🏷️ €9900 | Yearly Subscription
includes MX-AI License, 1-year Updates, Support, and Marketplace Access.
-21fac8?logo=chatbot&logoColor=white){kind=icon}
MX-AI is the BubbleRAN closed-Loop automation and intelligence platform tailored to 5G/6G E2E networks offering open ecosystem and development kits to accelerate the development, deployment, and sharing of network applications - xApps, rApps, data processing, and AI Agents - cross multi-vendor, multi-model, and multi-cloud (multi-x) networks.
💡 Getting started is simple: choose or customize a agent blueprint from our portfolio, and deploy it with a single command:
bash$ brc install aifabric smo-agent.yaml
📄 Download Data Sheet 📰 Read blog MX-AI Walkthrough
Why MX-AI ?
- Tame 5G/6G complexity - Autonomously orchestrate multi-vendor RAN/Core with closed loops.
- Proactive operations - Agents detect anomalies, predict faults, and cut MTTR from hours to minutes.
- Sovereign by design - Run SLMs (5–20 GB) fully on-prem/edge; burst to large GPUs only when needed.
- Digital-twin safeguard - Test policies in MX-DT and push only if better (“apply-if-better” gates).
- One hub for reuse - Share xApps/rApps, agents, and tuned models via MX-HUB, no lock-in.
What’s Included?
- MX-AI Core: Multi-agent runtime, Orchestrator, A2A protocol, tool connectors
- Base Agents: O-RAN SMO, O-RAN RIC, Observability and Actions
- Dev Kits (SDK/CDK/ADK): templates, readymade samples, one-command container builds
- MX-HUB Access: Pull/push agents, datasets, models with versioning
- Web GUI, CLI & Chat: Intent to actions with UI
- Integrated Data & APIs: SMO observability connectors
[BETA]
🚀 Add-on Specialized Agent
€9900 / All Agents / Year OR €2900 / Agent / Year
Tailored AI-agent development is available as an add-on service. Contact us for the delivery of a personalized solution.
🟢 NOW 🟣 BETA 🟡 PLANNED
| Agent Category | Status & Agent | Description |
|---|---|---|
| Infra / Lifecycle | 🟢 Network Blueprint | create/update blueprint (included) |
| 🟢 SMO | orchestrate configs (included) | |
| 🟣 RIC | enforce policies (included) | |
| 🟡 xApp/rApp | deploy/monitor apps | |
| 🟡 Kubernetes | cluster health | |
| Observability | 🟢 Watcher | real-time metrics and RAG (included) |
| 🟡 Digital-Twin | what-if replicas | |
| 🟡 Data Collection | dynamic KPIs | |
| Orchestration | 🟢 Orchestrator | intent → agents (included) |
| Compliance | 🟡 Spec/Regulatory | 3GPP/O-RAN Q&A |
| 🟡 Judicial | detect misbehaviour | |
| Negotiation | 🟣 SLA Agent | symbiotic mediator |
| Predictive & Ops | 🟡 PM Agent | predict faults |
| 🟡 AD Agent | detects anomalies | |
| 🟡 Resolution Agent | resolves anomalies |
ℹ️ Note: Watcher keeps MX-AI’s vector DB fresh; Orchestrator coordinates via A2A; SMO deploys and updates network blueprints and configurations.
Multi-Model Support
- Local: SLMs (5–20 GB) on 16 GB GPUs or CPU-only; burst to A100/H100 when needed.
- Logos: are trademarks of their respective owners and used here for identification only.
MX-AI Core Software Stack
Mx-AI Benefits at a Glance
| # | Benefit | Description |
|---|---|---|
| 1 | O-RAN-friendly & Open APIs | R1/A1, SMO/RIC, REST/gRPC; OSS/BSS, CRM, billing connectors. |
| 2 | Sovereign SLM-first | Run 5–20 GB SLMs on-prem/edge; data stays local. |
| 3 | Predictive optimisation | Anticipate surges/failures; reduce congestion & MTTR. |
| 4 | NOC/Field-Ops automation | Guided workflows, smart ticketing, fewer escalations. |
| 5 | Twin-driven rollouts | Test fixes in MX-DT; “apply-if-better” to live network. |
| 6 | Analytics & billing | Reconcile invoices, detect anomalies, predict churn. |
| 7 | Privacy & compliance | XAI dashboards, EU-AI-Act-ready patterns, federated learning. |
| 8 | Reuse via MX-HUB | Share agents, datasets, tuned models, no lock-in. |
Practical Use-Cases
| # | Use-Case | Description |
|---|---|---|
| 1 | Build–Benchmark–Publish | Ship agents with SDK wizards; replay traffic; publish to MX-HUB. |
| 2 | Multi-Agent Experiments | Run variants in parallel; compare latency/throughput/energy. |
| 3 | Plug-and-Play Integration | O-RAN R1/SMO north-bound; unify OSS/BSS/CRM/billing data. |
| 4 | Twin-Driven Closed Loops | Validate policies in MX-DT; promote only improvements. |
| 5 | NOC & Field-Ops | Knowledge + telemetry + decision support; fewer truck rolls. |
| 6 | Planning & Optimisation | Simulate demand; optimise spectrum/capacity; site planning. |
Ready to test?
bash$ brc install aifabric tutorial-agent.yaml
- MX-AI: Tutorial Agent
- BubbleRAN Command Line (
brc) Tutorial - Would you like to talk with our team? Book a live demo
Need more information?
Check our frequently asked questions about MX-AI to learn more and get quick replies.
BubbleRAN also offers tailored AI-agent development as an add-on service. Whether you need a specialized agent or want to extend the MX-AI platform with custom capabilities, our team can work with you to define the technical specifications and deliver a personalized solution. Contact us to discuss your needs and explore the details.
To answer your unique deployment and projects needs, we can plan a live demo, help you forward with a requirements questionnaire, and connect you with our partner ecosystem (universities, system integrators, cloud providers). 📧 contact@bubbleran.com
Frequently Asked Questions
1️⃣ Can MX-AI run fully on-prem?
Yes. SLM-first deployments run on modest edge GPUs. You can burst to larger GPUs when needed.
2️⃣ Do you integrate with our SMO/RIC?
MX-AI is O-RAN-friendly (R1/A1) and offers REST/gRPC adapters for common SMO/RIC NBI.
3️⃣ How do we publish and reuse agents?
Via MX-HUB. Pull/push agents, datasets, and tuned models with versioning and fork/merge workflows.
4️⃣ What hardware do we need?
MX-AI runs great on a single 16–24 GB GPU.
For training or large-scale inference, use A100/H100 class GPUs.
5️⃣ What if I don’t have my own GPU ?
You need to purchase an API key from an external provider, as this is not included by default.
6️⃣ How is data privacy handled?
Data stays local in sovereign mode.
We support audit logging, role-based access, and optional federated learning.
No telemetry leaves your site unless you opt-in.