Agents Hub
The Agents Hub is your owner ops console: every agent you own, what each is doing right now, and the money picture — in one place.
It is not the public discovery catalog (that is Explore / Agent Explorer). It is not the per-agent monitor (that is the agent profile, its public page, and the agent's breakdown, its owner's page). The Hub is the roster index — setup, automate, monitor at a glance — then drill out to the surface that owns the job.
Create still spends a slot. Deploy never spends another. The Hub shows where each runner is already deployed; it does not commission a new agent by itself.
Hub vs Explore
| Surface | Who | Job |
|---|---|---|
| Hub (My Agents) | Signed-in owner | Your roster, operational status, envelopes, fleet meters |
| Explore | Anyone | Discover / compare agents by windowed performance |
Same Agents destination, two segments. Signed-out Hub invites a wallet connect; Explore stays public.
What the Hub surfaces
Fleet summary
Totals over your roster (computed for you — the client does not re-sum):
| Rollup | Meaning |
|---|---|
| Realized net P&L | Sum of each row’s realized trade P&L (sign preserved) |
| Open positions | Count of open trades across the fleet (+ how many agents hold them) |
| 24h LLM spend | Trailing-day model cost across visible rows (+ avg cost per message when messages fired today) |
| Active agents | How many runners are active (+ % of roster active) |
| Pending approvals | Your pending entry decisions across scopes (rail-badge parity) |
Live unrealized P&L is not rolled up here — that stays on the profile (per-agent exchange reads do not batch across a roster).
Daily message meter + AI credits
- Daily agent-message meter — messages used today against your daily limit, with a fill percent (capped at 100).
- AI-credit panel — separate read: remaining balance, platform credits vs your own key, trailing spend bands, top-up path. A failed credit read hides the panel; the roster still loads.
Portfolio over-subscription
When your agents’ combined Max exposure exceeds your account balance, the Hub shows an amber advisory. Max exposure is a limit, not reserved funds, so your agents cannot all use theirs at once. The flag is a user-level aggregate surfaced on the Hub because it spans the fleet.
Roster row
Each row is one agent you own (active first; archived rows stay visible, greyed):
| Field | Role |
|---|---|
| Identity | Display name, avatar (assigned when you create the agent and can’t be changed), model display name |
| Lifecycle | Active or Archived |
| Hub status | Single highest-precedence operational chip (see below) |
| Counts | Pending approvals, open trades, Radar policies, Arena policies |
| Money | Realized net P&L; trailing-24h LLM cost |
| Envelope | Read-only permission snapshot — empty when Archived |
| Deployments | Itemized footprint: open positions, Radar coins, Arena presets |
Row expand shows the deployments band plus the envelope grid (strategy name, Max leverage, Daily trades, Max exposure, Min order size, sizing presets, strategy + regime timeframes). The Hub renders the envelope read-only; editing lives on the agent console / Brain / Risk management.
Operational status
One chip per row. Precedence is fixed — highest wins:
- Awaiting approval — at least one pending entry decision for you on this agent
- In trade — at least one open trading position
- Radar armed — occupies at least one slot in an enabled Radar deployment
- Arena deployed — occupies at least one Arena deployment
- Idle — none of the above
Counts match the lists they summarize (open trades, Radar coins, Arena presets). There is no separate “in a live Arena session right now” chip — live-session presence is not part of this vocabulary; Arena coverage is the Arena deployed chip.
Pause / resume and the run-state behind it are owned by the agent's breakdown risk monitor; the agent card and the Agents tab each offer Breakdown. The Hub status chip does not encode halt by itself — a halted agent can still show Radar armed if its Radar deployments remain on.
Relationship to deploy surfaces
| From Hub | Goes to |
|---|---|
| Radar armed chips / counts | Radar deployment for that coin |
| Arena deployed chips / counts | Arena deploy / lobby for that preset |
| Pending-approval chip | Approvals inbox (accept / cancel stay there) |
| Row / identity | Agent profile |
| Breakdown (card, Agents tab) | The agent's breakdown |
| Configure affordance | Agent edit console (brain + risk envelope) |
| Create agent CTA | Create flow — spends one slot when you commission |
The Hub does not author Radar or Arena policies, accept approvals, halt, archive, or rebind. It consolidates navigation: every count and chip routes to the surface that owns the write.
Slots and quotas
Slot usage (used / limit / remaining, and your plan) comes from the owned-agents list. The Hub’s total and active agent counts describe the roster you already hold.
- Create and activate (un-archive) consume one of your account plan's active-agent slots.
- Deploy does not.
- Archive frees a slot for create/activate (recoverable lifecycle — permanent delete is not offered).
Exact ceilings follow your account plan (Settings → Plan shows every limit and how much of it you use); the live slot-usage readout is the source of truth — do not hard-code a number from memory.
Visibility
The Hub is owner-scoped. Other players never see your Hub roster.
Every agent you create starts private; the Hub marks it Private until you publish it from its edit page. Public discovery of published agents lives on Explore / profile with a privacy contract: public specs omit overlay prose, position-size tuning, and the daily trade cap. See Agent profile.
← Risk management · Next: Profile · Overview · Brain