Breeze isn't a dashboard you operate — it's an RMM with an AI operator built in that works the fleet for you. The operator triages alerts, patches fleets, writes scripts, and generates compliance reports using the same tools your techs use, governed by a 4-tier risk engine you control so it can never run amok.
Free and open source. BYOK with your Anthropic key. Optional managed mode via LanternOps Brain.
Four real conversations. Same tools your techs use.
Every action is classified, logged, and reversible. The operator proposes — your risk engine decides.
Examples are representative. The operator's exact responses depend on your fleet state, policies, and risk classifications.
Watch the operator investigate a real device issue.
The operator uses the same APIs your techs use.
Every RMM capability is exposed to the operator as a standardized tool. Each tool has a risk tier. The same reboot is Tier 2 inside a maintenance window and Tier 3 outside one — context drives policy automatically.
List devices, get details, query fleet state
Retrieve, update status, link to tickets
Reboot, shutdown, lock, isolate, install, uninstall
Status, schedule, deploy with maintenance windows
PowerShell, Bash, or Python with result retrieval
Compliance, security, inventory, executive reports
Self-host Breeze, drop in your Anthropic API key, start asking questions.
Same tools. Same guardrails. Pick where the reasoning runs.
Bring Your Own Key · Free
Included with every Breeze deployment
Good enough to be useful. Limited enough to upgrade.
Managed AI · Per-endpoint pricing
Everything BYOK can't do
Same tools. Smarter brain. Zero migration.
LanternOps can request actions. Your Breeze instance decides whether to allow them. Risk classification is enforced at the RMM level — not the operator level. Double validation: LanternOps pre-validates with its intelligence layer, then your RMM re-validates with its risk engine. Belt and suspenders.
Every action is auditable. Every tool call is logged. Every approval decision is recorded.
The operator works because the rest of Breeze does.
The in-app AI assistant with risk-tiered actions and full audit trail.
AI that can take direct action on endpoints under guardrails.
Hierarchical configuration policies that govern what Brain can do.
The reports Brain generates automatically — compliance, security, executive.
Common questions about the AI operator
The AI operator is the autonomous layer built into every Breeze RMM deployment — it works the fleet for you instead of waiting to be operated. It uses the same tools and APIs your technicians use — listing devices, querying alerts, running scripts, scheduling patches, generating reports — and it operates under a 4-tier risk engine that classifies every action before execution. You ask in plain English; the operator proposes; your risk engine decides whether the action runs automatically, requires approval, or is blocked. The reasoning engine behind it is called Breeze Brain.
Yes for BYOK (Bring Your Own Key) mode, which is included free with every Breeze deployment. You provide your own Anthropic API key in settings and the operator runs locally inside your RMM. LanternOps Brain is an optional managed mode where LanternOps hosts the reasoning engine for you and adds persistent memory, cross-tenant intelligence, and automated playbooks — no key required from you.
Only within the limits your risk engine defines. Tier 1 (reads) runs freely. Tier 2 (low-risk mutations like cache clears) auto-executes and is audit-logged. Tier 3 (impactful actions like reboots, domain controller patches, agent uninstalls) requires human approval. Tier 4 is blocked outright. Context shifts tiers — a reboot inside a maintenance window is Tier 2; outside one it is Tier 3. The risk engine is enforced at the RMM level, not the operator level.
ChatGPT and similar chat tools have no access to your fleet, no concept of devices or alerts, and no execution authority. The Breeze operator is wired into your RMM's tool catalog — device tools, alert tools, action tools, patch tools, script tools, report tools — and every call it makes is governed, logged, and reversible. It can investigate a slow laptop, deploy a patch, or generate a compliance report end-to-end, not just describe how you would do it.
BYOK Brain is free, runs locally with your Anthropic API key, and reacts to one event at a time with no memory across sessions. LanternOps Brain is managed, includes persistent per-tenant memory, anonymized cross-tenant intelligence, an automated playbook library, multi-agent orchestration, and compliance evidence generation for NIST, CIS, SOC 2, and HIPAA. Both drive the same operator — the same tool catalog and the same risk engine. Only the reasoning layer changes.
Yes. The upgrade is one click — Settings → AI Brain → LanternOps → Connect, then authorize via OAuth. Your Breeze instance does not change. Same tools, same risk engine, same data. LanternOps Brain connects remotely through the Brain Connector API. No migration, no data movement, no downtime.
The operator investigates, acts, and documents — inside your RMM, governed by your policies. Free and open-source. No vendor lock-in.