-app alerts fire on transitions into attention states.

Budget Caps (Soft & Hard)

Set a hard spending limit that stops a session when its cost crosses it, plus an earlier one-time warning. Sessions on a subscription plan are never capped.

What's inside (6)
  • Per-session hard cap — force-kill a session when its cost crosses a limit.
  • Per-session soft warning — a one-time warning well before the hard kill.
  • Per-provider daily cap — optional per-vendor daily spawn+kill cap (off by default).
  • Subscription exemption — subscription sessions are never spend-capped.
  • Runaway-spend anomaly alert — an alert when a metered vendor's daily spend spikes.
  • Fail-open safety — an unreadable ledger never kills a paid session you're running.

Mid-Stream Messaging & Interrupt

Type to a session while it is still working, or stop its current output without ending it. A running timer shows how long the turn has gone, and a cue confirms your stop registered.

What's inside (6)
  • Send while running — type mid-turn; the app delivers into the live process or kills+respawns cleanly, context preserved.
  • Interrupt without killing — stop the current output (Esc or Stop) and keep the session alive for the next instruction.
  • Esc-key interrupt guard — mashing Escape can't fire duplicate interrupts.
  • Provider-aware interrupt — non-Claude sessions route interrupt through their own engine so the turn really stops.
  • Live streaming ticker — a "streaming… Nm Ns" ticker shows the running turn's elapsed time.
  • Interrupt acknowledgement — an "interrupt sent" cue the instant the gesture registers.

Session Lifecycle

Start, pause, snooze, save, archive, close or move sessions as you like. Ended sessions resume when you message them, and sessions running when the app closed pick back up at next launch.

What's inside (14)
  • Create / spawn — start a fresh session in any project.
  • Always resumable — ended sessions resume on the next message.
  • Pause / unpause — kill the running agent and park the session; flip it back when ready.
  • Snooze — hide an attention session until a chosen time; auto-wakes when due.
  • Save (shelve) — flag valuable/completed work into a collapsible "Saved" sidebar section.
  • Archive / unarchive — retire a session (clears draft/snooze, and merges its worktree if the auto-lander is on) or restore it.
  • Close / terminate — stop a session's process and remove its panel.
  • Stop sticks — a session you stop stays stopped; auto-restart, agents and the auto-lander never revive it until you restart or message it.
  • Crash recovery — sessions running when the app died auto-resume on next launch.
  • Genuine-error persistence — a session you saw go red stays red across restart.
  • Runaway-spawner guard — a session that spawned children is never auto-resumed after a crash.
  • Pop-out window restore — popped-out sessions reopen automatically next launch, even after a crash.
  • In-session activity notes — automatic pause/resume/archive markers appear inline in the transcript.
  • Move to project — relocate a session to a different project, with undo.

Session Pinning

Pin the sessions that matter so they stay at the top of their project's list. Pin or unpin from the header or the menu, and the change shows instantly.

What's inside (3)
  • Pin to top — pin a session so it sorts above the list in its project.
  • Pin/unpin toggle — from the header and the overflow menu.
  • Optimistic with rollback — pin flips instantly; a silent failure reverts with a toast.

Draft Persistence (Crash-Safe)

Text you have typed but not sent is saved as you go, so switching sessions or refreshing the page does not lose it. Pasted images and large pasted text are kept too.

What's inside (6)
  • Auto-save drafts — unsent composer text saves continuously and survives session switches.
  • Three-layer durability — held in memory, then saved inside the app, then saved in the app's database — so a hard refresh keeps your text.
  • Pasted images & text-chips persist — pasted images and large pasted-text blocks survive reload.
  • Cross-client draft sync — draft clears echo across desktop + paired mobile without clobbering active typing.
  • Identity-scoped wipe — drafts blanket-clear on account change so text can't leak to the next user.
  • Teardown flush — a graceful close flushes pending drafts losslessly.

Session Cost, Token & Turn Tracking

See what each session costs in dollars, with an approximate marker when the engine bills by usage. Session stats also show turn counts, how much text was exchanged, and how long each turn took.

What's inside (6)
  • Per-session USD cost — accumulated cost tracked per session, shown as a header chip.
  • Every session shows its cost — the dollar chip appears for every session with a known cost, from $0.00 onward, whatever the billing model.
  • Estimated-cost marker — engines that charge by usage show an "≈" prefix, so the number is honest about being an estimate.
  • Turn count & token totals — the number of exchanges and the amount of text sent and received, shown in Session Stats.
  • Turn duration badges — each finished turn shows "took Nm Ns".
  • Cross-compaction duration — compaction dividers show total active time, excluding idle gaps.

Context Window Usage Indicator

A header indicator shows how full a session's context is, and amber warnings appear at 75% and 90% before it fills. You can turn either warning off right from the message.

What's inside (6)
  • Context donut/bar — a header indicator shows real context usage with color thresholds.
  • Details popover — click for a detailed breakdown of context usage.
  • 75% & 90% warnings — persistent amber dividers at "context filling" and "compaction imminent".
  • Warn-once per fill-up — de-duped so a respawn/restart doesn't re-fire.
  • In-message toggle — turn either threshold off without opening Settings.
  • Efficient polling — the authoritative query runs once per turn, gated on visibility + fullness.

Session History & Undo

Press Ctrl+Z to reverse your last session action, such as pause, snooze, archive, move, rename, close or color, several steps back. Undoing a pause or close returns the session to "ended" rather than faking a live one.

What's inside (5)
  • Ctrl+Z undo — reverse your last session action (pause, snooze, archive, move, rename, close, color).
  • Multi-level history — a bounded stack walks back through recent actions.
  • Field-aware arbiter — undoes the action from a text field when pristine, yields to native text-undo once you type.
  • Undo toast (opt-in) — a focus-independent Undo button on a toast.
  • Honest reversal — undo of pause/close returns the row to "ended", never faking a live agent.

Session Naming

Rename any session by editing its title in the header or from the menu. The change shows instantly, and Ctrl+Z restores the old name.

What's inside (4)
  • Inline rename — edit the title in the header.
  • Rename from menu — via the overflow menu.
  • Optimistic with rollback — updates instantly; a failure rolls back with a toast.
  • Rename undo — Ctrl+Z restores the prior name.

Attachments

Send pasted images, PDFs and large blocks of text along with a message. Big pasted text collapses into a chip, and you can preview queued attachments before sending.

What's inside (6)
  • Paste images — sent inline to the agent as image blocks.
  • PDF attachments — delivered as native document content.
  • Text-document attachments — large text docs saved to the workdir and referenced.
  • Pasted-text chips — big text blocks become collapsible chips spliced into the message.
  • Per-session storage — attachments saved to per-session directories.
  • Pending strip + lightbox — preview queued images/chips before sending.

Message Image Carousel

When an AI reply contains three or more images, they appear as one swipeable carousel with a counter instead of a tall stack. One or two images stay inline, and you can open any of them full screen.

What's inside (6)
  • Count badge — a corner counter (like 3 / 12) shows which image of how many.
  • Mobile swipe — swipe through the images without flipping to the next session.
  • Desktop arrows — prev/next buttons, greyed at the ends.
  • Tap to open full-screen — opens the current image in the existing viewer.
  • Inline for 1–2 — a single or pair of images stays stacked as before.
  • Display-only — copy and export keep the original message.

Swipe Navigation (Mobile)

On a phone, swipe left or right to move to the previous or next session. Accidental small drags are ignored, and a downward flick closes large overlays.

What's inside (5)
  • Horizontal session swipe — swipe left/right for previous/next session.
  • Scroll-aware commit — only commits once a scrollable child is pinned to its edge.
  • Velocity + offset thresholds — ignores accidental micro-drags.
  • Prev/next arrows — optional header arrows on mobile.
  • Swipe-to-dismiss overlays — a downward flick closes big mobile overlays.

Send Later (Scheduled Delivery)

Write a reply now and schedule it for later. It reaches the session at the time you chose, waking it if it is paused or archived, with attachments included. If delivery fails after three tries, you get an inbox alert.

What's inside (8)
  • Schedule a response — pick a future time to deliver a composed message (Ctrl+Shift+L).
  • Scheduled attachments — images, PDFs, and text-chips delivered with the message.
  • Status-aware delivery — delivers into a live process (interrupting) or resumes an ended/paused session.
  • Auto-unpause / un-archive — a due message wakes a paused/archived/snoozed target.
  • At-most-once delivery — atomic claim guards against double-delivery.
  • Retry then give up — up to 3 attempts across restarts, then a system message.
  • Visible failure alert — a deduped inbox alert when a scheduled reply can't be delivered.
  • Cancel scheduled — clear a pending scheduled message before it fires.

Session Tags & Tags Library

Opt-in

Label sessions with your own tags or reusable library tags, shown as chips under the title. The Tags Library lets you manage tags and see tagged sessions together. This is an optional feature.

What's inside (6)
  • Free-form tags — ad-hoc tags on a session (max 10, 30 chars).
  • Library tags — reusable named tags applied across sessions.
  • Header tag chips — tags render as a chip strip under the title.
  • Mobile tag collapse — multiple tags collapse to first + "+N" on mobile.
  • Tags Library hub — a hub to manage tags and see tagged sessions cross-session.
  • Tag chip context menu — edit/remove a tag from its chip.

Session Export

Copy a conversation as Markdown or export it to a file as Markdown or PDF, with Word and Google Docs available if you enable them. Exports keep the prose and your messages and drop the tool noise, with a size preview first.

What's inside (7)
  • Copy as Markdown — copy the visible conversation with a token-count toast.
  • Copy since last compaction — copy only from the last compaction divider forward.
  • Export to file — save the transcript as Markdown, Word (opt-in), or PDF.
  • Export to Google Docs — publish the transcript to a new Google Doc (opt-in).
  • Visible-only export — strips tool-call markers and system rows; keeps prose + your messages.
  • Raw thread export — a troubleshooting file with every stored message verbatim, each labelled shown, folded or hidden (unredacted).
  • Size preview — the menu shows words · chars · ~tokens before you export.

Detachable / Pop-Out Windows

Open any session in its own window. The window remembers its position and size, reopens at next launch even after a crash, and keeps receiving that session's live updates.

What's inside (4)
  • Pop out to window — open a session in a standalone window.
  • Geometry memory — popped-out windows remember position/size.
  • Restore on launch — reopen automatically next start (crash-safe).
  • Push routing — detached windows still receive their session's live updates.

Session Controls & Message Filters

One menu holds snooze, pause, send later, copy link, archive, rename and more, and you can promote favorites to one-tap header buttons. You can also filter the transcript by who spoke, or ask a side question that stays out of the main conversation.

What's inside (10)
  • Overflow action menu — snooze, pause, send-later, copy link, archive, rename, and more in one menu.
  • Message filter — filter the transcript by All / Agent / You.
  • Events filter — a day-grouped list of lifecycle/system events for troubleshooting.
  • Aside mode — ask a throwaway side question in a branch, excluded from the main transcript.
  • Copy deep link — copy a deep link to the session.
  • Attach to task — link a session to a task.
  • Session resources popover — a diagnostic view of the session's live process tree.
  • Per-session MCP servers — configure MCP servers for one session.
  • Customize session bar — promote chosen menu actions to one-tap header buttons; right-click a menu action to pin it, or use the Settings checklist.
  • Fixed scroll policy — hardcoded, non-configurable transcript scrolling with jump buttons.

Custom Render Rules

Write your own text-matching rules that turn matching text in messages into colored badges, optionally with a link. A test preview shows the result before you save, and one switch turns all of them off.

What's inside (7)
  • Your own regex → a badge — each rule is a text pattern; wherever it matches a message (agent output or your own), the match appears as an inline badge instead of plain text.
  • Tone & icon — pick a badge color (neutral / accent / success / warning / danger / info) and an optional icon from a small curated set.
  • Label & link templates — build the badge's text and an optional clickable web link from the match, using $0 for the whole match and $1 to $9 for its parts.
  • Live "test it" preview — see the badge and its resolved link on a sample line before you save.
  • Manage the list — add, edit, reorder (first match at each position wins), toggle, and delete rules in Settings → Sessions → Custom Render Rules.
  • Master toggle — one switch disables all custom rendering without deleting your rules.
  • Safe rendering — real UI badges (no raw HTML), http/https-only links, code blocks and existing links skipped, and invalid / zero-width / greedy regexes guarded; zero cost when you have no rules.

Clean Room

Clean Room gives you a blank, vanilla agent with none of your instructions, memory, skills or connected tools, and none of Omniscio's own additions, so you can test and compare against a clean baseline.

What's inside (7)
  • Vanilla session spawn — every session inside Clean Room runs the engine with none of your customizations and none of Omniscio's added layers.
  • Full customization strip — none of your global instruction files, saved memory, skills, project instructions or connected tools reach the session (it uses the engine's own clean mode).
  • Omniscio-layer strip — the awareness note, Plain Speak, conversation markers, the publish/convert/download helpers, and the multiple-choice question instruction are all left out.
  • Hook-free, empty scratch folder — none of the automatic before/after-tool actions fire, and the session starts in a fresh empty folder with no project or files.
  • Real engine kept — it is still Claude Code with its own base identity and native tools, so it is a fair control group, not a raw model or a permission jail.
  • Per-session engine picker — choose the engine per session (Claude by default, plus the Claude-compatible DeepSeek / Kimi / GLM / MiniMax).
  • Built-in sidebar project — appears among the projects like Session Search, not a folder on disk.

Communications & Channels 13

Unified Inbox

See sessions, texts, Gmail and other channels together in one triage view, with tabs and unread counts. Clicking a row opens the right viewer, and reading a text clears it from the inbox.

What's inside (6)
  • All comms in one place — SMS, Gmail, and channels aggregated with sessions.
  • Channel filtering tabs — filter by All / SMS / Gmail (and channels) with unread badges.
  • Native viewer routing — clicking a row opens the correct native viewer.
  • J/K navigation — keyboard move through inbox conversations.
  • Attention badge — a combined session + messaging attention count.
  • Clears as you read — opening an SMS thread removes it from the inbox and clears its unread dot in the same moment; the app's own automatic selections never remove a thread you did not open.

Gmail Integration

Read and manage your Gmail inside Omniscio, next to your code. Reply, forward, search, snooze, undo a send, and get AI reply suggestions and summaries of long threads, with keyboard shortcuts throughout.

What's inside (12)
  • Mail sidebar project — with a live unread-count badge.
  • Full thread view — read conversations inline with rich HTML and expandable recipients; every attachment shows on its message and saves with one click.
  • Compose / reply / forward — send, reply, reply-all, or forward without leaving the app.
  • Gmail search — full Gmail query syntax, paginated.
  • Archive, mark-read, star — optimistic UI with undo.
  • Category tabs — Primary, Social, Promotions, Updates, Forums.
  • Email snooze & undo send — hide a thread until later; a delayed-send cancel window.
  • Multi-select bulk actions — batch archive/read/label.
  • AI reply suggestions + thread summary — one-tap drafts and auto-summaries of long threads.
  • Compose draft preservation — unsent drafts saved on close, restored on reopen.
  • Markdown-to-HTML send + sanitization — sends proper HTML mail; strips malicious inbound HTML.
  • Keyboard-driven — single-key archive/star/reply/nav plus category chords.

SMS (Pushbullet Bridge)

Read and send your phone's text messages from your desktop through Pushbullet, with live incoming messages, notifications, contact photos and picture messages, plus one-tap AI reply suggestions.

What's inside (9)
  • Phone SMS on desktop — a hub bridging Pushbullet's SMS API.
  • Conversation list — threads with previews and unread badges.
  • Send / reply — through the paired device.
  • Real-time incoming sync — a live connection delivers new messages instantly.
  • Archive with auto-unarchive — archived threads resurface on a new message.
  • OS notification per text — a chime + toast that deep-links to the conversation.
  • Wizard setup — enter token → select device → connect.
  • Contact images & MMS — pulls avatars and renders picture messages.
  • AI reply suggestions — one-tap draft replies.

Native SMS (Real SIM, No Cloud)

Send and receive texts from your phone's real number with no cloud service in between. A self-hosted app on your Android phone passes messages to Omniscio, where they appear in the same text inbox.

What's inside (4)
  • Self-hosted Android bridge — uses an open-source local SMS gateway on your phone.
  • Inbound webhook — the phone POSTs each received text to the app (HMAC-verified).
  • Outbound over your SIM — the app tells the phone to send the text.
  • Shared inbox intake — flows into the same SMS UI/notifications as Pushbullet.

Telegram Integration

Use your Telegram account inside Omniscio: sign in with your phone, then read, send, edit, delete and forward messages, search chats and download media. Live sync and AI reply suggestions are included.

What's inside (7)
  • Telegram project — conversations + messages in their own sidebar project.
  • Phone-based auth — send-code → sign-in → optional 2FA; session stored encrypted.
  • Send / edit / delete / forward — full message operations.
  • Real-time + background sync — live events plus periodic catch-up with a watchdog.
  • Mute / archive / snooze / dismiss — per-conversation management.
  • Media download & search — fetch photos/files; search conversations.
  • AI reply suggestions — one-tap drafts.

Slack Integration

Bring Slack direct messages, channels and mentions into Omniscio, and reply in channels and threads. It connects outward from your computer, so you never have to open a public address.

What's inside (5)
  • Socket Mode — a connection Omniscio opens outward, so you never have to expose an address for Slack to call.
  • Monitors DMs, channels, mentions — ingests messages into a Slack channel project.
  • Send + threads — reply into channels/threads with thread mapping.
  • Reconnect with backoff — exponential backoff and quick acks.
  • Wizard setup — enter tokens → pick channels → connect.

Unified Channel System

Every messaging service you connect works the same way, with conversations, unread counts and search combined. If one fails to start, the others still work, and each gets its own sidebar space.

What's inside (6)
  • Channel adapter interface — each connected service plugs in through one small connector and one line that registers it.
  • Channel registry — aggregates conversations, unread totals, and cross-channel search.
  • Composite IDs — addressing so IDs never collide across channels.
  • Fault-tolerant startup — one adapter failing doesn't block the others.
  • Per-channel virtual hubs — an auto-created sidebar space per enabled channel.
  • Capability flags — each connected service declares what it supports: live updates, sending, threads, formatted text and search.

RSS / Atom Feeds

Subscribe to RSS and Atom feeds and read articles inside Omniscio. Duplicates are ignored, you can open the original or archive an article, and an optional daily digest email covers each feed.

What's inside (5)
  • RSS project — each feed entry is its own conversation.
  • Per-feed polling with dedup — periodic refresh that ignores duplicates.
  • Article reader — sanitized HTML body with Open Original + Archive.
  • Feed management UI — add/edit feeds, URL validation, per-feed refresh, status dots.
  • RSS daily digest — a scheduled per-feed digest email.

Generic Webhook Channel

Turn messages from any outside service into inbox items. Omniscio gives each source its own local web address to send to, with a test button to check it works.

What's inside (3)
  • Localhost webhook server — receives structured messages at a separate web address for each source.
  • Webhook project — incoming payloads render as messages.
  • Per-source config — configurable port, URL display + copy, and a test button.

Channel Automations

Set rules that act on incoming messages: auto-respond, label, archive, summarize, forward, notify or start a session. Describe a rule in plain English or start from presets, and rate limits keep any rule from running away.

What's inside (8)
  • Condition + action chain — 1–10 ordered actions per automation, after the spam filter.
  • Condition types — always / a rule (wildcard pattern, keyword or text pattern) / AI (a structured reply, and if the AI fails the message still gets through).
  • Action types — auto-respond, label, archive, whitelist, summarize, forward, notify, spawn a session.
  • Template variables — the sender, message text, channel and subject can be inserted into an action's settings.
  • Natural-language authoring — describe a rule in plain English; a parser builds it.
  • Preset templates — prebuilt single- and multi-action starting points.
  • Rate limiting — per-automation cooldown, concurrency cap, circuit breaker.
  • Run activity log — per-run, per-action results recorded.

Google Calendar

Off by default

See your Google Calendar in month, week or agenda views, get "starting soon" reminders and change notices, add events by typing plain sentences, and ask an AI assistant about your schedule. Off by default.

What's inside (6)
  • Calendar project view — month/week/agenda backed by the Google Calendar API.
  • Channel adapter — events surface in the unified inbox/search.
  • "Starting soon" reminders — a configurable minutes-before alert.
  • Add/changed notices — separately-toggleable notifications on event changes.
  • Quick add — natural-language event creation.
  • Calendar AI chat — an AI assistant over your calendar.

Google Drive

Off by default

Search your Google Drive files from Omniscio's search, import a Google Doc, or publish Markdown to a new Doc. Agent sessions can read your Drive but cannot change it. Off by default.

What's inside (3)
  • Drive channel adapter — read-only search surfaced in unified search.
  • Doc import/publish — import a Google Doc; publish markdown to a Doc with tables.
  • MCP Drive server — exposes Drive to agent sessions (search, list, read, info, quota; read-only).

Google Sheets & Contacts

Off by default

Search your Google Sheets and ask plain-English questions about their data, and get Google Contacts suggested when you address a message. One Google sign-in covers Gmail, Calendar, Drive, Sheets and Contacts. Off by default.

What's inside (5)
  • Sheets channel adapter — read-only search over Sheets.
  • AI Sheets assistant — natural-language queries over sheet data.
  • Contacts service — resolves and ranks Google Contacts for recipient auto-complete.
  • Shared OAuth — one Google sign-in covers Gmail, Calendar, Drive, Sheets and Contacts.
  • Google Workspace MCP — a connector that gives agent sessions access to Google Workspace tools.

Remote, Mobile & Control 9

Web Remote Access

Control Omniscio from your phone's browser or as an installed home-screen app. Pair by scanning a QR code, see and revoke connected devices, and reach it only through your own Tailscale network unless you switch on public access.

What's inside (12)
  • WebSocket + HTTP listener — streams UI state and dispatches actions to remote clients.
  • Mobile-optimized responsive UI — a full touch layout with a bottom tab bar and drill-down.
  • QR code pairing — scan an on-screen QR to connect a phone instantly.
  • 256-bit token auth — a unique access pass for this installation is required for every request, and it is checked in a way that cannot be guessed by timing.
  • Private Tailscale access — by default only your own devices signed in to Tailscale can reach it; public internet access (Tailscale Funnel) is an off-by-default switch with a warning.
  • Connected device management — see and revoke paired devices.
  • Installable PWA — install to the home screen.
  • WebSocket compression + delta batching — 60–80% smaller payloads over slow links.
  • Bootstrap hydration — one handshake frame hydrates the whole remote store.
  • Freeze-aware keepalive — won't drop a healthy phone when the desktop stalls.
  • Security hardening — brute-force limiting, DNS-rebinding defense, same-origin guard, settings redaction.
  • File Peek + messaging over web — view files and use SMS/Telegram from the phone.

Artifact Sharing (Omniscio Shares)

Publish a session, message or selection as a single web page with a link. Protect it with a password, set an expiry, update it in place, revoke it, allow comments, and track views.

What's inside (11)
  • Share Engine — renders a conversation/artifact into one fully-inlined HTML file.
  • Relay-backed publisher — a Cloud Function mints the token and signed upload URLs.
  • Selection / message / session scopes — share a text selection, one message, or a whole session.
  • Publish from CLI — publish from a file path or pasted text (the mobile artifact flow).
  • Password protection + expiry — gate a share behind a password; set an expiry or "never expires".
  • Republish in place — refresh content while keeping the URL.
  • Revoke + delete — take a share offline server-side.
  • Send to channel — deliver a share link out via a messaging channel.
  • Share comments — viewers can comment.
  • View poller + alerts — track view activity.
  • Shares panel — manage published shares in-app.

SSH Remote Execution

Run sessions on a remote server over SSH instead of your own computer. A setup wizard installs keys from a one-time password, new hosts are trusted once, and a changed key is rejected. Test the connection before launching.

What's inside (8)
  • Remote session launch — run a session's process on an SSH-connected server.
  • Password-bootstrap wizard — enters a one-time password, then installs keys for key-based auth.
  • Ed25519 key generation — app-managed keypairs per remote.
  • TOFU host verification — trusts a new host once, rejects a changed key.
  • App-isolated known_hosts — keeps remote-server identity records in Omniscio's own storage instead of your personal SSH folder.
  • Per-remote config + ProxyJump — the server address, connection port, user name, key, starting folder and environment settings, plus connections that pass through one or more intermediate servers.
  • Connection testing — test reachability and Claude availability before launching.
  • Injection-hardened validation — hostnames/usernames reject unsafe characters.

CLI Control Server

Let other tools and scripts control Omniscio through a private connection on your own computer, protected by a token. Six access levels, approval prompts for changes, an activity log and kill switches keep you in control.

What's inside (13)
  • Localhost HTTP server — listens only on your own computer, and can be switched off.
  • Bearer-token auth — a token in the OS vault, auto-delivered for skills.
  • Six levels of access — full trust, in-app, agent, limited connector, cloud and third-party. Limits: an agent-level caller cannot use the full-trust commands or start a paid session without your opt-in; a read-only caller cannot change anything.
  • Deny-by-default paid spawn — the session-spawn route refuses agent tokens unless the owner opts in.
  • Session spawn — start a real session in a project, with options to set the title and choose the agent engine.
  • Spawn pacing + idempotency — a durable queue releases spawns steadily; a request-id de-dupes retries.
  • Provenance headers — trace every action/spawn back to its origin session.
  • Approval-gated actions — many mutations land as inbox "pending" rows until approved.
  • Per-family + per-action approval overrides — turn approval on/off per action family, or auto-approve one exact kind.
  • Read budgets + activity log — sensitive reads throttled; every call audited to a "Recent CLI Activity" card.
  • Capabilities intent-search — map a plain-English goal to a route.
  • Kill switches — per-feature CLI toggles act as panic buttons.
  • Broad route coverage — projects, sessions, tags, recipes, cron, automations, settings, share, bookmarks, scratchpads, SSH, web-access, AHK, messaging, voice, vault, coaching, PM boards, integrations, alerts, diagnostics, backup.

Bookmarks (Personal Launcher)

Save links, folders, files, programs, commands and jumps to sessions or projects in a searchable toolbar menu. Nested folders, drag-to-reorder and Shift+B to bookmark a session make it a quick personal launcher.

What's inside (7)
  • Eight kinds — Folder, URL, Path, Executable, Command, plus Session/Project/Virtual navigation jumps.
  • Toolbar popover — a searchable hierarchical tree.
  • Launch behavior — URLs in the browser, paths in the OS default app, executables detached, commands with a first-run confirm.
  • In-app nav bookmarks — jump straight to a session, project or saved view by its identifier, with live labels and a warning when a link no longer works.
  • Quick-bookmark a session — Shift+B, context menu, or popover, with undo.
  • Nested folders + reorder — up to 5 levels, drag-to-reorder, spring-loaded auto-expand.
  • CLI control + hardening — six commands, and starting a program from a bookmark is refused when the request comes from the command line.

ContextDock Integration

Opt-in

Link outside document bundles and lists to a project so a snapshot is included in every new session's first message. Choose a compression level per document, pin bundles, refresh by hand, and unlink with undo. Opt-in.

What's inside (8)
  • Vendored CLI — starts the ContextDock command-line tool and passes its access key through the environment, never writing it to a log.
  • Link bundles/lists/docs — a snapshot written into the project's docs folder.
  • First-message injection — the snapshot inlined into every new session's first message.
  • Three picker tabs — Bundles, Lists, and full-library search.
  • Compression levels — Original / Key Points / Summary per doc, with running token totals.
  • Bundle pinning + preview — pin bundles; view the rendered markdown.
  • Manual refresh + unlink undo — snapshots don't auto-update; unlink with a re-link undo.
  • Rate-limit governance — one chokepoint paces requests under the per-key cap.

AutoHotkey (AHK) Integration

Manage AutoHotkey text shortcuts as a project with an editor. Omniscio keeps your shortcut file in sync and reloads the script when you save, and an AI text correction panel can turn a fix you typed into a permanent shortcut.

What's inside (6)
  • AHK project — a real linked project with a Monaco editor.
  • Managed hotstrings file — generated from a table, with an atomic write and clobber guard.
  • File watcher + reload-on-save — watches for changes and reloads the running script.
  • AI text-correction block — optional proofread/shorthand keys wired to the CLI.
  • Add as hotstring from anywhere — the AI Text Correction panel saves what you typed and its correction as a permanent hotstring, and reloads your script so it works at once.
  • Script index AI pipeline — a 2-stage extraction turns scripts into a searchable index.

Clipboard History

Read your recent clipboard entries, copy one back, pin or delete entries, or clear the history, all through Omniscio's control connection.

What's inside (3)
  • History list — read recent clipboard entries.
  • Copy back — re-copy a stored entry.
  • Pin / delete / clear — manage the history.

Diagnostics & Developer Experience

See live debug logs inside Settings, export all logs as a ZIP, and send bug or feature reports with diagnostics attached. Omniscio also notices when the app stops responding and keeps your phone connected.

What's inside (6)
  • Live debug log — the most recent 2,000 log lines, streamed into Settings as they happen.
  • Diagnostic bundle — assembles device/version/log context for reports.
  • Log export — a ZIP of all application logs.
  • In-app feedback — bug/feature reports sent with auto-collected diagnostics.
  • Detachable windows — pop a session or a panel into its own window, and each window keeps receiving its own updates.
  • Freeze detection — notices when the app stops responding and keeps your phone connection alive.

AI Features & Coaching 5

AI Manager (Plain Speak)

Plain Speak rewrites each finished agent reply into a short plain-language card you can read at a glance, with a toggle back to the original. You can turn it on per session or pause it everywhere.

What's inside (9)
  • Plain Speak rewrite — rewrites a completed reply into a glance-readable plain-language card.
  • Original view toggle — flip between the plain-language card and the raw message.
  • Delete-only section reviewer — blanks card sections that don't earn their place.
  • Jargon scrub — grammar-safe de-jargoning of the card.
  • Gate-report native card — dev-pipeline gate reports render natively (free), never a paid rewrite.
  • Literal-read skip gates — skips the rewrite on interrupts, rate-limit, and auth/API errors.
  • Per-session enable toggles — Plain Speak opts in per session.
  • Preview + pause-all — dry-run the pipeline; one master switch pauses it app-wide.
  • Decisions audit log — every rewrite persisted with reason, tokens, and cost.

AI Response Suggestions & Snippets

See three suggested next replies for each session, text or email, and send one with Alt+1, 2 or 3. Save frequent replies as snippets, and Omniscio offers to save phrases you keep typing.

What's inside (7)
  • Suggestion chips — 3 auto-generated next-step replies per session (shared across Session/SMS/Email).
  • Prefetch + Alt+1/2/3 send — generated ahead of time; a keyboard shortcut sends the match.
  • Flash-before-send — a brief visual confirmation on activation.
  • Response snippets — save frequently-used replies with optional auto-submit and usage tracking.
  • Quick Reply picker (Zap) — a dropdown of saved quick replies.
  • Quick-reply nudge pill — detects repeated phrases you type and offers to save them.
  • Style profile — learns your writing voice to shape email/SMS suggestions.

AI Session Titles

Sessions get readable names automatically from the conversation, generated on a low-cost model. You can customize the naming instructions, and Omniscio can also draft save messages and change summaries.

What's inside (4)
  • Auto-generated titles — names a session from its conversation content.
  • Configurable prompt — customize the title-generation instructions.
  • Cheap-provider routing — runs on a cheap utility model to keep cost near zero.
  • Commit-message drafts — AI-drafted save messages in the standard short format, plus change summaries.

AI Coaching Platform

Opt-in

An opt-in space for structured self-coaching: pick from interview prompts, save finished interviews as versioned notes, and get a profile and short follow-up sessions built from them. Earlier notes feed into each new interview.

What's inside (10)
  • Coaching hub — a dedicated sidebar space, seeded on enable.
  • Interview library — dozens of seeded interview prompts to start a conversation.
  • Save from transcript — turns a finished interview into a durable first-person artifact.
  • Versioned artifacts — every save is a new version; history never overwritten.
  • Progressive context — prior artifacts auto-fed into each new interview.
  • Core profile — a synthesized who-you-are summary, regenerated only when artifacts change.
  • Coaching snacks — short follow-up sessions generated from your artifacts + profile.
  • Check-in scanner — a periodic heartbeat that can drop a gentle journaling nudge.
  • Notification chime — a once-per-attention chime when a coaching session needs you.
  • Artifact export + embeddings — export artifacts; a semantic index of them.

Summarization & Provider Routing

Long messages are condensed before read-aloud, and email and text threads get AI recaps. Small AI jobs go to the cheapest capable service, falling back to Anthropic if one fails, and you can open the recap after a long chat is compacted.

What's inside (4)
  • TTS summarization — condenses a long message before read-aloud.
  • Compaction summary viewer — an on-demand "Show summary" shows the short recap the engine wrote when it trimmed a long conversation.
  • Email / SMS thread summaries — an AI recap of a conversation.
  • LLM provider routing — one shared service sends each small AI job to the cheapest service that can handle it, falls back to Anthropic without you noticing, stops retrying when a service keeps failing, and records the cost against the feature that used it.

Automation & Scheduling 9

Auto-Run (Away Mode)

Set rules that reply to, retitle, archive or triage sessions that finish while you are away, based on keywords, project, tag or time of day. Loop and spend limits prevent runaway replies, and automatic replies carry a green badge.

What's inside (10)
  • Global auto-response rules — condition-based rules matched against a session's finished output.
  • Four condition types — keyword, project, tag, or time-of-day window (windows wrap past midnight).
  • Six rule actions — reply, retitle, archive, start a new session, raise an inbox note, or triage.
  • Triage action — set title, apply a tag, and/or set inbox color in one shot.
  • Reply from a Quick Reply — pull canned text from a saved snippet.
  • First-match-wins ordering — rules evaluated in display order.
  • Pre-emptive evaluation — matched sessions never flash amber or notify first.
  • Cross-engine support — rules fire for non-Claude sessions too.
  • Loop & spend guards — no-progress loop cap, start-session daily cap, loop-breakers, rate-limit exclusion.
  • Auto badge + provenance — auto-replied turns carry a green "auto" badge linking to the rule.

Recipes (Multi-Step Playbooks)

Save multi-step playbooks you can reuse across projects, or describe one in plain English and let AI draft it. Runs show live progress and cost, honor spend and time limits, can pause for your approval, and resume from where they failed.

What's inside (15)
  • Named multi-step recipes — ordered steps with shared parameters.
  • Global & project-scoped — store recipes everywhere or per-project.
  • Three execution modes — same-session, multi-session, or parallel.
  • Parameter slots — typed parameters with labels, defaults, and required flags.
  • AI-evaluated follow-ups — each step decides to continue, retry, or move on.
  • Pipeline expansion & sub-recipes — a step can fan out into a wave, or call another recipe.
  • Real-time progress + cost — live step status, per-step and cumulative cost.
  • Cost cap + time cap — per-run spend and wall-clock ceilings that abort a runaway.
  • Resume on failure — resume from a checkpoint; completed steps skipped, cost carried.
  • Run control — pause, resume, stop, or inject an operator turn mid-run.
  • In-run approval gates — a step can pause for approve/reject.
  • Execution history + run memory — a saved history of every run, with timing, costs and a summary.
  • AI recipe drafter — describe a recipe in plain English; AI instantiates or synthesizes it.
  • Pattern library — bundled, tested recipe patterns to instantiate from.
  • Approval gate on save — a playbook created from the command line waits as "pending" until you approve it.

Automations Hub

One sidebar hub holds your automation rules and auto-replies. Expand a row to edit it in place, or use the quick-create buttons to start a new one.

What's inside (4)
  • Two-section sidebar — collapsible Rules and Auto-replies sections.
  • Accordion editors — click a row to expand its inline editor.
  • Quick-create buttons — new rule / new auto-reply pre-selecting the category.
  • PII-safe telemetry — category-change and row-expand events with an allow-list.

Recipe Scheduling

Run a saved recipe on a recurring schedule and preview the next run times. Turning a schedule on needs your approval because it spends money, while turning it off applies immediately.

What's inside (4)
  • Cron-style schedules — attach a recurrence to a recipe.
  • Split approval gate — arming is approval-gated (paid); disarming applies immediately.
  • Bounded dispatch + duplicate guards — drains a backlog without a paid burst; no double-fires.
  • Upcoming-runs preview — list the next scheduled fire times.

Cron / Scheduled Jobs

Schedule scripts, recipes, new sessions or workflows in the timezone you pick, using standard timing rules or everyday phrasing. See each run's history, run one now, chain jobs, and let AI diagnose and propose fixes for failing ones.

What's inside (10)
  • Four job types — script, recipe, session (spawn), or workflow.
  • Standard cron expressions — with everyday phrasings turned into a schedule by the command line.
  • Run modes — one-off, limited (max N runs), or recurring.
  • Per-job timezone & encrypted env — schedules run in a timezone you choose, and secret environment values are stored encrypted.
  • Run history + Run Now — per-job run log with output/errors; fire any job immediately.
  • Enable/disable & job chaining — pause a job or trigger another on completion.
  • Approval-gated creation — new jobs queue an inbox approval with a plain-English description.
  • Self-healing — a failing job's error is AI-diagnosed and an auto-fix proposed (per-job toggle).
  • Watchdogs — zombie-run reaper, liveness detector, overdue/dark-scheduler alerts.
  • Retention purge — daily cleanup of old run history.

Scheduled Messages, Drip & Snooze

Set reminders that arrive in your inbox on a repeating schedule, or queue a pile of items to trickle in over time. Snooze hides a session or inbox item until a time you choose, then brings it back.

What's inside (5)
  • Scheduled messages — a subject+markdown note delivered to yourself on a recurrence (no paid spend).
  • Drip feeder — queue a pile of items and trickle them into the inbox on a schedule.
  • Loop drips — a single-item drip repeats forever (e.g. "send me this photo daily at 9am").
  • Snooze — hide a session/inbox item until a chosen time, with auto-return.
  • Idle release scheduler — schedules session release on idle.

Super Prompts (Prompt Library)

Start sessions from a library of ready-made prompts plus your own. Filter by tag, let an AI advisor recommend one, preview it, and pick which project it launches into.

What's inside (9)
  • Prompt catalog — a large curated bundle plus your own prompts.
  • Two-pane picker — a minimal Find/Browse home, then list + live preview.
  • Launch-into target — pick which project the prompt launches into.
  • Tag filtering + "Help Me Choose" — filter by tag; an AI advisor recommends a prompt.
  • Prompt editor — title, summary, description, body, and a stock first response.
  • Stock first response — a pre-written opening shows instantly; the model spawns on your first reply.
  • Tombstones & duplicate — soft-delete/restore user prompts; copy a builtin into an editable one.
  • Remote refresh — polls a remote catalog for new curated prompts.
  • Linkable prompts — deep links open a Run / Copy / Open-in-picker menu.

Coaching Tips

Off by default

Get occasional tips on shortcuts, voice and navigation based on how you use the app. Tips are off by default, with cooldowns and a daily limit so they never become noise, and you can switch categories on or off.

What's inside (5)
  • Master switch, off out of the box — Settings → Coaching turns the whole engine on; nothing is surfaced until you do.
  • Tip catalog — tips triggered by tracked actions/counts across shortcuts, voice, productivity, navigation.
  • Per-tip lifecycle — shown/dismissed/completed/snoozed state per tip.
  • Cooldown + daily cap — a startup delay, per-tip cooldown, and daily ceiling prevent spam.
  • Category toggles — enable/disable coaching by category.

Recurring Codebase Audits & Import

Schedule recurring AI audits of a project's code, write your own audits, or run one on demand with your approval. Each run keeps its findings and history, and you can import existing OpenClaw recipes and schedules.

What's inside (5)
  • Per-repo audit automations — named scheduled audit runs subscribed to a project.
  • Custom audits — author your own audit definitions.
  • Run-now — run an audit on demand (approval-gated paid session).
  • Findings + reports — structured findings and run history per run.
  • OpenClaw port — import existing OpenClaw recipes and schedules into the app.

Git, Code Review & Data 12

Git Worktree Isolation

Each session can work in its own separate copy of the project on its own branch, so parallel sessions do not trample each other. Finished work merges back to your main copy, and unfinished work is never destroyed.

What's inside (8)
  • Per-session worktree — a session works on its own branch in an isolated directory.
  • Three-level enable cascade — per-session → per-project default → app-wide default.
  • Auto dependency copy — copies the project's installed libraries, dependency list and local settings into the separate copy, so it runs straight away.
  • Merge back — Retry Merge moves a finished session's work into your main copy; with the automatic merge on, archiving or stopping the session does it for you.
  • Per-project merge queue — serializes merges so concurrent sessions don't collide.
  • Conflict handling — a conflict raises a "Resolve" action that spawns an AI session.
  • Startup recovery — reconciles orphaned/stale worktrees on restart.
  • Dirty-work protection — teardown never destroys uncommitted work or a live run.

Git Diff Viewer

Review uncommitted changes side by side or in one column, with unchanged stretches folded away and whitespace optionally ignored. Ask for a plain-English explanation of any file's change, or see who wrote each line.

What's inside (12)
  • Monaco diff editor — original vs modified with real syntax highlighting.
  • Unified / side-by-side toggle — switch layouts with the V key.
  • Collapse unchanged regions — long identical runs fold away.
  • Ignore-whitespace / word-wrap toggles — re-fetch with whitespace suppressed; wrap long lines.
  • Adjustable font size & tab width — per-file toolbar controls.
  • Optional minimap — the code minimap on the diff.
  • Inline git blame — per-line author, date, and commit on toggle.
  • Line annotations — attach an ephemeral note to any line.
  • AI change summary — an on-demand plain-English explanation of what a file's diff does.
  • Binary / too-large placeholder — a friendly notice instead of an empty editor when a file cannot be shown as text or is too large to open.
  • New-file synthesis — untracked files render as an all-additions diff.
  • Safety caps — size and timeout limits so a huge diff can't hang the app.

Session-Scoped Diffs (Changes Panel)

See only what an agent changed since it started, or all uncommitted changes, or compare any two saved points. Changes are grouped by project and refresh as the agent writes code.

What's inside (6)
  • Project vs Session mode — all uncommitted changes, or changes since the session's start commit.
  • Commit-range comparison — pick two commits and diff between them.
  • Multi-repo discovery — finds projects inside or next to your main one and groups changes by project.
  • Tree / flat toggle & status filters — group into a folder tree or flat list; filter by change type.
  • Auto-refresh on output — re-checks what has changed as the agent writes code, batched, not on every change.
  • Not-a-repo empty state — a clear message when the folder isn't under git.

Accept / Reject Review Workflow

Approve or discard changes one file or one block at a time, or in bulk, with keyboard shortcuts. A summary bar tracks what you have reviewed, and discarding asks you to confirm.

What's inside (7)
  • Accept / reject file — mark reviewed (Y) or discard via git (X, confirmed).
  • Accept all / reject all — bulk-review remaining files.
  • Per-hunk accept/reject — approve or revert individual change blocks.
  • Review summary bar — reviewed count and bulk actions.
  • Discard all changes — a confirmed working-tree reset.
  • Keyboard-driven review — J/K navigate, Y/X accept/reject, V toggle, O open, R refresh, B blame.
  • Open in external editor — jump the selected file into the system editor.

Git Metadata & Commit/Push

See which files changed, how many lines were added or removed, and which line of work you are on. Write a message and commit your changes, then push the branch, all without a terminal.

What's inside (7)
  • Status badges — Modified/Added/Deleted/Renamed/Copied/Unmerged/Untracked per file.
  • Insertion/deletion counts — per-file added/removed line counts.
  • Repo status bar — which line of work you are on, the latest saved point, and how many files have changed.
  • Sidebar changed-file badge — a live count of uncommitted files per project.
  • Commit box — write a message and stage-all-and-commit (per-repo in multi-repo projects).
  • Push current branch — push with humanized errors.
  • Injection-safe git — every version-control command runs the tool directly, never through a command shell.

Pull Request Review & Merge (GitHub plugin)

Review, approve, request changes on and merge pull requests without leaving Omniscio. This free marketplace plugin also adds issues, a code browser, releases, notifications and build status.

What's inside (5)
  • Review queue — the pull requests waiting on you, in one list.
  • Any repo's pull requests — open a repository's PRs with diffs, per-file "Viewed", comments and review threads.
  • Merge / approve / request changes — act on a PR from the plugin's own panel.
  • Update branch / enable auto-merge — ask GitHub to bring a PR up to date, or turn GitHub's own auto-merge on and off.
  • Issues, code browser, releases, gists, notifications, Actions/CI — the rest of the GitHub surface the plugin adds.

Where's My Work

Off by default

A read-only screen that tells you in plain language what became of your changes, filing each branch as landed, waiting on review, turned down or stranded. It is off until you turn it on.

What's inside (3)
  • Plain-language buckets — every branch of a project filed as Landed, Waiting on review, Turned down, Stranded, Couldn't check or Housekeeping.
  • Read-only — it reads your project's copy of the repository and GitHub; it changes nothing.
  • Count tiles & pull-request links — how many branches sit in each bucket, with a link to each branch's PR on GitHub.

Codebase Analysis (Codebase Stats)

Analyze a project on demand: file and line counts, health flags like leftover to-dos, git activity and hotspots, outdated or vulnerable packages, test coverage, and a scan for exposed passwords and keys. Results are cached, so reopening is instant.

What's inside (11)
  • File-walk stats — total files, lines of code, bytes, per-extension breakdown.
  • Health tab — TODO/FIXME count, any-type usage, large-file flags, secret findings.
  • Git tab & insights — commits, contributors, churn hotspots, knowledge silos, stale files, active branches.
  • Deps tab — vulnerability and outdated-package counts from an audit.
  • Coverage tab — detects and runs the project's test suite (for the common test tools it supports) and reads how much of the code the tests cover.
  • Test-to-source ratio — classifies test vs source files and computes the ratio.
  • Secret scanning — a scan for patterns that look like passwords and access keys, with a filter for false alarms and an ignore list for each project.
  • Costs tab — the project cost rollup.
  • Cache by commit — results are remembered for the current saved version, so reopening is instant.
  • Fix-in-session — spawn an agent to address findings.
  • Background pre-warming — pre-computes each project's stats under load gates so the modal opens instantly.

Statistics View

Understand how you use Omniscio, with trends over time, spend by feature, credit usage per account, shortcut use, personal records and a per-project comparison.

What's inside (6)
  • Overview & Trends — top-line usage summary and trends over time.
  • Spend & Feature Usage — cost breakdown, per-feature spend, which features you use.
  • Hotkey usage & efficiency — how often each shortcut fires and where you mouse instead.
  • Usage tab — API credit usage, per-account bars, heatmap, daily projection.
  • Records tab — personal records with a day-sessions drill-down.
  • Project stats table — per-project usage comparison.

Data Export / Import

Back up all your data to a ZIP and restore it later. Restore previews what it will change first, saves a copy of your current data before overwriting anything, and leaves secrets out of the backup.

What's inside (8)
  • Full backup export — ZIP of all data, sanitized settings, recipes, and attachments (secrets excluded).
  • Two-phase import — preview (validate, show counts/warnings) then execute.
  • Pre-import backup — saves a copy of your current data and settings before anything is overwritten.
  • Full-replace transaction — the import runs as one atomic transaction.
  • Zip-bomb / row-count guards — caps entry count, uncompressed size, and per-table rows.
  • Schema/platform warnings — warns you when a backup comes from an older version of the app or from a different operating system.
  • Column-whitelist safety — only real columns are inserted (blocks crafted-backup injection).
  • Settings-only export/import — a small settings file that can be merged into what you already have, with any secrets removed.

Local & Cloud Backups

Automatic backups run on startup, on a timer or on demand, keep several copies, and check for corruption at launch. You can also mirror an encrypted copy to a cloud folder, or email an encrypted setup backup to your own Gmail.

What's inside (9)
  • Triggered backups — on startup, on a timer, and on demand.
  • Retention ring + bit-rot floor — keeps the newest N and ≥2 physical copies so one bad sector can't wipe all.
  • Corruption detection + restore — a boot integrity check offers restore-from-backup.
  • Pre-migration & pre-update snapshots — separate sets of saved copies taken before a data upgrade and before an app update.
  • Setup Backup to Gmail — emails an encrypted setup backup to your own Gmail on a schedule.
  • Backup Mirror — writes an AES-256-GCM-encrypted bundle to a chosen (cloud) folder, auto-syncing.
  • Cloud-folder auto-detection — suggests detected Dropbox/OneDrive folders as one-click targets.
  • Mirror restore + fresh-machine migration — replace-all or merge from a mirror archive or file.
  • Staleness / failure alerts — alerts after repeated failures or when backups go stale.

Data Retention & Auto-Cleanup

Choose how long ended, archived or paused sessions are kept, from 1 to 365 days, and old data is deleted automatically. Active sessions are never auto-deleted, and lowering the window warns you first.

What's inside (6)
  • Session data retention — auto-delete old ended/archived/paused sessions (1–365 days).
  • Reduce-retention confirm — lowering the window warns before it deletes.
  • Scratchpad auto-delete — opt-in purge of untouched Quick Capture notes.
  • Communications content erasure — opt-in permanent erase of old message content after a grace period.
  • Vault trash sweep — a deleted Vault (KMS) note stays recoverable by hand from the vault's .trash folder only until it passes the same window, then it is permanently deleted.
  • Active-data protection — active sessions are never auto-deleted. Approval rows are cleared once they pass the retention window.

Operations & Reliability 7

Auto-Lander

When you mark finished work ready, Auto-Lander merges it into your main copy on your own computer, one branch at a time, and never uploads anything. If a merge keeps getting sent back, it reopens the session to fix it.

What's inside (8)
  • In-process land engine — re-applies the finished work's saved changes and moves the main copy forward in one all-or-nothing step.
  • Several can land in one move — when more than one branch in a repo is ready, the ones that fit land together in a single update (on by default), each with its own merge commit and its own landed note; turn batching off to go back to one branch per move.
  • Comes on with the Dev Pipeline — enabling the Dev Pipeline arms it and watches every repository the pipeline covers; your own explicit on/off and repo list always win, and any project can be set to watch-only so it reports what it would merge without changing anything.
  • Never writes to a remote — it never uploads or changes your online copy.
  • Retries before giving up — if a merge is sent back several times, it pauses new merges briefly and reopens the session that wrote the change to bring it up to date.
  • Auto-spawn remediation — when it gives up, it starts a temporary session to bring the work up to date and mark it ready again. On by default, up to 4 at a time; these are billable sessions.
  • Give-up alert self-clears — the "merge by hand" card withdraws once the branch later lands.
  • Land-event history — records landed + conflict outcomes.

Resources Diagnostic Panel

See a live view of the app's own processes with CPU and memory graphs to find what is using your computer. You can close a process, with a check that stops you closing the wrong one, and it costs nothing when closed.

What's inside (4)
  • Process discovery — walks the app's process tree.
  • Per-process CPU/memory — sampled with inline sparklines.
  • Close a process — with a check so a stale list can never close the wrong thing.
  • Zero cost when closed — timers clear when the last viewer leaves.

API Cost Tracker & Per-Feature Caps

Track what each AI feature spends and set daily caps per feature, such as the vault, mind map, coaching and writer. A tracking failure never breaks the feature, and a brief outage will not block a paid one.

What's inside (4)
  • Per-model cost logging — records each API response's cost, priced from a single source of truth.
  • Per-feature daily caps — a shared gate sums today's spend per feature (KMS, mind-map, coaching, council, writer).
  • Fail-open caps — a transient DB outage reads as allowed so a paid feature isn't starved.
  • Non-fatal — silently swallows DB failures so tracking never breaks a feature.

Git Guardrails

Agent sessions are stopped from committing or pushing to the main branch, or stashing over unfinished work. On by default, you can exempt a repo or pause it, and it still works in autonomous modes.

What's inside (4)
  • Bundled PreToolUse hook — auto-wired into each session via a session-private settings file.
  • Protected-branch & destructive-op blocks — stops an agent committing/pushing to master or stashing over other WIP.
  • Per-repo exclusion + time-boxed pause — exempt a repo or pause the guard.
  • Fires in autonomous mode — a hook, not a permission card, so it survives bypass modes.

Developer Guardrails

Off by default

Extend the same git safety checks to every Claude Code session on your computer, not only those Omniscio starts. It works on Windows, macOS and Linux, supports pause and per-repo exemptions, and turning it off removes it cleanly. Off by default.

What's inside (4)
  • Machine-wide — installs one guard into your shared Claude settings, so every Claude Code session on the computer is protected, not just the ones Omniscio starts.
  • Same blocks, reused engine — saving into or uploading to your main copy, editing while on it, and a destructive undo of unfinished work — using the same checks as Git Guardrails.
  • Cross-platform — works on Windows, macOS, and Linux.
  • Shared pause + exclusion, clean revert — the same time-boxed pause and per-repo exclusion as Git Guardrails; turning it off removes it cleanly.

Secret Paste Guard

Off by default

When you paste an API key or password, Omniscio offers to protect it. The AI sees only a placeholder, and the real value is wiped from your saved history, search, drafts and exports. Off by default.

What's inside (4)
  • Paste detection — spots an API key / token / password pasted into the composer and offers to protect it.
  • Handle substitution (Claude-binary engines) — stores the real value on your computer behind a harmless placeholder; the AI only ever sees the placeholder, and the real value is swapped in only at the moment the action runs.
  • History scrub (every engine) — the real value is wiped from your local data, search results, drafts, exports, the on-screen chat and, once the session ends, the saved conversation.
  • Fail-safe — on any error the literal handle stays and the action fails harmlessly; never a leak, never a blocked command.

Toolchain, Provenance & Platform

Covers setup and safety extras: install and update tools, trace where actions came from, switch workspaces, check web apps an agent builds, optionally encrypt your local database, and clean up old unviewed shares.

What's inside (6)
  • Toolchain management — install, check (concurrency-gated), and update the external CLIs the app drives.
  • Session provenance — trace inbox actions and spawns back to the originating session ("Generated by" / "Spawned by").
  • Self-serve workspaces — create and switch between the workspaces (orgs) you belong to.
  • Web-app verify (Obscura) — a tool that functionally checks a web app the agent builds (load, elements, no console errors).
  • Database encryption — encrypt the app's local database on disk (off by default); the key lives in your computer's secure key store, and a recovery code is your backup way in.
  • Smart Share Reaper — old, unviewed "never-expires" shares get a Keep/Delete prompt with a grace expiry.

Voice & Audio 8

Voice Conversation & Report-Back

Off by default

Have a spoken back-and-forth: hear replies read back, ask questions about the open session, or ask a running agent and hear its answer. Off by default, with separate daily spending limits and a saved history.

What's inside (6)
  • Report Back — the AI's spoken-prose reply after a voice command is read back.
  • Layer 2 conversational assistant — up to ~12 turns with on-screen context awareness.
  • Layer 3 session voice — ask a spoken question about the currently open session.
  • Layer 4 ask the live agent — queue a spoken question to a running agent and hear its answer.
  • Per-layer daily spend caps — independent USD ceilings so voice never runs away on cost.
  • Voice history recording — every exchange is saved for later review.

FlowVoice — OS-Wide Dictation

Dictate into any app on your computer: hold a global hotkey, speak, and the cleaned-up text is typed at your cursor. Audio is saved as you speak and failed transcriptions are retried, so a dictation is not lost.

What's inside (7)
  • Type at the OS cursor — cleaned transcript pasted wherever your cursor is, in any application.
  • Global hold + toggle hotkeys — system-wide hold-to-talk or press-to-toggle keys.
  • Floating idle pill (HUD) — a click-to-dictate pill, hidden when idle by default; right-click it to keep it on screen or open FlowVoice settings.
  • Auto-submit into the app — when the app is frontmost, optionally send the dictated draft.
  • Pre-warmed recorder — a hidden capture window cuts first-dictation latency.
  • Auto health check — self-tests the speech server and mic permission at startup.
  • Never loses a dictation — audio is saved as you speak; a failed transcription is retried automatically and kept for a one-click retry.

Voice Commands

Hold a hotkey and speak to create, send, pause, snooze or archive sessions, switch views and more, with over 50 built-in actions. You can chain commands and define your own trigger phrases.

What's inside (11)
  • Push-to-talk hotkey — Alt+V or a global hotkey starts listening; a mic button too.
  • 3-layer intent parser — a quick pattern match (under a millisecond), then an on-device meaning match (about 20 ms), then an AI model as a fallback (about 300 ms).
  • 50+ built-in actions — create/send/interrupt/pause/snooze/archive sessions, navigate views, toggle theme, control TTS, Gmail, PM.
  • Command chaining — "open settings and then check voice status" runs commands sequentially.
  • Custom voice commands — define your own trigger phrases mapped to actions (up to 50).
  • Three dictation modes — single, continuous, buffered.
  • Automatic silence detection — stops recording after your configured pause.
  • Three STT providers — Deepgram Nova-3, ElevenLabs Scribe v2, Groq Whisper.
  • Voice response confirmation — optional spoken reply: short, conversational, or off.
  • Live app context — the parser knows the current view/sessions so "archive that" resolves.
  • Daily STT spend cap — a USD ceiling across paid speech-to-text engines.

Text-to-Speech (Read Aloud)

Hear an agent's replies read aloud with a play button, or automatically when you open a session that needs you. Code and tables are skipped, long replies can be summarized, and you choose the voice, speed and a daily spend limit.

What's inside (10)
  • Manual play button — three-state button reads the last AI message.
  • Auto-read mode — optionally auto-speak when you first open a "Needs You" session.
  • Three TTS providers — Fish Audio, Grok (xAI), or ElevenLabs.
  • 50+ voices per provider — with preview and custom voice IDs.
  • Chunked streaming playback — a tiny first chunk for fast time-to-first-syllable.
  • Smart text processing — strips markdown, code, tool markers, and tables so you hear prose.
  • Summarization modes — verbatim, summarize, or auto before speaking.
  • Speed & volume control — adjustable playback speed and volume.
  • Disk LRU cache — caches synthesized audio to avoid re-billing.
  • Daily read-aloud spend cap — a USD ceiling across the speech path.

Omni Session Briefing

Press a button or hotkey, or say "brief me", for a spoken 75 to 120 word catch-up on what a session did while you were away, covering accomplishments, decisions and blockers. Briefings are reused until the session changes.

What's inside (4)
  • On-demand voice briefing — a plain-English recap of accomplishments/decisions/blockers.
  • Four triggers — header speaker button, Ctrl+Shift+J hotkey, "brief me" voice command, auto-on-open.
  • Configurable model + prompt — choose the model and override the briefing prompt.
  • Smart caching — reuses a briefing until new messages, a model change, or a prompt change.

PM Voice Commands

Create, move, update, read and list items on your project boards just by speaking.

What's inside (1)
  • PM voice actions — create item, move item, status update, read item, list items by voice.

Wake Word Detection

Off by default

Say "Hey Omniscio" and start talking, no keypress needed. It is off by default, you can adjust its sensitivity, and it can listen only while the app is focused. A test button lets you try it.

What's inside (6)
  • Dual engine — a free built-in wake-word engine (included, no key needed).
  • Bundled wake words — "Hey Omniscio" (default), plus "Computer".
  • Action mode — a wake word runs the spoken text as a command or types it as dictation.
  • Adjustable sensitivity — a fire threshold you can tune.
  • Focus-only mode + auto-pause — listens only while focused; yields to active dictation.
  • Test button — try the wake word with an auto-stop.

Per-Microphone Voice Tuning

Omniscio remembers the calibrated silence and speech levels for each microphone you use, and lets you set how long a pause ends a voice command.

What's inside (2)
  • Per-device thresholds — saves calibrated silence-floor and speech-threshold per mic.
  • Silence timeout — a configurable pause before a command auto-stops.

Media & Screen Capture 4

Record for Agent

Off by default

Record your screen while you talk and mark key moments by hotkey, note, voice or a drawn box. Then send the take to an agent that reviews it and works through the task list with you. It builds on the Screen Recorder.

What's inside (4)
  • Talk while you record — narrate what you are showing instead of typing it out.
  • Mark the moments — flag the parts that matter by hotkey, typed note, voice or a drawn box.
  • Send to agent — the agent reviews the take, shows cropped screenshots to confirm it understood, and works through the task list with you.
  • It is told not to file anything — the agent is instructed to create no tickets or notes; the conversation is the whole output.

Screen Recorder

Off by default

Record your screen, a single window or a region, with optional webcam and audio. Trim and annotate the take, add captions and AI summaries, and share it as a link or publish to Vimeo. Off until you turn it on.

What's inside (6)
  • Quick Record & presets — start with your saved setup, or open a new recording to choose sources and layout.
  • Screen, window or region — capture any display, a single window, or a drawn region, with optional webcam and audio.
  • Review, trim & edit — check the take, cut it down, and annotate it before you share.
  • Share a link or publish to Vimeo — send the finished recording as a link or publish it to Vimeo.
  • Captions & AI summaries — caption a recording and have the AI summarize what happened in it.
  • Library, recovered takes & storage — browse your recordings, finish a recovered take after a crash, import an existing file, and clear what you no longer need.

Screenshots / Snip Tool

Off by default

Press a hotkey to draw a region and snip it. Each capture is saved as a PNG, copied to your clipboard and confirmed with a sound, and you can annotate it and browse everything in a library. Off until you turn it on.

What's inside (3)
  • Snip a region — a global hotkey opens a region selector and captures what you draw.
  • Saved, copied and confirmed — each snip is saved as a PNG, copied to the clipboard, and confirmed with a shutter sound and a toast.
  • Annotate & browse — annotate a capture and browse everything you have snipped in the Screenshots library.

Video Player

Every video and audio clip in Omniscio plays in one player, in the app and on shared links. It offers looping, keyboard shortcuts, full screen and a layout that fits phones.

What's inside (4)
  • Everywhere a video appears — in the app, on a shared link, on the embed page other sites use, and for films drawn live by code.
  • Repeat & slim audio layout — loop a clip, and play audio-only shares in a compact layout.
  • Keyboard shortcuts & full screen — control playback from the keyboard, or go full screen.
  • Phones — the player adapts to a phone screen.

Knowledge, Skills & More 9

The Vault (KMS)

A private knowledge base your agents can search, read, write and cite. Capture notes once and every session can use them. It is off by default, and you turn it on in Settings.

What's inside (3)
  • Notes & vault — capture structured knowledge the app and your agents can search and cite.
  • Agent read/write — sessions query and update the vault via the knowledge tools, metered by per-feature caps.
  • UI says "Vault" — the persisted store keeps its internal names; the interface calls it Vault / The Vault.

Mind Map

Lay out ideas as a tree on a canvas, import an outline or a spreadsheet, and export a map as a picture or text. Your agents can read your maps and build new ones for you.

What's inside (4)
  • Mind Map canvas — a keyboard+mouse idea tree with auto-layout, collapse/expand, styling.
  • Mind Map library + export — saved maps, export to JSON/PNG/Mermaid, mobile controls.
  • Import from outlines and spreadsheets — build a map from a Markdown outline, a Mermaid mind map, a CSV or an Excel file.
  • Agents can build maps — an agent can read, create and edit your maps, and turn an idea into a task.

Skills

Browse, turn on and turn off the skills your agents can use, whether global, per project or from plugins. A companion view shows which skills add the most overhead so you can prune them.

What's inside (3)
  • Skills panel — browse, enable, and disable your global, project, and plugin skills from a dedicated surface.
  • Skill overhead insight — a companion view flags which skills add the most token overhead so you can prune.
  • Bundled vs your skills — distinguishes skills Omniscio ships from ones you or a plugin added.

Ask Omniscio

Ask Omniscio how to do things in the app. A read-only tutor answers without touching your projects, and when you ask it to build something it points you to start a real session instead.

What's inside (2)
  • Read-only tutor — answers "how do I…" questions about the app without touching your projects.
  • Hand-off, not do — asked to build something, it points you to spawning a real session instead of thrashing.

MCP Servers

Manage the tool servers your agents can use. Add, enable or disable them globally, and choose which ones a project or a single session gets. Connectors that need a password fetch it only when used.

What's inside (3)
  • Global server list — add, enable, and disable MCP servers centrally.
  • Per-project & per-session overrides — choose which servers a project or a single session gets.
  • Secret-safe — a connector that needs a password fetches it only when it is used, and never stores it in readable settings.

Email Cleanup

Declutter your inbox by sender with an AI-guided walkthrough that lets you keep, archive or unsubscribe in bulk. A simpler flat sender list is available if you prefer it.

What's inside (2)
  • Sender walkthrough — an AI-guided pass over your senders to keep, archive, or unsubscribe in bulk.
  • Classic layout option — a simpler flat sender list for those who prefer it.

Email Summarizer

Tap once to get the key points of a long email or thread.

What's inside (1)
  • Summarize a message or thread — condense a long email into its key points.

PR Merge Queue

Off by default

Watch your open pull requests in one live list, with optional one-line AI summaries and checks and merge-readiness tracked in one place. Off by default, and summaries send PR details to your AI provider.

What's inside (3)
  • Open-PR queue — a live list of your pull requests.
  • One-line AI summaries — a plain-English sentence on each PR pill; off by default, and when it is on the PR title, description and changed-file list are sent to your configured AI provider.
  • Babysit to merge — track checks and merge-readiness from one place.

Music Recommendations

Ask for tailored music recommendations without leaving Omniscio.

What's inside (1)
  • Recommendation helper — get music suggestions via a bundled helper skill.

Notifications & Focus 7

Notifications (OS + In-App)

Get desktop alerts when a session needs you, replies automatically or loses sign-in, set to always, only when backgrounded, or never. Pick sounds per type, and click a notification to land in the right session.

What's inside (10)
  • OS notifications — desktop alerts on needs-you, auto-responded, auth-expired.
  • 3-way behavior — always / only-when-backgrounded / never.
  • In-app toasts — 19 categories, each with its own on/off switch except Errors and Warnings, which always show.
  • Notification sounds — 8 built-ins + system sounds + custom uploads, per-type assignment.
  • Pre-decoded audio + per-minute cap — sounds replay smoothly; at most one chime per type per minute.
  • Quiet recovery sounds — "restored/resolved" notices skip the alarm chime.
  • Click-to-focus — clicking a toast restores the window and deep-links to the session.
  • Auth-expired alert — a silent OS notice when a token fails to refresh.
  • Auto-focus on needs-you — optionally bring the window forward.
  • Text-to-speech read-out — optionally speak the alert.

Silence, Mute & Post-Send Navigation

Silence all notifications for a while, mute noisy projects, or turn off texts and calendar reminders on their own. You also choose where Omniscio takes you after you send a reply.

What's inside (5)
  • Silence mode — mute all notifications globally or until a set time.
  • Per-project mute — silence chosen noisy projects.
  • Per-channel toggles — separate on/off for incoming SMS and calendar reminders.
  • Off-dashboard alert — a "Go to Session" toast and nav badge when you're elsewhere.
  • Post-send navigation — stay / next-in-project / next-in-inbox / clear panel, configured separately for inbox vs project.

Daily Weather Report

An optional evening forecast card in your inbox with tonight, tomorrow and a 3-day outlook. It needs no account or key, archives itself if you do not open it, and is skipped if the app was closed.

What's inside (7)
  • One card a day — tonight, tomorrow (high/low, conditions, rain chance, wind, sunrise/sunset) and a 3-day outlook, posted at your chosen delivery time.
  • Free and keyless — forecast from Open-Meteo with no account, no key and no AI; only the place name you type and its coordinates leave your computer.
  • Self-tidying — an unopened card archives itself at your chosen time; one you opened (desktop or phone) stays.
  • Never stale — if the app was closed through the whole window, that day is skipped rather than posted late.
  • Your units — Fahrenheit with mph, or Celsius with km/h.
  • Send a test report — a Settings button that shows the place it found, or a plain reason it couldn't.
  • Mutable — the "Daily weather report" card type can be turned off like any other inbox card.

Mobile & Web Push

Your phone or browser still gets alerted when a session needs you, hits an error or ends, even in the background. A privacy option strips the message text and keeps only the link.

What's inside (5)
  • Mobile FCM push — paired phones get Firebase push on needs-you / error / ended.
  • Web push — PWA/browser push from a real per-device subscription.
  • Content-free privacy mode — optionally strip message text, keeping only deep-link IDs.
  • Invalid-token pruning — dead device tokens are pruned server-side.
  • Broken-phone watchdog — an opt-in alert if a phone connects but never reports a load.

Focus Mode (Batch Alerts)

Batch noisy alerts so you are interrupted once instead of once per item, triggered by a count, a time or both. Errors and sign-in problems always come through, and chosen sessions can bypass the batching.

What's inside (9)
  • Batch gate — needs-you, SMS, digest, and approval items queue instead of each firing.
  • Rule triple — fire on a count threshold, a time threshold, or both.
  • Toolbar bell pill — off / armed / tripped states, pinnable.
  • Whitelist bypass — chosen sessions always alert individually.
  • Pierce states always fire — errors/auth/rate-limit are never silenced.
  • Inbox-hide overlay — the armed state visually quiets sidebar dots, badges, and counts.
  • Click-and-hold peek — temporarily reveal hidden items without ending the cycle.
  • Auto re-arm — returns to quiet once the inbox drains.
  • Pomodoro integration — optionally auto-enables during focus blocks, off during breaks.

Daily Digest

Get a once-a-day AI recap across sessions, texts, Gmail, calendar, Telegram, Slack, feeds and board activity at a time you choose. Ask follow-up questions, hide sections or projects, and a daily spend cap applies.

What's inside (8)
  • AI summary via Haiku — a cheap Claude-generated recap with a daily $ cap.
  • 9 configurable sources — sessions, SMS, Gmail, Calendar, Telegram, Slack, RSS, PM events, PM feed.
  • Custom schedule — a user-set hour and minute.
  • 7-day catch-up — backfills recent history on first run.
  • Follow-up Q&A — ask questions about the digest after it's generated.
  • Per-alert dismissal + permanent suppressions — dismiss items; permanently hide recurring alerts.
  • Per-section toggles + per-project exclusions — hide whole sections or leave projects out.
  • Category hotkeys — act on the digest when its viewer is active.

Weekly Summary & Meeting Digest

Get a Monday-morning weekly recap with AI coaching suggestions, plus an optional daily or weekly meeting recap. Each one arrives once per period.

What's inside (4)
  • Weekly summary — a Monday-morning recap with AI coaching suggestions.
  • No-op without a key — quietly does nothing for Claude accounts signed in without an API key (and costs nothing).
  • Meeting digest schedule — an opt-in daily/weekly "catch me up" meeting recap.
  • Claim-before-spawn — a once-per-period key prevents double-firing across restarts.

Accounts, Themes & Interface 11

Accounts & Authentication

Sign in with your Claude account or an Anthropic API key, and see real-time 5-hour and 7-day usage. Rate-limited sessions resume when the limit resets. Pick a model and thinking level per session, or another engine.

What's inside (9)
  • Claude login — sign in with your own Claude account, or use the one Claude Code already has.
  • API key accounts — add an Anthropic API key, encrypted at rest.
  • Usage dashboard — real-time 5-hour + 7-day credit usage per account with stale warnings.
  • Context transfer on restart — sessions that can't resume get a compacted briefing instead of losing history.
  • Rate-limit / capacity recovery — rate-limited sessions resume on their own when the limit resets.
  • Model picker — the current Claude lineup plus legacy models, per session.
  • Reasoning-effort control — per-session thinking level: Auto / Low / Medium / High / Max.
  • Non-Claude provider picker — Codex, Gemini, DeepSeek, Kimi, GLM, MiniMax, Cursor, Grok/GPT, Pi and more, as the engine behind a session.
  • Hardware-swap hardening — detects dead-decrypt credentials and self-heals on re-auth.

Visual Themes

Choose from 14 built-in visual themes in dark or light, or build your own in Theme Studio. Themes apply instantly with no restart, and you can adjust sidebar side, text size and layout presets.

What's inside (11)
  • 14 built-in skins — Glassmorphism, Linear, Aurora, Neon, Spotify, Luxury, Vercel, Liquid Glass, Aurora Glass, and more.
  • Dark / Light / System — each skin has dark and light palettes.
  • Live preview — themes apply with no restart.
  • Accent color system — each theme drives buttons, links, and active indicators.
  • Custom .theme.json themes — author themes with ~50 CSS variables; import, open folder, delete.
  • AI-assisted theme guide — a built-in guide teaches the AI to create a theme file.
  • Theme Studio — build, live-preview, save, edit and export a custom theme in the app (accent, background tone, status colours, fonts, corners, every colour key); starts from the current look.
  • CSS-injection-hardened — theme values are validated so a shared file can't break out.
  • Sidebar position + text size — left/right sidebars; separate desktop and mobile text size.
  • Chat depth & motion dials — message-shadow depth and a motion/polish elevation dial.
  • Layout Mods — presets for the Hubs sidebar (Compact Rail, Labeled Rail) and the session list (Calm List), each tunable, with a Safe Mode that restores standard layouts.

App Shell & Health Banners

A frosted title bar gives you an inbox shortcut and a count of sessions needing you, plus clear banners when you are offline, the app seems frozen, or you started in Safe Mode.

What's inside (9)
  • Glass drag bar — a frameless frosted title bar; the whole bar is a window drag region.
  • App icon → inbox & attention badge — the favicon jumps to the inbox; an accent count of needs-you sessions.
  • Animated logo — the orb swirls in the title bar, Quick Launch, the loading card and the Windows downloader while in use; right-click it to turn it off.
  • Custom caption buttons — minimize/maximize/close on Windows; native traffic lights on macOS.
  • Standalone window title bars — for detached windows.
  • Offline / reconnecting / connection-lost banners — network state, gated so blips don't flash.
  • App-frozen banner — "app may be frozen — waiting" when the main loop stalls; auto-clears.
  • Safe Mode banner — shown when the app booted in Safe Mode.
  • Credential / backup / extensions nudges — first-run offers to add a key, import a backup, or install extensions.

Keyboard Shortcuts & Keybindings

Rebind any shortcut, give an action several combos, use two-key sequences, and get warned about conflicts. A one-handed preset puts everything on the left side, and global hotkeys work from any app.

What's inside (9)
  • Rebind any action — customizable in Settings via inline capture.
  • Multiple combos per action — an action can hold several bindings.
  • Conflict detection — flags a combo bound to multiple actions, scoped per area.
  • Chord bindings — two-key "X > Y" sequences.
  • OS-reserved guard — rejects binding reserved combos.
  • One-handed preset — a one-click left-hand-only layout, reversible.
  • Global hotkeys — bring-to-front, Omni briefing, Quick Launch, voice push-to-talk.
  • Global-hotkey conflict report — reconciles what actually registered with the OS.
  • CLI-instant changes — shortcut changes take effect immediately when made from the command line.

Onboarding & Setup

A guided first run walks you through language, how your data is handled, choosing and connecting your AI, and installing essential tools. Take an interactive demo on sample data, and rerun setup anytime.

What's inside (9)
  • Guided first-run — 7 steps (8 on macOS): Language and look → Tell us about you → How your data is handled → Choose your AI → Connect your AI → Add an API key (optional) → Install the essentials → Grant permissions.
  • Cinematic intro — full-bleed intro slides with a fading overlay.
  • Theme gallery step — pick a skin during setup.
  • Project step auto-launch — creating the first project auto-launches its first session.
  • Fire-and-forget toolchain install — the setup slide installs recommended tools in the background.
  • Post-onboarding install check — re-checks and toasts if any tool failed.
  • Auto-start demo tour — a 34-step interactive demo on injected sample data (no DB writes).
  • Re-runnable — re-launch the wizard anytime from Settings.
  • Cascade onboarding — a parallelism-cascade first-run redesign subsystem.

Toolchain Manager

Detect and one-click install about 40 command-line tools, from AI agents to git and cloud tools, all from Settings → Connected Tools. Recommended ones install on first run, and an inbox alert offers Update now when a tool goes out of date.

What's inside (8)
  • Curated tool catalog — ~40 tools across AI agents, git, cloud, containers, runtimes, browsers, media, security.
  • First-run recommended sweep — a default subset auto-installs; heavier tools are opt-in.
  • Auto-detect installed tools — probes binaries and shows green/amber status.
  • Just-in-time install — some tools install on demand when a flow needs them.
  • Install provenance — a consent screen shows each tool's source.
  • Retry / update per tool — re-run install or update from Settings.
  • Update alerts for Claude Code and Codex — an inbox card with a one-click Update now when either agent tool is out of date; the update runs in a terminal on your computer.
  • Update alerts for your other tools — the same card and one-click update for the other recommended tools (Git, GitHub's command-line tool, the package managers pnpm and Bun, OpenCode and the rest, with a download page for the hand-installed ones), with its own switch.

App Tours & Coaching

Twelve guided tours highlight real parts of the screen, chain into each other, and offer themselves the first time you use a feature. A 34-step demo uses sample projects and sessions so nothing real changes.

What's inside (6)
  • 12 standard tours — Welcome, Core Workflow, Recipes, Gmail, SMS, Automations, Voice, Settings, and more.
  • Tour chaining — each tour's last step suggests the next.
  • Spotlight + overlay steps — darkens the screen and highlights a real UI element.
  • Rich step blocks — text, bullets, tips, prerequisites, try-it, and keyboard-shortcut blocks.
  • Contextual auto-offers — feature tours offer themselves on first use.
  • 34-step interactive demo — injects fake projects/sessions into the real dashboard.

File Preview Renderer

Preview Markdown, SVG, HTML, Mermaid diagrams and LaTeX math right in the viewer, with a toggle to the raw source. HTML previews run in a locked-down frame with no scripts, forms or network access.

What's inside (6)
  • Markdown preview — GFM with syntax highlighting.
  • SVG preview — sanitized to strip escape hatches.
  • HTML preview — in a fully-sandboxed iframe (no JS, forms, popups, or network).
  • Mermaid diagrams — async render with a red error card on failure.
  • LaTeX math — KaTeX display mode, sanitized output.
  • Raw / Preview toggle — defaults to Preview; resets on file change.

Settings System

Search every setting by keyword and jump straight to it. Settings are organized into clearly named rooms and hub pages, with a Setup Assistant to rerun onboarding, the demo or the tours.

What's inside (5)
  • Full-text settings search — per-section indexes with keywords/synonyms; deep-link to any setting.
  • "Rooms" layout — reorganized, better-named settings groups (shipped as default).
  • Settings hubs — grouped hub pages: Keyboard Shortcuts, Email, Inbox, Automations.
  • Setup Assistant — re-run onboarding, run the demo, launch tours.
  • CLI-driven settings — settings patchable over the control server (with approval gating).

Localization

Pilot

Use Omniscio in 34 languages, including Chinese, Japanese, Korean, Hindi, Arabic and many European languages. English is the default and fills in any text that is not yet translated.

What's inside (4)
  • Language picker — only languages past a coverage threshold appear.
  • Fallback to English — any untranslated string falls back.
  • 34 languages — European, Chinese, Japanese, Korean, Hindi, Arabic/Urdu/Persian (RTL), and eight Philippine languages.
  • Offered by default — every language ships in the picker with no reveal step; English stays the default, and first-run OS detection never auto-switches you to a non-English language.

Tooltips System

Hover over or focus on a control to see a tooltip that matches your theme, with keyboard shortcuts shown as key caps. Tooltips are skipped on touch screens, where hovering is not possible.

What's inside (5)
  • Global native-title interceptor — styles every plain title= app-wide.
  • Rich tooltips — portal-mounted, hover-delayed + focus-triggered, optional multiline/interactive.
  • Hotkey key-caps — a hotkey control renders its key as a cap in the tooltip.
  • Theme-customizable — tooltip colors driven by CSS vars.
  • Touch-safe — suppresses hover tooltips where hover isn't supported.