Run AI models on your own hardware with automatic optimization and a single endpoint
More intelligence on hardware you already own
Stage
Not given
MVP
Founded
Not given
Not given
Based in
Not given
US
Pricing model
Open source
Freemium
Pricing
Not given
Pantry is free and open source. The rest of the AI stack (Iron, Butter, Syrup, Whisk, Waffle) is in private early access with pricing to be determined.
Key features
Automatic model loading from Hugging Face and other sources
Hardware-aware model optimization for VRAM and context length
OpenAI-compatible endpoint
Support for multiple inference engines
Single unified endpoint for all models and machines
Distributed compute across multiple machines
Built-in app catalog with chat UIs and RAG tools
Integration with cloud providers
Pantry: free, open-source vulnerability scanner for macOS and Linux
Iron: GPU kernels optimized for Apple silicon, NVIDIA CUDA, and AMD ROCm
Butter: multi-modal inference engine for text, vision and audio
Whisk: memory and context management to mix documents and context into requests
Syrup: control plane for monitoring, telemetry, access control and cost per GPU
Waffle: agent harness for building assistants
Runs on Apple silicon, NVIDIA RTX, H100, H200, B100, B200 and AMD ROCm
Local execution keeps data on your hardware by default
What makes it different
No manual engine configuration needed
Automatic workload-based tuning
One endpoint covers local and cloud models
Built on trusted community engines
Built for lower cost per token through efficiency optimization
Private by default; data stays on your hardware
Supports multiple hardware platforms with write-once kernels
Pantry offers free, open-source vulnerability scanning and patching
Enables AI on commodity hardware people already own