AI, accounts & models settings
Settings reference for the AI models used in sessions, the built-in AI-powered features such as coaching, suggestions and digests, and how that configuration is shared with other artificial-intelligence tools on the machine.
On this page
- Default session model
- Default provider
- Default thinking level
- Model vendor routing
- AI Council sidebar launcher
- Bake-Off model comparison
- AI reply suggestions
- AI suggestion model
- AI Coaching — conversation style
- AI Coaching — daily message style
- AI Coaching — CLI access
- AI Coaching — ask for feedback after sessions
- AI Coaching — invitations from your coach
- Daily Digest
- Daily Digest model
- Weekly Summary
- Weekly Security Digest
- Weekly Summary model
- Sync to Other AI Tools
- Provider Config Sync — auto-sync
- Provider Config Sync — instructions
- Provider Config Sync — skills
- Provider Config Sync — copy skills back in
- Sync agent instructions across tools
Controls for the AI models Omniscio uses in your sessions, built-in AI-powered features (coaching, suggestions, digests), and how your configuration is shared with other AI tools on your machine.
Default session model
The AI model Omniscio picks when you start a new session and have not chosen a model manually. You can override this per-session from the session header. Leave it empty to use the provider's own default. If you switch providers (see Default provider), you will usually want to update this to a model that provider offers. Find the full list of supported models in Settings → Sessions → Models.
Default provider
Which AI provider backs new sessions when no per-session choice has been made. Omniscio supports Claude (Anthropic), GPT models, open-weight models via proxy providers, and more. Changing this also steers which models appear at the top of the model picker. Your existing sessions are not affected — only new ones started after the change. Related: Default session model, Proxy models.
Default thinking level
How deeply the model "thinks" before it replies. Options, from least to most reasoning: auto (the model decides), low, medium, high, xhigh, max. Higher levels produce more thorough answers but take longer and cost more per turn — at Max an open-ended first message can spend several minutes thinking before its first step. A fresh install starts on High, and unless you have set this yourself Omniscio keeps the level in step with its recommendation, which is also high — a level you choose yourself is never changed. Pick auto or a lower level when you would rather have quicker, cheaper replies, and raise it for complex reasoning tasks. You can also override this per-session.
Model vendor routing
Replaced by Who pays & who serves. Which company serves a model is now a row in its family's supply list, so this setting is no longer read and its Settings card is gone. What follows describes it as it was.
For models served by more than one AI provider (GLM, DeepSeek, Kimi, MiniMax), pins which provider actually handles each one. By default Omniscio automatically routes to the cheapest ready vendor. Use this to lock a specific model to a specific provider — for example if you have a rate-limit agreement or key with one vendor but not another. Empty means fully automatic. Found in Settings → Sessions → Model vendors.
AI Council sidebar launcher
Shows or hides the one-click AI Council row in the Prompt Tools section of the sidebar. On by default when the Multi-Model Council feature is enabled. Turn it off if you prefer to keep the sidebar tidy and access the Council another way. Mirrors the Bake-Off sidebar toggle — both share the same Prompt Tools area. Requires the multi-model-council feature to be on, and the row also hides whenever AI Council is switched off in the Sidebar Items picker (the picker lists AI Council once, and that toggle covers both AI Council rows).
Bake-Off model comparison
Shows or hides the Bake-Off entry in the sidebar. Bake-Off runs the same prompt across several models (or prompts) and lays the results side by side so you can compare quality, speed, or style before committing to one. On by default. Turn it off to remove it from the sidebar if you never use it. Related: AI Council.
AI reply suggestions
Shows a row of short AI-drafted reply options below the chat composer after the agent responds — tap one to send it instantly instead of typing. Off by default. When on, Omniscio runs a small background model call after each agent reply to generate the suggestions. Most useful in fast back-and-forth sessions where you want to keep the conversation moving without composing each reply from scratch.
AI suggestion model
The specific model used to generate the quick reply suggestions below the composer (when AI suggestions are on). Defaults to a fast, cheap model suited for this lightweight task. Change it only if you find the suggestions unhelpful and want to try a more capable model — note that a more capable model will cost more per suggestion batch.
AI Coaching — conversation style
Sets the tone of your AI coaching interviews. warm (default) is affirming and gentle — the coach leads with encouragement. neutral is professional and balanced — straightforward without being cold. direct is efficient and to the point — minimal small talk, maximum signal. You can change this at any time; it takes effect on your next coaching session.
AI Coaching — daily message style
Controls the category of the daily rotating message shown on the coaching Dashboard greeting banner. Seven options: motivational (default), coaching, mindfulness, stoic, humor, gratitude, challenge. Each category has 30 pre-generated messages; the one shown is deterministic by date, so it changes once per day. Your choice takes effect immediately — no reload needed.
AI Coaching — CLI access
Allows external agents to read your coaching artifacts and start coaching interviews over the local CLI control server. On by default. Flip it off to block all coaching access from the command line — for example if you want to keep your coaching content private from any agents running on this machine, regardless of what they are asked to do.
AI Coaching — ask for feedback after sessions
When on (the default), a short rating prompt appears when a coaching session finishes, so the coach learns what worked. Turn it off to stop being asked; choosing "Don't ask again" in the prompt does the same thing. It only affects the prompt — your coaching interviews keep working either way. Find it in Settings → AI Coaching.
AI Coaching — invitations from your coach
When on (the default), the coach may suggest one short sitting a day about something it noticed in your coaching and Journal data, such as a worry that keeps coming up, a goal that has gone quiet or a break after real progress. The invitation shows above the foundations meter, or on the Journal's Today screen while the Journal is on. Turn it off to stop invitations: the coach stops looking for them, makes no AI call for them and shows no card. Find it in Settings → AI Coaching.
Daily Digest
Generates a daily briefing that summarises AI session activity across all your hubs, plus optional sections for calendar events, communications, RSS feeds, and action items. Delivered to your inbox each morning at the scheduled time. On by default — the scheduler fires unless you explicitly switch it off. Turn it off, and choose which sections to include, in Settings → Email & Summaries. The digest uses a lightweight AI model and respects your daily cost cap.
Daily Digest model
The AI model used to write your Daily Digest. Automatic (default) inherits the global Utility AI model (DeepSeek when you have a key set up, otherwise the built-in default). Pick a specific model here to override that choice for the digest only — useful if you want a more capable model for richer summaries without changing your global utility model. Found in Settings → Sessions → Per-feature AI models.
Weekly Summary
Generates a written summary of the past week's session activity every Monday at the scheduled hour. Delivered to your inbox as an inbox card you can read and archive. Disable to pause future runs — your existing summaries stay visible. The summary uses a mix of a lightweight model for its analysis steps and the flagship model for the final write-up, so it costs slightly more than a digest.
Weekly Security Digest
Once a week, one inbox card that rounds up the last seven finished days of security-shaped events on this computer: security alerts, spend alerts that look like a runaway, secret and dependency scan findings, what agents did through the local control server, and any cloud incidents that reached your inbox. The same summary is emailed to the address you are signed in with, when an agent email address is set up. A week with nothing to report still produces the card and still sends it — that is deliberate, because a digest that never arrives is itself worth noticing. Off by default: turn it on here to receive it. Nothing arrives until this computer has been set up for seven days, so a brand-new install is never greeted with a security card saying nothing happened.
Weekly Summary model
The AI model used for the Weekly Summary's analysis steps (the final write-up always uses the flagship model). Automatic (default) inherits the global Utility AI model. Override it here if you want to steer which model does the lightweight Map and Verify passes without changing the flagship model that writes the prose. Found in Settings → Sessions → Per-feature AI models.
Sync to Other AI Tools
The master switch for Sync to Other AI Tools, which keeps your skills (and, if you opt in, your instructions and chosen MCP servers) available in Codex, Gemini, OpenCode, Cursor, Grok, Antigravity, Pi and Hermes. On by default, for new and existing installs; switch it off and Omniscio writes nothing to any other tool, and the choice sticks. Found in Settings → Automations & Rules → Sync to Other AI Tools. It is a desktop-only page and the phone view cannot change it.
Provider Config Sync — auto-sync
When on, Omniscio re-syncs what you share (your skills, and your instructions and chosen MCP servers if you turned those on) to the other AI tools on your machine in the background about every six hours. Off by default, which means the sync runs when you click Sync now and, for skills, in a light refresh when you start sessions. Turn auto-sync on if you change your setup often and want the other tools to always have the latest version without having to remember to sync. Found in Settings → Automations & Rules → Sync to Other AI Tools (desktop only).
Provider Config Sync — instructions
Off by default. When on, your own agent instructions (the presets you enabled and your custom text, never Omniscio's own reply-format rules) are written as a clearly marked block into the instructions file each target tool reads, and the rest of that file is left alone. Turning it off removes the block again. Useful to leave off if you manage tool-specific instructions separately. Found in Settings → Automations & Rules → Sync to Other AI Tools.
Provider Config Sync — skills
On by default. Controls whether your Omniscio skills (the SKILL.md folders) are installed into the other AI tools. On means tools such as Codex, Gemini, Antigravity, Pi, Hermes and Cursor can also run your skills (OpenCode and Grok read your skills folder directly). Off keeps skills local to Omniscio, and a skill copy you edited inside another tool is never overwritten or deleted either way. Note: each target tool has a skill-count budget; syncing too many skills to Codex (which has a strict loader limit) will trigger a budget alert. Found in Settings → Automations & Rules → Sync to Other AI Tools.
Provider Config Sync — copy skills back in
Off by default for everyone. Its switch, Also bring in skills from other tools, sits under Sync skills in Settings → Automations & Rules → Sync to Other AI Tools and shows while skills sync is on. When enabled, a skill you authored in Codex, Gemini or OpenCode is copied into your Omniscio skills folder before the next sync, only if no skill of that name exists there yet; the original in the other tool is never changed. It is separate from the skills switch, because it writes into your main skills folder, so turning on skills sync never turns it on.
Sync agent instructions across tools
Mirrors your canonical agent instructions file (CLAUDE.md or AGENTS.md) into the filenames that other AI coding tools read — including Codex, Gemini CLI, Cursor, Cline, Copilot, and Windsurf. Off by default. Turn it on if you work across several AI tools and want them all to follow the same project rules without copying files manually. Related to Provider Config Sync but operates independently (no sync targets needed).