Sandbox Python Packages

pydantic-monty

A minimal, secure Python interpreter written in Rust for use by AI

pydantic-monty-runtime

A minimal, secure Python interpreter written in Rust for use by AI

pydantic-monty-client

A minimal, secure Python interpreter written in Rust for use by AI

k8s-agent-sandbox

agent-sandbox enables easy management of isolated, stateful, singleton workloads, ideal for use cases like AI agent runtimes and reinforcement learning (RL).

tensorlake

Tensorlake is a serverless runtime for sandboxes and deploying background agentic applications

opensandbox

Secure, Fast, and Extensible Sandbox runtime for AI agents.

runloop-api-client

Official Python SDK for Runloop — secure Linux sandboxes (Devboxes) where AI agents run code, edit files, and expose ports

pydantic-ai-backend

File Storage & Sandbox Backends for Pydantic AI: console tools for file operations, Docker-isolated sandboxes for safe execution, and permission system with presets for access control. Enables secure multi-user handling and testing in agents via in-memory, local, or containerized storage.

boxlite

The micro-VM for AI agents — light enough to embed on your laptop, elastic enough to power an agentic cloud.

jupyter-kernel-client

🪐 > Jupyter Kernel Client through HTTP and WebSocket.

code-sandboxes

📦 Code Sandboxes — Run code in isolated sandbox variants through a unified API.

codeboxapi

👾📦 CodeBoxAPI is the simplest sandboxing infrastructure for your LLM Apps and Services.

opensandbox-code-interpreter

Secure, Fast, and Extensible Sandbox runtime for AI agents.

microsandbox

🧱 easy, fast, programmable and local-first microVM runtime and library

pydeno

Run AI-generated JavaScript from Python, securely, in a sandbox: real V8 in a supervised, OS-sandboxed worker process (Seatbelt, Landlock, seccomp), with your Python functions as the only way out.

evalidate

Safe and fast evaluation of untrusted user-supplied python expressions

agentenv-framework-protocol

Creating realistic RL environments requires collaboration between researchers, engineers, and domain experts across many dimensions: artifacts, environments tools, dynamism of the environment, reproducibility, and more. There is no open source framework for building these environments effectively. Until now.

polyaxon

AI Infra / AI Orchestration / AI Control Plane

containarium-telemetry

Open-source agent runtime — SSH-native isolation, eBPF egress policy, Kubernetes + LXC backends, GPU passthrough, MCP-native CLI

velaris-lang

Run code an AI wrote without handing it everything you can reach. Each function declares what it may touch. You grant the run one folder, one host or a number of calls, and the runtime refuses anything else the moment it's tried.

kern-sandbox

Rootless container runtime with no daemon. Runs agent tool calls and LLM-generated code in kernel-enforced containers.

agentenv-framework

Creating realistic RL environments requires collaboration between researchers, engineers, and domain experts across many dimensions: artifacts, environments tools, dynamism of the environment, reproducibility, and more. There is no open source framework for building these environments effectively. Until now.

opensandbox-server

Secure, Fast, and Extensible Sandbox runtime for AI agents.

agent-airlock

A type-checker and contract layer for AI agent tool calls, deny-by-default, in-process, Pydantic-only. Strict argument validation, ghost-argument stripping, and self-healing retries for MCP servers and agent frameworks.