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.
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.
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.
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.
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.
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.
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.
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.
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 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.