Run AI models on your own hardware with automatic optimization and a single endpoint
Secure microVM sandboxes for AI agents
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Open source
Freemium
Pricing
Not given
Free plan: $0/month with $25 included usage and up to 5 running sandboxes. Starter: $20/month with $20 monthly usage and 20 running sandboxes. Pro: $99/month with $110 monthly usage and 100 running sandboxes. Scale: $399/month with $450 monthly usage and 500 running sandboxes. Usage metered at $0.01
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
E2B SDK compatible API gateway
Multiple sandbox sizes (Small, Medium, Large, XL with 1-8 vCPU and 2-16 GiB)
Live terminal and desktop viewing
SSH access with VS Code Remote support
Pause and resume with memory intact
Long-running sandboxes on Pro and Scale plans
Credential vault for secrets management
Egress control with allow and deny lists
Custom Docker images via Dockerfile
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
Direct E2B SDK compatibility without code rewriting
Usage-based billing with included credits, no overages on paused sandboxes