freshcrate
Home > Security > sandbox

sandbox

Run untrusted AI code safely, fast

Description

Run untrusted AI code safely, fast

README

Concave Sandbox Banner

Concave AI Sandbox

Run AI code safely, fast, untrusted

A self-hostable code execution sandbox platform built with Firecracker microVMs. Sub-200ms startup times with snapshot-based warm pooling.

About

Concave provides secure, isolated code execution environments for running untrusted code. Built with Firecracker microVMs, gRPC orchestration, and modern infrastructure tools.

  • Fast VM provisioning with golden snapshots
  • gRPC control plane for VM lifecycle management
  • Streaming data plane for file transfers and real-time output
  • HTTP API gateway with authentication
  • Python SDK for easy integration
  • Dashboard and documentation site

Getting Started

See SETUP.md for complete deployment instructions.

  1. Set up GCP project and domain
  2. Configure Terraform and Ansible
  3. Deploy infrastructure
  4. Install Python SDK: pip install concave-sandbox

Documentation

Contributing

Contributions are welcome! See CONTRIBUTING.md for guidelines.

Security

If you discover a security vulnerability, please create an issue. All security issues will be promptly addressed.

License

This project is licensed under the MIT license.

Release History

VersionChangesUrgencyDate
0.0.0No release found — using repo HEADLow12/19/2025
main@2025-12-19Latest activity on main branchLow12/19/2025
main@2025-12-19Latest activity on main branchLow12/19/2025
main@2025-12-19Latest activity on main branchLow12/19/2025
main@2025-12-19Latest activity on main branchLow12/19/2025
main@2025-12-19Latest activity on main branchLow12/19/2025
main@2025-12-19Latest activity on main branchLow12/19/2025
main@2025-12-19Latest activity on main branchLow12/19/2025
main@2025-12-19Latest activity on main branchLow12/19/2025
main@2025-12-19Latest activity on main branchLow12/19/2025

Dependencies & License Audit

Loading dependencies...

Similar Packages

AGENTS.md_generator🤖 Generate secure, automated repo documentation and pull request checks with a safe-by-default toolchain for coding agents.main@2026-04-21
awesome-lark-botsProvide open-source AI bots for Lark to automate tasks like brainstorming, project planning, content creation, and monitoring within a secure chat interface.main@2026-04-21
Secure-Agent-LauncherBlock AI agent access to sensitive macOS paths and log all actions to protect private data during command execution.main@2026-04-21
cuaOpen-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows).computer-server-v0.3.39
OpenSandboxSecure, Fast, and Extensible Sandbox runtime for AI agents.docker/execd/v1.0.13