Omniscio

Performance settings

Settings reference for how much work the app does behind the scenes and how it shares the computer, framed around one question: when the app feels slow, what is worth changing. Nothing here changes what sessions produce, recommended switches are on by default, and Lite mode, low power mode and showing only user and agent messages are named as the first three to try.

On this page

These settings control how much work Omniscio does behind the scenes and how it shares your computer with everything else. Most of them exist to answer one question: when the app starts feeling slow, what is worth changing?

Two rules before you dive in:

  • Nothing here changes what your sessions produce. Every switch on this page affects only how Omniscio draws itself and how it schedules work — never the answers your agents give.
  • Start with the recommended ones. Anything labelled recommended is on by default because it measurably helps. The rest are opt-in experiments or Windows-specific tuning for particular machines.

If the app feels slow right now, the three worth trying first are Lite mode, Low power mode and Show only your messages and the agent's replies.


Performance monitor

The background watch that fills the Performance Monitor panel and raises the cards that warn you when this machine is struggling. It runs on a timer, reads Omniscio's own logs and ledgers, and keeps a bounded copy of their most recent lines so each reading is cheap apart from the first.

Auto (the default) keeps it on for a computer with 13 GB of RAM or more and off below that, because on a small machine the memory it retains is memory a Claude session could be using. Always on and Always off override that judgement. Turning it off reads nothing and keeps nothing: the Performance Monitor panel and the status readout say plainly that the monitor is off and offer the way back on, rather than showing an empty or zeroed page. The change takes effect immediately — no restart.

Accepted values: auto / always on / always off. Auto by default.

Lite mode (optimize for a less powerful computer)

One switch that makes Omniscio lighter on an older or slower computer. Turning it on enables Low Power Mode, holds new sessions back when memory is low, reclaims memory from idle sessions on Windows, staggers how sessions load, and stops keeping extra chats pre-built in the background. Turn it off to go straight back to the settings you had before. Anything to do with startup takes effect the next time you open Omniscio.

Accepted values: on / off. Off by default.


Keep my computer smooth under load (recommended)

When you have a lot of sessions running at once, Omniscio eases off its own background monitoring so your computer stays responsive. It does not change anything your sessions produce — only how hard Omniscio works behind the scenes. Turn it off for the older, always-on monitoring.

Accepted values: on / off. On by default.


Speed up agent commands (skip a safety check that cannot apply)

Skips a slow security check for agent commands that could not possibly trigger it, which makes each command noticeably cheaper. Anything involving git or your master branch still gets the full check, completely unchanged. Omniscio installs and manages the hook for you and keeps a backup, so you can turn this off again at any time. On computers that do not have that heavy check installed, it does nothing at all.

Accepted values: on / off. Off by default.


Run agent hooks in a resident host

Every agent tool call runs a few small safety and housekeeping checks. With this on, Omniscio keeps one long-lived helper process running them, so each call starts one tiny native program instead of a full Node runtime — hundreds of fewer process starts a minute on a busy machine, which is what keeps the app smooth when several sessions are working at once. Turning it off restores the old one-process-per-hook behaviour at the next session start; nothing about what your sessions do changes either way. Windows only for now — other systems keep the per-call behaviour regardless.

Accepted values: on / off. On by default.


Run background jobs in one shared process

Omniscio runs scheduled background jobs on its own — health checks, clean-ups, watchers. With this on, they all run inside one long-lived helper process, so a job no longer starts a whole new program every time it runs — hundreds fewer program starts an hour. A job that gets stuck is stopped at its time limit without holding up the others, and everything the helper started ends when Omniscio closes. Turning it off runs each job in a program of its own again from its next run; which jobs run, and when, stays exactly the same.

Accepted values: on / off. On by default.


GPU acceleration

Uses your graphics card to draw the app. Leave this on unless you are seeing graphics glitches or the app will not start. Turned off, drawing falls back to the processor and the app will feel noticeably slower.

Accepted values: on / off. On by default.


Low power mode

Turns off the visual extras — background blur, heavy animation and decorative shadows — so the app draws more smoothly on a laptop or a computer with built-in graphics. It takes effect straight away; no restart needed.

Accepted values: on / off. Off by default.


Fast session switching

Makes clicking between sessions feel snappier by not re-drawing the panels you are not switching to. It changes nothing about what your sessions do, and reverts instantly if you turn it off.

Accepted values: on / off. On by default.


Cheaper live updates when many sessions run

Each live update a busy session sends wakes only its own panel instead of nudging every open session. Worth trying if you often run many sessions at once and the app feels busy. It re-wires instantly with no restart, and never changes what your sessions do.

Accepted values: on / off. Off by default.


Smooth streaming output (recommended)

Paints fast-streaming text about 30 times a second instead of on every single token. Long answers look smoother, and the rest of the app stays responsive while several sessions stream at once. Turning it off paints every token the moment it arrives — more processor work, and nothing is more correct for it.

Accepted values: on / off. On by default.


How often background sessions refresh

How often text from sessions you are not looking at gets repainted, in milliseconds. A higher number means less background work when many sessions stream at once. The session you are actually viewing always stays smooth, and a background session catches up as soon as you switch to it. Only applies while smooth streaming output is on.

Accepted values: 100 – 5000 milliseconds. Default 500.


Show only your messages and the agent's replies

Hides the step-by-step tool work and folds each turn into a collapsed "N actions" pill you can open whenever you want the detail. This is the single biggest speed-up for busy sessions. Turn it off for the older view that shows every intermediate step as it happens.

Accepted values: on / off. On by default.


Keep recently viewed sessions instant

Keeps the sessions you have looked at recently fully built in memory — the way a browser keeps background tabs ready — so switching back to one is instant instead of a rebuild. A built-in limit caps how many are held so memory stays bounded, and only sessions that are not actively streaming are kept. Trades some memory for speed.

Accepted values: on / off. Off by default.


Keep The Vault loaded for instant switching

Once you have opened The Vault, Omniscio keeps the editor loaded in the background so coming back to it is an instant flip instead of rebuilding it every time. Only one editor is held, and only after you first open The Vault. Desktop only.

Accepted values: on / off. On by default.


Keep recently opened panels loaded

Keeps the panels you have opened — AI Coaching, Calendar, Drive, Sheets, Supermail, Team Chat and the Browser (in its full-browser mode, so your tabs keep their pages) — loaded in the background, so switching back into one is instant instead of rebuilding and re-fetching it. Each panel is only held after its first open. Desktop only. (The Browser had its own "Keep the Browser loaded in the background" switch; it is retired, and the Browser follows this one.)

Accepted values: on / off. On by default.


Keep Tasks loaded for instant switching

Once you have opened the Tasks panel, Omniscio keeps it loaded in the background so coming back to it is an instant flip instead of rebuilding the list every time. Desktop only.

Accepted values: on / off. On by default. This applies to everyone on this computer.


Show checkboxes on tasks

Shows a checkbox at the start of every task. Turn it off for a cleaner list with no checkboxes. You can still finish a task from the keyboard (press x or e), by middle-clicking the row, or from the row's menu.

Accepted values: on / off. On by default. This applies to everyone on this computer.


Show the Tasks mode label

Puts a small label at the end of the task you are on for a few seconds after you land on it or change mode, then it steps aside, so you know what your next key will do. When single letters act as shortcuts it reads "Shortcuts on · Space to type" (Space starts typing in the task; Enter adds a new task below) in the same color as the row's outline; while you are typing into a task it reads "Typing · Esc for shortcuts" in green. The outline colors are unchanged. It is also in Tasks → Customize as Show mode label. Desktop only (a phone has no keyboard shortcuts to name).

Accepted values: on / off. On by default. This applies to everyone on this computer.


Checkboxes select tasks instead of finishing them

Makes task checkboxes work like an email inbox: ticking a box selects the task rather than completing it, so a stray click can never clear a task by accident. A bar appears as soon as anything is ticked, with Done and Dropped on it. Holding Ctrl or Shift always selects, whichever way this is set.

Accepted values: on / off. Off by default. This applies to everyone on this computer.


Finish tasks without the confirmation step

Removes the "are you sure?" prompt when you finish or drop tasks, so a batch clears in one click instead of two. Undo still appears every time, and finished tasks move to Archived rather than being deleted, so a mistake is always recoverable. Deleting a selection of tasks, or every task in a project, always asks first, whatever this is set to. Clearing a task's text and clicking away deletes that task without asking, along with its notes, links and attached files; press Ctrl/Cmd+Z to bring it back before you restart the app.

Accepted values: on / off. Off by default. This applies to everyone on this computer.


Remove finished tasks instantly

Removes a task from the list the moment you check it off. With this off, a finished task stays crossed out for a short pause and then folds away. The task still moves to Archived, and Undo (Ctrl/Cmd+Z or the toast's Undo button) brings it back either way. Also in Tasks → Customize → Editing.

Accepted values: on / off. Off by default. This applies to everyone on this computer.


Where new tasks are added

Choose where a task you add with the Quick Add row appears in the list. Top puts new tasks above the others; Bottom adds them to the end.

Accepted values: Top / Bottom. Default: Top. This applies to everyone on this computer.


Tasks with no priority show as

When a task has neither importance nor urgency set, Tasks cannot tell which of the four groups it belongs in. Not sorted yet (the default) leaves it out of the groups — its chip says "Not sorted yet" — until you give it a priority. You can instead file every such task under Do-first, Plan, Delegate or Later. A group you pick yourself on a task is never changed by this.

Accepted values: Not sorted yet / Do-first / Plan / Delegate / Later. Default: Not sorted yet. This applies to everyone on this computer.


Compact task rows

Tightens the spacing between task rows so more of them fit on screen. Applies both to the All Hubs view and to each Hub's task list.

Accepted values: on / off. Off by default. This applies to everyone on this computer.


Hide completed tasks

Hides tasks you have finished wherever they still appear, mainly the Done section of the Today view. Most finished tasks leave the list on their own when you complete them, so this only affects the few that stay behind.

Accepted values: on / off. Off by default. This applies to everyone on this computer.


Keep trickles running while Tasks is hidden

When you turn Tasks off, its background work pauses, including trickles — the scheduled releases that send a task to your inbox. That hold means a task you were waiting to be reminded about stays quiet until Tasks comes back. Turn this on to keep trickles running while Tasks is hidden, so they still send tasks to your inbox and file them as usual. Off by default. Find it in Settings under Tasks (Tasks display), or search Settings for "trickles". This applies to everyone on this computer.


Pre-build inbox sessions

Builds your most recent inbox (needs-you) sessions in the background so switching into them is instant. A built-in limit keeps the app fast even when the inbox is long; older ones take about half a second to open. Turn it off to do no pre-building at all.

Accepted values: on / off. On by default.


Keep chat responsive under heavy load

When many sessions are open, Omniscio stops the ones you cannot see from doing work every time another session sends a message. Scrolling stays smooth and the chat always lands in the right place, however many sessions are running. Turn it off to build every hidden session in full, as before.

Accepted values: on / off. On by default.


Pre-load new sessions

Keeps one blank session ready in each Hub so that starting a new one with Ctrl+T is instant. Turn it off and new sessions start on demand — slightly slower, but lighter on your computer.

Accepted values: on / off. On by default.


Stagger session loading at startup

Spreads out the building of background session panels after the app starts or reloads, instead of building them all at once, which can freeze the window for a few seconds on launch. The session you are looking at always loads first and immediately; the rest follow within a few seconds.

Accepted values: on / off. Off by default.


Reclaim RAM from idle sessions (Windows only)

Periodically asks Windows to release the memory held by Claude sessions that have been sitting idle for at least this many minutes. The sessions are not closed and nothing is lost — the memory is simply handed back and reloads in about a tenth of a second the next time the session is used. Set to 0 to switch this off.

Accepted values: 0 – 1440 minutes (0 = off). Default 0 (off).


Release idle sessions to reclaim more memory

Once a session has finished its turn and been waiting on you for this many minutes, Omniscio fully releases its background engine — reclaiming all of the memory it was holding, roughly 250–450 MB for each session, rather than just trimming it. Your conversation stays on screen and is reloaded in the background the moment you send your next message, which makes that first reply slightly slower. A session that is waiting on your answer to a question or a plan keeps its engine. Set to 0 to switch this off. Works on every platform.

Accepted values: 0 – 1440 minutes (0 = off). Default 15.


Reclaim memory automatically when it runs low

When your computer's free memory drops and stays low, Omniscio tidies up the memory its own idle sessions are holding. It never interrupts a session that is mid-reply, and it only ever touches Omniscio's own sessions. No effect on macOS or Linux.

Accepted values: on / off. On by default.


When to reclaim memory

The trigger point for the tidy-up above: once free memory stays below this share of your total, Omniscio starts reclaiming. A higher number means it acts sooner and more often; a lower number means it only steps in under real pressure.

Accepted values: 1 – 90 percent of total memory. Default 15.


Cap runaway processes in a single session (Windows only)

Puts a firm ceiling on how many programs one session can run at once, so a single misbehaving agent — a runaway loop, an over-parallel command — cannot flood your computer and freeze it. The limit is generous and sits far above anything a normal session reaches, so it only ever stops something genuinely out of control. Nothing already running is ever killed; new programs simply wait until some finish.

Accepted values: on / off. On by default. Windows only.


Cap combined CPU use when many sessions run (Windows only)

Puts a ceiling on how much processor power all Omniscio Claude sessions together may use — sessions, subagents, test runs and builds included — once your computer is busy. A single session you are waiting on can still use the whole machine; the ceiling only applies when something else wants the processor. Omniscio also runs sessions at below-normal priority so they give way to your own apps.

Accepted values: on / off. Off by default. Windows only.


Maximum combined CPU use

The ceiling used by the setting above, as a share of your computer's total processor power. A lower number is friendlier to your other apps but slower for heavy batch work.

Accepted values: 25 – 90 percent. Default 50.


Never go above the CPU ceiling, even on an idle computer

By default the ceiling is soft: it only applies when other apps want the processor, so a single session you are waiting on can still use the whole machine. Turn this on to make it a hard limit that applies all the time — a stronger guarantee, but a lone session will be slower.

Accepted values: on / off. Off by default. Windows only.


Give Omniscio's own window priority (Windows only)

Runs Omniscio's own window above normal priority while sessions run below it, so the app — and other apps you are using, like your browser — stay responsive when many sessions are saturating the computer.

Accepted values: on / off. Off by default. Windows only.


Keep Omniscio's database in memory (Windows only)

Holds Omniscio's database in fast memory so Windows cannot push it out to disk and then have to read it back from a busy drive — which is what causes the occasional whole-app freeze during heavy multi-session work. It sizes itself to your computer, keeps within a safe limit so it cannot crowd out your other apps, and switches itself off on computers with little memory. Only Omniscio's own database is held, never your sessions.

Accepted values: on / off. On by default. Windows only.


Serve the database from private memory (Windows only)

Serves Omniscio's database from a block of memory Windows cannot take back, instead of reading it from the file on disk. Under heavy disk load Windows can evict a file-based database, and the app freezes while it re-reads it; private memory cannot be taken back that way, so those freezes stop. Fully reversible — turn it off and restart to go back. Takes effect the next time you start Omniscio.

Accepted values: on / off. Off by default. Windows only.


Run the database on a background thread

Runs Omniscio's database reads on a background thread instead of the one that draws the window, so a slow disk cannot freeze the interface mid-query.

This was long labelled experimental because an earlier version made multi-session use slower — database reads queued behind each other. The August 2026 rework of this worker cleared the failure that warning was about, so it no longer describes this build. It is on by default. Machines with less than 13 GB of memory stay on the old path automatically, because the off-thread helpers hold their own large mapping of the database and that is exactly where the old version hurt.

Switching it on or off takes effect immediately, with no restart.

Accepted values: on / off. On by default.


Let sessions give way to your own apps (recommended)

Runs every Claude session — and everything it starts, including searches, git, builds, tests and subagents — at below-normal priority, so it steps aside for the Omniscio window and your other apps when the computer is busy. A session you are waiting on by itself still uses the full machine; it only yields when something else needs the processor. This is the gentler, always-safe alternative to a hard CPU cap.

Accepted values: on / off. On by default. Windows and macOS.


Let sessions give way on the disk too (recommended)

The disk side of the setting above. Sessions and everything they start run at low disk priority and below-normal memory priority, so when Omniscio needs to read from disk — or pull its own memory back in — it goes first. This is what keeps typing and clicking responsive while many sessions are hammering the drive. Sessions still run at full speed whenever Omniscio is idle. Windows only.

Accepted values: on / off. On by default. Windows only.


Pause all testing

Stops any new test, typecheck, lint or build run from starting anywhere on this computer, so background testing stops piling up. Runs already under way finish normally — nothing is killed and no paid cloud run is thrown away. This is the switch to reach for when the machine feels bogged down by agent testing, because pausing your sessions does not stop it: a test run keeps going after the session that started it has stopped.

It stays on until you turn it off. A pause made here never times out, restarting Omniscio does not clear it, and an agent cannot lift it: node scripts/testing-pause.mjs clear and DELETE /gate/testing-pause both refuse it and say that only the owner can turn it off in Settings, and a timed pause an agent starts does not replace it. While the switch is on, Omniscio checks about once a minute that the pause is really in place and puts it back if anything removed it. Every pause, resume, refused resume and restore is written to a small log with the session that asked — node scripts/testing-pause.mjs history prints it — so a pause that goes missing can be traced to whoever removed it.

You can flip this switch from the command line too. With the app's own full-trust CLI key, PATCH /settings/pauseAllTesting with {"value": true} turns this switch on and writes exactly the same no-expiry pause the switch itself writes, and {"value": false} turns it off and clears it. No approval click is needed, and every flip lands in the log above with the calling session named, so a pause set this way is traceable the same as one set by hand. An agent's own scoped, per-session token can never do this: it is refused and the attempt is recorded, because the pause you set here is also the standing permission to hand-tag untested work, and that stays yours to give.

You will never be asked about it. This pause is also your standing answer to the one question it used to cause. When testing is paused, work that cannot get a test result no longer stops and asks you how to proceed: your agents finish the work and tag the branch anyway, and the tag itself carries testing paused by owner - untested so anyone reading it later knows the change shipped without a test run. A timed brake an agent started does not carry that permission — only the pause you set here does — so an agent cannot give itself permission to skip testing by pausing the box.

Your agents can pull a timed brake. With no Settings change and no approval step, an agent (or anyone driving the local control surface) can pause testing directly — POST /gate/testing-pause — for a window of its choosing, up to a 24-hour ceiling. That road deliberately does not move this switch, so a pause an agent started leaves the switch reading off while testing really is held. Ask GET /gate/testing-pause to see whether a pause is live, who started it and when it clears, and DELETE /gate/testing-pause to clear a timed one early. A run held back by a pause finishes with no verdict — never a pass and never a fail — and says who paused it, since when, and when it resumes (for the pause made here: that it stays paused until you turn the switch off).

Plain test runs hold too, not just the gated ones. A test started any way at all is refused while the pause is on: a gated run, a bare npx vitest, a Playwright run, an Electron window a test opens, the repository's own test wrappers, and each standalone package's own test lane. Every one of them reads the same pause and refuses before it starts anything — before a window opens and before a missing package is installed. The refusal names the pauser, says when it lifts, and exits 86, a code of its own so an agent can tell "the box is paused" from "your change broke a test".

Background jobs hold too. While the pause is on, the master test-baseline refresh on this computer skips its fire and the ready check skips its guard run, and each says that testing is paused. A skipped baseline fire is recorded as a paused fire, not a failure, so a pause never raises a "baseline producer is failing" alarm; the baseline simply stops refreshing until testing resumes.

Accepted values: on / off. Off by default.


Batch your agents' find commands (recommended)

Rewrites the file-searching commands your agents run so they work in efficient batches instead of starting one program per file. A single runaway search can otherwise start tens of thousands of programs and freeze your computer. It is also faster. Only turn it off if a specific command genuinely needs the old behavior. Applies to your next new session.

Accepted values: on / off. On by default.


Separate database helper for big background reads

Starts one more background database helper that runs Omniscio's big, non-urgent database reads — the crew roster and the scheduled-jobs list — on their own read-only connection, so those scans cannot queue in front of the reads your agents are waiting on. The helper costs about 120 MB of memory, so it is off by default and those reads share the main background helper. Turn it on if you run many agents at once. It cannot write anything. Takes full effect after a restart.

Accepted values: on / off. Off by default.


Speed up merge batches

While "merge all ready branches" runs, that job is given above-normal priority and your other sessions are briefly dropped to below-normal, so the batch finishes sooner on a busy computer. Your other sessions keep running — they just give way. It reverts on its own when the merge ends, after a 30-minute safety timeout, or as soon as you turn it off.

Accepted values: on / off. Off by default.


Spacing between sessions when many restart at once

When several sessions come back together — after an app restart, after recovering from a rate limit, or all at once from the Bulk session manager — this is how far apart Omniscio spaces their starts, so a big batch does not hit your computer all at the same time. When memory runs tight (85% or more) or cannot be read, it also keeps only a handful of them working at once, so a large restart cannot exhaust the machine; while memory is comfortable the spacing alone paces the batch. While the app is still opening it may start them sooner, but only once your computer has room. Sessions you start or restart yourself, one at a time, are never delayed. Set to 0 to fall back to the built-in spacing.

Treat this as a ceiling, not a fixed gap. When Omniscio can tell the interface is keeping up — no frozen moments, no lag you would feel, memory comfortable — it brings sessions back closer together than the number you set, down to about five seconds apart, so a big restart finishes sooner instead of trickling for the best part of an hour. The moment anything does slow your computer down, including the restart itself, it goes straight back to your number.

Sessions running on a cloud machine are not held to this. Their work happens on their own machine, so they come back on their own faster lane and never wait behind sessions restarting on this computer.

Accepted values: 0 – 30 seconds. Default 1.5.


Seconds between background starts during severe lag

How cautiously background agent work proceeds while Omniscio detects severe interface lag. A higher number gives stronger protection for your computer; a lower number lets agents move faster. Normal operation, and anything you start yourself, is never delayed. Leave this alone unless you have a reason to change it — by default Omniscio works out the right value for your machine.

Accepted values: seconds. Left unset by default, so Omniscio derives the right value for this computer.


Auto-lander

The master switch for the auto-lander — the background service that merges each branch you have marked ready-to-merge into your main branch automatically, on this computer only. It never pushes anywhere, it only ever moves things forward (so nothing can be lost), and it never touches a branch somebody is resolving by hand. Turning the Dev Pipeline panel on arms it for the repositories that panel already covers, so you usually do not have to switch it on by hand; your own choice here always wins, in both directions. Left off, nothing lands on its own and your finished branches wait for you. The same switch also lives in the Dev Pipeline panel's Setup tab.

Accepted values: on / off. Follows the Dev Pipeline until you choose otherwise.


Announce when a worktree is cleaned up

When you archive a session that already has a pull request, its worktree is cleaned up automatically. This shows a brief notification when that happens. Turn it off for fully silent cleanup.

Accepted values: on / off. On by default.


Session-based worktree cleanup

An extra, opt-in worktree cleanup that runs alongside the worktree reaper (the switch that removes finished work areas, described in Worktree reaper): instead of judging a folder by whether its work landed, it reasons about your ledger of worktrees and the sessions that used them, and retires only a folder it can show nothing still needs. It is cross-platform and off by default; turn it on to use it, and the two limits below cap what it may spend.

Accepted values: on / off. Off by default.


How many cleanup sessions may run per day

The most paid cleanup sessions the session-based cleanup above may start in one day, a whole number from 1 to 50. It is on top of your global daily spending cap, so whichever limit is reached first decides. Once the day's count is used up, no further session starts until tomorrow.

Accepted values: a whole number, 1–50. Default 5.


Daily spend cap for cleanup sessions

A dollar ceiling on what the session-based cleanup's sessions may spend in one day, on top of your global daily budget. Once today's spend on these sessions reaches it, no more start. Set it to 0 to remove this ceiling (your global cap still applies).

Accepted values: dollars, 0–100. Default 2.


Push sessions onto efficiency cores when the CPU is busy (Windows, hybrid CPUs)

On computers with a mix of fast and efficient processor cores (Intel 12th-generation and newer, including Core Ultra), this keeps Claude sessions on the efficient cores while overall processor use is above about 85%, and lets them back onto every core once it drops below about 60%. Your sessions keep working while the fast cores stay free for Omniscio and your browser. It does nothing on computers that do not have that mix of cores, so it is safe to leave on.

Accepted values: on / off. Off by default. Windows, hybrid CPUs only.


Ease memory pressure by paging busy sessions to disk (Windows only)

When your computer is low on memory, Omniscio tells busy sessions — and the tests they run — to keep less in fast memory and put the rest onto the disk. Sessions keep running; they simply slow down until memory frees up. It starts above roughly 85% memory use and lifts again below roughly 70%. It never affects Omniscio itself, and never cancels, blocks or kills anything.

Accepted values: on / off. Off by default. Windows only.


Decide which agents start first when several are waiting

When more agent sessions are created at once than your computer can comfortably run, the app starts them in the order that best fits the machine rather than all at once, and lets the rest in as room frees up. A single session you open by hand is never held behind this ordering. Turn it off and every new session starts the moment it is created, in the order it was created.

Accepted values: on / off. On by default.


Hold new sessions back when memory is low

When your computer is low on memory, this pauses new sessions that arrive in a burst — automatically created bug and feature sessions, recipe runs, mass restarts — until memory frees up, so a flood of sessions cannot push the machine into a freeze. A single session you open by hand is never delayed, and anything held starts within a few seconds. Sessions resuming after an app restart are always paced this way regardless of this setting. Works on every platform.

Accepted values: on / off. Off by default.


The memory level that triggers holding sessions back

The point at which the setting above starts holding burst sessions back, as a share of your computer's total memory in use. Lower is more cautious and holds sooner; higher means it only steps in when memory is nearly full.

Accepted values: 50 – 95 percent. Default 85.


Wait between freshly created sessions

How long to wait between starting brand-new sessions that an agent or automation creates in a burst — a script opening many sessions in a row, for example. This stops rapid automated starts from piling up all at once. Sessions you open yourself are never affected. Set to 0 to start them immediately.

If your computer is very busy, a waiting session can be held back briefly to protect it, but never more than 30 seconds past its turn, so at the default setting the queue still starts one every 30 seconds.

Accepted values: 0 – 300 seconds. Default 30.


Stop sessions loading tools they do not use

Every session normally starts all the tool servers listed in your global Claude configuration, including ones it never touches — the Playwright browser tool alone can take about 95 MB each. With many sessions open, those idle servers add up to gigabytes of wasted memory and can slow the whole computer down. With this on, each session loads only the tools Omniscio actually set up for it, so the waste cannot build up, and sessions start a little faster. Your Omniscio tools — memory, The Vault, Google and any custom servers — keep working exactly as before. Applies to Claude sessions; Codex, Gemini and Cursor are unaffected.

Accepted values: on / off. On by default.


Keep the computer awake while sessions are running

Stops your computer going to sleep while one or more sessions are running, so long jobs keep working when you step away. The screen can still sleep to save power — only system sleep is blocked — and normal sleep returns the moment every session has finished. Works on Windows and macOS; on Linux it depends on your desktop environment.

Accepted values: on / off. On by default.


Run the active session in its own process (experimental)

Draws the session you are viewing in its own background process inside the main window, so it stays responsive while the rest of the app is busy. It takes effect the next time you click a session.

Accepted values: on / off. Off by default.