Features
Sub-90ms sandbox creation
Fully isolated sandboxes with dedicated kernel, filesystem, and network
Process execution with real-time output streaming
File system operations with CRUD permission controls
Native Git integration with secure credential handling
Built-in LSP support for multi-language analysis
Stateful environment snapshots for persistent sessions
Massive parallelization for concurrent AI workflows
Programmatic control via Python, TypeScript, Ruby, Go, Java SDKs
GPU compute (Nvidia H100, H200, RTX 4090, RTX 5090, RTX PRO 6000)
Web terminal, SSH, VNC, and VPN access
Webhooks for sandbox events
One-command install on macOS, Linux, Windows
Run hundreds of open models locally
MLX engine for Apple Silicon (faster, less memory)
GGUF model support via llama.cpp (Ollama 0.30)
NVIDIA Nemotron 3 Ultra for high-throughput reasoning
Cloud scaling with Free, Pro, Max tiers
Run multiple cloud models in parallel (1, 3, 10)
Web-enabled cloud agents for real-time info retrieval
Fully offline operation for mission-critical work
Data never used for training; privacy-first design
CLI tool with model management and configuration
REST API for building AI applications
Upload and share private models (Pro and above)
40,000+ community integrations
Desktop app for macOS, Linux, Windows
