Agent-first GPU compute marketplace with per-second billing
More intelligence on hardware you already own
Stage
Not given
MVP
Founded
Not given
Not given
Based in
KN
US
Pricing model
Paid
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
Per-second billing with no minimum
Agent skill for AI coding agents
Prepaid balance with card or crypto payment
94 GPU models from data center to consumer class
Provider-set pricing with 95% provider share
Public price feeds and API access
Model Context Protocol server for AI documentation search
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
Agent-first design with one-command GPU provisioning
Providers set own prices on open marketplace
No minimum rental period or reservation required
Crypto payment option with 2.5% bonus
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