Igris Runtime
Secure AI execution for edge devices.
Deploy AI anywhere with a 16MB binary. Run GGUF models locally, work offline, and manage your fleet from the cloud when needed. Fleet dashboard included free.
16MB Binary, Zero Dependencies
What It Does
Deploy AI to any device without Docker or complex setup.
How It Works
Single static binary compiled for Linux, macOS, and ARM architectures. No runtime dependencies, no package managers, no version conflicts. Just download and run.
Key Features
- •Single 16MB executable
- •Linux, macOS, ARM support
- •No Docker required
- •Static compilation
BYOM - Bring Your Own Model
What It Does
Run any GGUF model locally. Use open-source models or your own fine-tuned weights.
How It Works
Load GGUF format models from HuggingFace, local files, or your own training pipeline. Runtime handles model quantization, memory management, and inference optimization automatically.
Key Features
- •GGUF model support
- •Phi-3, Llama, Mistral compatible
- •4-bit and 8-bit quantization
- •Automatic memory management
Works Offline
What It Does
Execute AI without internet connectivity. Perfect for remote, mobile, and air-gapped environments.
How It Works
All inference happens locally on-device. Models run entirely in memory with no cloud calls required. Cache persists across restarts. Network outages don't stop execution.
Key Features
- •100% offline operation
- •No cloud dependencies
- •Persistent local cache
- •Network-fail resilient
Sandboxed Execution
What It Does
Secure, isolated AI execution with enforced safety boundaries.
How It Works
Every AI workload runs in a sandboxed environment with configurable limits on execution time, memory usage, and output size. Prevents resource exhaustion and runaway processes.
Key Features
- •Resource limits enforcement
- •Execution timeouts
- •Memory boundaries
- •Safe process isolation
Fleet Dashboard Integration
What It Does
Auto-sync with fleet dashboard when online. Included free.
How It Works
When devices have connectivity, Runtime automatically syncs status, telemetry, and logs with the fleet dashboard. Push model updates and configuration changes to your entire fleet. QR code pairing for instant device linking.
Key Features
- •Zero-config sync
- •Real-time status monitoring
- •Over-the-air model updates
- •QR code device pairing
- •Included free with Runtime
Get Started with Runtime
Download the Runtime binary for your platform, add your GGUF models, and deploy to any device. The fleet dashboard is included free for cloud-based fleet management.
Download RuntimeFleet View
The horizon that appears when you scale.
When you have multiple Runtime devices, this is the command center. Not a separate product. Not an integration. Just the natural evolution of running more than one thing.
Zero-Config Fleet Management
What It Does
Manage all your Runtime devices from a single dashboard. No setup required.
How It Works
Runtime devices automatically connect and report status when online. View all your devices, their health, model versions, and activity in real-time. No manual configuration needed.
Key Features
- •Automatic device discovery
- •Real-time status monitoring
- •Device health tracking
- •Model version overview
QR Code Device Pairing
What It Does
Add new devices to your fleet in seconds with QR code linking.
How It Works
Generate a QR code from the dashboard, scan it with your device, and it's instantly linked to your fleet. No API keys to copy, no config files to edit. Perfect for field deployment.
Key Features
- •Instant QR code pairing
- •No manual configuration
- •Bulk device onboarding
- •Field-deployment ready
Over-the-Air Model Updates
What It Does
Deploy new models to your entire fleet with a single click.
How It Works
Upload GGUF models to the dashboard and push them to selected devices or your entire fleet. Runtime devices download and verify updates automatically. Rollback if issues occur.
Key Features
- •Single-click model deployment
- •Selective or fleet-wide updates
- •Automatic verification
- •Safe rollback capability
Configuration Sync
What It Does
Keep device configurations consistent across your fleet.
How It Works
Define configuration templates in the dashboard and apply them to groups of devices. Runtime syncs configs when online and caches them for offline operation. Changes propagate automatically.
Key Features
- •Configuration templates
- •Group-based management
- •Automatic sync when online
- •Offline config caching
Fleet Analytics & Logs
What It Does
Monitor performance and troubleshoot issues across your entire fleet.
How It Works
Aggregate logs, metrics, and telemetry from all Runtime devices. View execution stats, error rates, resource usage, and model performance. Export data for external analysis.
Key Features
- •Centralized log aggregation
- •Performance metrics
- •Error tracking
- •Data export (CSV, JSON)
Included with Runtime
What It Does
The dashboard unlocks automatically when you scale. No separate purchase.
How It Works
The fleet dashboard is not a separate product—it's part of Runtime. Free tier gets basic dashboard access. Pro and Enterprise unlock advanced features. No separate billing.
Key Features
- •Included with Runtime
- •No additional cost
- •Scales with your plan
- •Unlocks automatically
The view unlocks when you scale
The fleet dashboard is included with Runtime. There is no separate pricing\u2014the view scales with your plan. Free tier includes basic dashboard features. Pro and Enterprise unlock advanced fleet management capabilities.
View Fleet Documentation