Capacity

rensei capacity is the org-level view of execution infrastructure - what providers and pools exist across your entire organization, their current utilization, and how much agent compute has cost you over a given window. Use it to provision new pools, inspect existing ones, and track spend before reviewing the billing dashboard.

For capacity that is scoped to the local machine (the daemon running on your laptop or a registered build host), use rensei host capacity. The rensei capacity commands shown here operate on the org-wide pool registry.

Deprecated aliases

rensei execution * was renamed to rensei capacity *. The old form still works in the current release but prints a deprecation warning.

Commands

`capacity show`

Print a unified live view of all execution capacity available to the org - persistent local hosts and on-demand cloud sandboxes combined.

rensei capacity show [--json]

Flag	Description
`--json`	Emit a structured JSON report

rensei capacity show
rensei capacity show --json

Example output:

Org execution capacity
======================

Persistent hosts (local pools)
  pool-local-main      3 hosts active   8/16 sessions   hybrid mode
  pool-local-gpu       1 host  active   0/4  sessions   persistent mode

On-demand sandboxes
  pool-cloud-e2b       e2b              0/∞  sessions   on_demand mode
  pool-cloud-modal     modal            0/∞  sessions   on_demand mode

Total running sessions:  8
Total available slots:   12 (persistent) + ∞ (on-demand fallback)

`capacity cost`

Show aggregated compute cost for the org over a sliding time window.

rensei capacity cost [--window 24h|7d|30d] [--json]

Flag	Default	Description
`--window`	`24h`	Time window: `24h`, `7d`, or `30d`
`--json`	-	Emit a JSON cost breakdown

rensei capacity cost --window 24h
rensei capacity cost --window 30d --json

Example output:

Compute cost - last 7 days
===========================

By pool:
  pool-local-main        $0.00   (self-hosted, no platform compute charge)
  pool-cloud-e2b         $14.28  (47 sessions × avg 18 min)
  pool-cloud-modal       $6.05   (8 GPU sessions × avg 22 min)

By project:
  my-fintech-app         $12.41
  internal-tools         $7.92

Total:                   $20.33

Self-hosted pools (local provider) accrue no Rensei compute charges. Cost tracking for those pools reflects the sessions executed but shows $0.00. Use the Factory cost breakdown dashboard for a full human-vs-agent cost view.

`capacity provider list`

List all sandbox and execution providers registered in the org.

rensei capacity provider list

Providers are the underlying substrate that pools are built on. Each provider has a family (sandbox, workarea, runtime, etc.) and a set of capability flags. See Sandbox providers - add a provider for the full capability matrix.

`capacity pool list`

List all execution pools in the org.

rensei capacity pool list [--json]

Flag	Description
`--json`	Emit pool array as JSON

rensei capacity pool list
rensei capacity pool list --json | jq '[.[] | select(.mode == "on_demand")]'

Example output:

ID                  NAME              PROVIDER   MODE         HOSTS  SESSIONS
pool-local-main     Local Main        local      hybrid       3      8/16
pool-local-gpu      GPU Workloads     local      persistent   1      0/4
pool-cloud-e2b      E2B Sandboxes     e2b        on_demand - 0/∞
pool-cloud-modal    Modal GPU         modal      on_demand - 0/∞

`capacity pool create`

Create a new execution pool.

rensei capacity pool create \
  --provider <provider-id> \
  --name "<display-name>" \
  --mode persistent|on_demand|hybrid

Flag	Required	Description
`--provider`	Yes	Provider ID from `capacity provider list`
`--name`	Yes	Human-readable display name for the pool
`--mode`	Yes	`persistent` (local hosts only), `on_demand` (cloud-spawned), or `hybrid` (local with cloud overflow)

# Create a hybrid local pool for backend work
rensei capacity pool create \
  --provider local \
  --name "Backend Local" \
  --mode hybrid

# Create an on-demand cloud pool for GPU inference tasks
rensei capacity pool create \
  --provider modal \
  --name "GPU Inference" \
  --mode on_demand

The created pool's ID is printed on success. Use it in rensei fleet route set --preferred-pool to start routing project work to it.

`capacity pool show`

Show configuration and live status for a single pool.

rensei capacity pool show <pool-id>

rensei capacity pool show pool-local-main

Includes current host membership, per-host session counts, pool mode, and the runtime_provides capability list. See Capacity pools for how runtime_provides affects substrate resolution.

`capacity pool update`

Update the display name or mode of an existing pool.

rensei capacity pool update <pool-id> [--name <name>] [--mode persistent|on_demand|hybrid]

Flag	Description
`--name <name>`	New display name
`--mode`	New mode: `persistent`, `on_demand`, or `hybrid`

# Rename a pool
rensei capacity pool update pool-local-main --name "Primary Local Fleet"

# Switch a persistent pool to hybrid (allow cloud overflow)
rensei capacity pool update pool-local-main --mode hybrid

Changing pool mode from persistent to on_demand takes effect immediately for new sessions. In-flight sessions on local hosts are unaffected. If the pool has no local hosts and mode is on_demand, all new sessions will spawn cloud sandboxes.

`capacity pool delete`

Delete an execution pool. The pool must have zero active sessions.

rensei capacity pool delete <pool-id>

rensei capacity pool delete pool-cloud-e2b

If the pool is referenced as a preferred or fallback pool by any project's routing policy, those routes are cleared and the affected projects fall back to org-default routing. You will be warned before deletion if any routes reference the pool.

Pool modes

Mode	Description	Best for
`persistent`	Work only runs on registered local hosts in this pool. Never falls over to cloud.	Security-sensitive workloads, BYOK model auth, BFSI compliance
`on_demand`	Work spawns cloud sandboxes (e2b, Modal, Vercel Sandbox, etc.). No local hosts required.	Elastic workloads, short-burst compute, GPU inference
`hybrid`	Local hosts first; spills to cloud providers when local capacity is exhausted.	General-purpose project work

For the full relationship between authMode and pool selection constraints (some auth modes require local pools), see LLM auth modes.

Fleet - multi-machine routing - set which pools a project prefers
Host capacity - per-machine envelope - tune maxConcurrentSessions and poolMaxDiskGb on the local host
Sandbox providers - provider capability matrix
Factory cost breakdown - human-vs-agent cost analytics

On this page