sandboxing
Latest stories covering sandboxing, with summaries and links to related coverage.
4 stories · 4 reports · page 1 of 1
Connected topics
Agent Safehouse – macOS-native sandboxing for local agents
tool
2 min read
Agent Safehouse provides macOS-native sandboxing for local agents, ensuring that they operate without affecting the broader system. The sandboxing mechanism restricts access to user permissions, allowing agents to run safely while preventing any unintended consequences.
Let's discuss sandbox isolation
tool
19 min read
Sandboxing untrusted code is crucial for safely running AI-generated code, customer scripts on multi-tenant platforms, and RL training pipelines. Various technologies, including Docker containers, microVMs, and WebAssembly modules, provide different levels of isolation for executing potentially harmful code.
Building secure, scalable agent sandbox infrastructure
tool
6 min read
Browser Use operates millions of web agents using AWS Lambda for isolated execution and instant scaling. The infrastructure supports code execution in a secure sandbox environment, allowing agents to run Python, execute shell commands, and create files.
Just-bash: Bash for Agents
tool
10 min read
Just-bash is a simulated bash environment with an in-memory virtual filesystem, designed for AI agents requiring a secure, sandboxed environment. It supports optional network access through curl with secure URL filtering and is currently in beta.