Open Source

Open Text Shield

Enterprise-grade SMS security powered by AI. Delivers sub-second spam detection locally with advanced machine learning—optimized for high-volume telecom operations.

Arrow icon
Get PricingView on GitHub

OTS Inference

Live API
Try these examples:
NEW

AI SMS Classification on GPU — Deploy in 5 Minutes

Read Guide arrow
99.7%Detection Accuracy
<1sResponse Time
50+Languages Supported
100%On-Premise / Local

Enterprise-Grade SMS Security Solutions

Choose between Community Edition for development and testing, or Professional Edition for production-ready carrier-grade deployments.

Community Edition

Open Source Foundation

100% Open Source & Free
Self-Hosted Deployment
Custom Model Training
Full Source Code Access

Perfect for development, testing, and organizations with in-house AI expertise. Build and train your own models with complete transparency and control.

Professional Edition

Production-Ready Solution

Latest Pre-Trained Models
TCXC SMPP Integration
Commercial Support SLA
Zero Configuration Setup

Enterprise-ready with pre-integrated SMPP stack, professionally trained models, and carrier-grade support. Deploy instantly into production environments.

Built for the Community

Open Text Shield is completely open source, transparent, and community-driven

100% Open Source

Full source code transparency with MIT license. No hidden algorithms, no vendor lock-in, complete control over your security infrastructure.

Community Driven

Built by telecom engineers for telecom operators. Contribute features, report issues, and shape the future of SMS security with the community.

Enterprise Ready

Production-tested by major telecom operators. Scalable architecture, comprehensive documentation, and professional support available.

Case study

PAiCore selected OpenTextShield for real-time SMS protection.

Multilingual, on-premise SMS classification — every message labelled ham, spam, or phishing in under 50 ms. The programmable SMSC turns those labels into operator policy.

"This is an A.I. use we can proudly get behind — flexible SMSC routing and filter rules + a dynamic open source A.I.-powered SMS firewall."
Celeo Arias · Open Source Telecom Solutions
99.7%
accuracy
<50ms
p95 latency
10+
languages
100%
on-premise
Read the case studyDiscuss your deployment6 min read · April 27, 2026

Deployment Comparison

Both editions deliver sub-second spam detection with 99.7% accuracy, differing in deployment complexity and support level.

Feature
Community
Professional
License & Cost
Free & Open Source
Commercial License
Model Training
Self-Trained Required
Pre-Trained & Optimized
SMPP Integration
Manual Integration
Pre-Integrated Stack
Support Level
Community Forums
24/7 Commercial SLA
Best For
Development & Testing
Production Deployment

Deploy in 5 Minutes

Production-ready Docker image with GPU acceleration and dynamic batching. Validated on AWS g4dn.4xlarge (NVIDIA T4) at ~100 messages/sec sustained — 132,000+ messages, zero failures, zero timeouts.

Validated on NVIDIA T4 · FP16 · ~100 MPS sustained
01

Install NVIDIA driver and container toolkit

One-time setup on Ubuntu/Debian so Docker can pass the GPU through to the container.

bash
sudo apt update && sudo apt install -y nvidia-driver-535-server
sudo reboot

# After reboot — install NVIDIA Container Toolkit
sudo apt install -y nvidia-container-toolkit
sudo nvidia-ctk runtime configure --runtime=docker
sudo systemctl restart docker

# Sanity check — should list your GPU
docker run --rm --gpus all nvidia/cuda:12.6.0-base-ubuntu22.04 nvidia-smi
02

Pull and run OpenTextShield

Pin to an exact version in production. The image is multi-arch (linux/amd64 + linux/arm64) — Docker selects the right variant automatically.

bash
docker pull telecomsxchange/opentextshield:v2.9.0

docker run -d \
  --name ots \
  --gpus all \
  --restart unless-stopped \
  -p 8002:8002 \
  -p 8080:8080 \
  telecomsxchange/opentextshield:v2.9.0
03

Verify the GPU is being used

The /metrics endpoint reports the device. Should show device="cuda" and fp16="true" on a GPU host.

bash
# Confirm GPU acceleration
curl -s http://<host>:8002/metrics | grep ots_api_info
# Expected: ots_api_info{version="2.9.0",device="cuda",fp16="true",...} 1

# Watch live GPU utilization while sending traffic
nvidia-smi -l 2
04

Test classification

Send an SMS to the prediction endpoint and get a label back in milliseconds.

bash
curl -X POST "https://ots.telecomsxchange.com/predict/" \
  -H "accept: application/json" \
  -H "Content-Type: application/json" \
  -d '{"text":"URGENT! You have won $5000! Reply CLAIM to collect your prize money now! Limited time offer!","model":"ots-mbert"}'

# Response: {"label":"spam","probability":0.97,"processing_time":0.04,...}
05

Optional tuning for your hardware

Defaults are tuned for a Tesla T4 (16 GB VRAM). Override via environment variables for smaller GPUs or low-latency debugging.

bash
# Smaller GPUs (under 8 GB VRAM)
docker run -d --gpus all \
  -e OTS_MAX_BATCH_SIZE=32 \
  -e OTS_BATCH_WAIT_MS=50 \
  -p 8002:8002 -p 8080:8080 \
  telecomsxchange/opentextshield:v2.9.0

# Single-request debugging — disable batching
docker run --gpus all \
  -e OTS_BATCHING_ENABLED=false \
  -p 8002:8002 \
  telecomsxchange/opentextshield:v2.9.0
View the full deployment guide on GitHub arrow

Real-Time Performance Comparison

See why telecom operators choose Open Text Shield over expensive commercial AI APIs

Commercial APIs

Commercial AI APIs

Response Time:Up to 30 seconds
Cost per Request:$0.01 - $0.03
Network Dependency:Internet Required
Data Privacy:External Servers
Local Deployment

Open Text Shield

Response Time:< 1 second
Cost per Request:$0.00
Network Dependency:Offline Capable
Data Privacy:100% Local

Ready to secure your messaging infrastructure?

Get started with OpenTextShield — explore the source, deploy locally, or talk to our team about the Professional Edition.

Star on GitHubGet in Touch