The SD-WAN built for the AI era.
Is your network agent‑ready?
Caged AI is a trademarked Mushroom Networks brand for SD-WAN, WAN bonding, and AI API governance, managed from one portal. Connect branches through encrypted mesh and apply policy to supported cloud or local model requests routed through the gateway.
280 + 140 + 90 + 120 = 630 Mbps
All four links carry traffic at the same time.
New York ↔ Austin: direct tunnel carrying traffic.
o4-mini denied. Model not allowed by the eng-readonly policy.
One box per branch.
Every branch from one dashboard.
Caged ships a real SD-WAN router at every site. Multi-WAN by default. Mesh that builds itself between branches. FEC-bonded paths for applications that need loss recovery. Firewall, NAT, DHCP, SNMP — every config object pushed from the Portal, no CLI required.
- → multi-WAN with self-forming branch-to-branch mesh and policy-driven failover
- → FEC-bonded WAN paths — recover packet loss across configured paths
- → firewall, NAT, DHCP, SNMP, routing — all GUI-driven, all version-controlled, all fleet-pushed
- → zero-touch provisioning and self-serve licensing — claim and configure sites through the portal
New York ↔ Austin: direct tunnel carrying traffic.
Traffic is striped across fiber, cable, and LTE.
3 paths · 7% average raw loss · 12 ms jitter · 0% effective loss in this example
Validate the versioned settings before pushing to the fleet.
Example fleet: 1,284 sites · 4 shown · snapshot, rollback, and retry queue
AI traffic, governed at the edge.
One gateway for supported cloud and local AI APIs. Apply policy to the requests routed through Caged. Configure access, budgets, and privacy rules: route selected calls to a local LLM, or redact detected PII before forwarding supported requests to the cloud. Detection coverage depends on the payload and configured rules.
- → supported OpenAI and Anthropic APIs and configured local endpoints — one policy plane
- → per-key controls — model allow-lists, usage budgets, endpoint blocks, privacy rules
- → provider choice — route requests among supported cloud and local model endpoints
- → privacy policy — redact detected PII in supported payloads, or route selected requests to a local model
Applications must use the gateway for these controls to apply. AI use outside that request path requires separate controls. Check API compatibility before planning your deployment.
read_the_ai_governance_brief →Policy saved and pushed. 14 branches synced, 12 virtual keys updated.
Example fleet: 14 branches · 4 shown · snapshot, rollback, and diff
o4-mini denied. Model not allowed by the eng-readonly policy.
Sample decisions · masked keys · metadata audit
In this example, policy routes redacted requests to the cloud and a selected sensitive request to the local model.
claims-team · caged_sk_…f30a · policy chooses per call
multi-wan load balancer
Bond wired or wireless WAN internet connections into one resilient uplink. Each WAN is monitored and dynamically weighted for load balancing, with per-rule traffic routing plus advanced firewalling.
↗encrypted branch mesh
Full-mesh overlay control plane. On-demand spoke-to-spoke tunnels created when traffic between branches is detected, torn down when idle. Dynamic weights across multiple paths.
↗ai api gateway
OpenAI and Anthropic out of the box. Local LLM endpoints on the same policy plane. Create and manage AI API proxy endpoints on devices you own and control, with traffic governance and optional PII firewalling.
↗centralized portal
Device inventory, zero-touch config, bulk config push with retry queue and DLQ, firmware batch upgrades with validate/execute gates, snapshot and rollback. Self-serve licensing. Single dashboard for all.
↗Caged AI is a trademarked Mushroom Networks brand.
Run a pilot at
one branch.
Drop a Caged AI box at a single site. Bring your existing WAN links. Bring your existing AI providers. Replace it inside a month — or keep going.