El sandbox-runtime de código abierto de Anthropic ofrece seguridad ligera a nivel de sistema operativo para agentes de IA y herramientas de línea de comandos, restringiendo el acceso a archivos y redes sin la sobrecarga de los contenedores.
Resumen generado con IA. Consulta el original para comprobar el contexto y la precisión.
Este es el extracto disponible del feed. Puede estar abreviado o en el idioma original.
In this article, we will discuss newly trending open sourced Anthropic’s sandbox-runtime (srt), the OS-level sandbox behind Claude Code’s sandboxed bash tool. The Anthropic sandbox-runtime limits which files a process can touch and which hosts it can reach. It does this without spinning up a container. It is also not tied to Claude Code. Your own agents, local MCP servers and plain command-line programs can run inside it. TL;DR Size: npm package @anthropic-ai/sandbox-runtime v0.0.81, about 11.4 MB unpacked, Apache-2.0, Node.js 22.12+. Runs on: any macOS or Linux dev machine or CI box. macOS uses Seatbelt; Linux needs bubblewrap, socat and ripgrep. Windows is alpha. Performance: sandboxing cut Claude Code permission prompts by 84% in Anthropic’s internal usage (self-reported). Best: 84% fewer permission prompts, with file and network limits enforced on the whole process tree. Worst: still a beta research preview, Windows support is alpha. What is Anthropic sandbox-runtime? Anthropic sandbox-runtime is an open-source tool that wraps any process in filesystem and network restrictions. You install it with npm install -g @anthropic-ai/sandbox-runtime, then prefix a command with srt. It works as a CLI and as a TypeScript library. How does sandbox-runtime work on macOS, Linux and Windows? srt uses each operating system’s own isolation primitives. Its restrictions cover the entire process tree, including scripts and subprocesses. macOS: sandbox-exec with dynamically generated Seatbelt profiles. Only ripgrep is required. Linux: bubblewrap with the network namespace removed. It also needs socat and ripgrep. Windows (alpha): a dedicated srt-sandbox account, a Windows Filtering Platform egress fence and explicit file ACLs. Traffic leaves only through HTTP and SOCKS5 proxies running on the host. On Linux, those proxies sit behind Unix sockets bind-mounted into the sandbox. On macOS, the Seatbelt profile allows only one localhost port. The proxies then apply your d
Una ayuda automática para ordenar, basada en fuentes, palabras clave y entidades, en una escala de 1–12. Alta: 9–12; media: 6–8; baja: 1–5. No mide urgencia, verifica noticias ni representa respaldo editorial.
Este tutorial demuestra cómo construir un copiloto de ingeniería con estado utilizando Letta para habilitar la gestión autónoma de la memoria, el estado compartido del agente y la recuperación semántica para flujos de trabajo de IA avanzados.
El nuevo modelo abierto de 4 GB de NVIDIA permite ejecutar agentes de voz y personajes de videojuegos de forma rápida y local en hardware de consumo, liberando recursos para otras tareas de IA.
Los autoencoders CADRE de Kyutai reducen la latencia de los modelos de mundo a menos de 230 ms, lo que permite simulaciones interactivas más rápidas y responsivas en una sola GPU H100.