Anthropic añade una función de "sueño" a los agentes gestionados de Claude

Anthropic presentó una nueva capacidad de "sueño" para sus agentes gestionados de Claude durante la conferencia para desarrolladores Code with Claude celebrada en San Francisco. La función permite a los agentes revisar sesiones recientes y almacenar patrones clave en la memoria para futuras tareas. La compañía también planea ampliar el acceso a otras herramientas y aumentar los límites de uso para los suscriptores.

El proceso de "sueño" se ejecuta de forma programada y analiza las sesiones de múltiples agentes para identificar patrones recurrentes, errores y preferencias compartidas. Los usuarios pueden optar por actualizaciones automáticas de memoria o revisar ellos mismos los cambios propuestos. Este enfoque ayuda a superar los límites en las ventanas de contexto durante proyectos prolongados que involucran a varios agentes trabajando juntos durante horas o días.

Artículos relacionados

Dramatic illustration of Anthropic imposing a paywall on Claude AI, blocking third-party agents from overloaded servers.
Imagen generada por IA

Anthropic ends unlimited Claude access via third-party agents, requires extra payments for heavy use

Reportado por IA Imagen generada por IA

Anthropic has restricted unlimited access to its Claude AI models through third-party agents like OpenClaw, requiring heavy users to pay extra via API keys or usage bundles starting April 4, 2026. The policy shift, announced over the weekend, addresses severe system strain from high-volume agent tools previously covered under $20 monthly subscriptions.

Anthropic announced on Wednesday the launch of Claude Managed Agents, a new product aimed at simplifying the creation and deployment of AI agents for businesses. The tool provides developers with ready-made infrastructure to build autonomous AI systems. It addresses a key barrier in automating work tasks amid the company's rapid enterprise growth.

Reportado por IA

Anthropic announced updates to its Claude Design tool on June 17 that add design system imports, tighter integration with Claude Code, and new export options. The changes target enterprise teams needing AI-generated designs to align with brand guidelines and move smoothly into production.

Anthropic announced a major computing deal with SpaceX on Wednesday that immediately boosts rate limits for Claude Code users. The agreement gives the AI company full access to a large data center in Memphis, Tennessee.

Reportado por IA

Microsoft has restricted its employees from using Claude Fable 5. The decision stems from data retention requirements set by Anthropic.

Cursor announced the launch of Cursor 3 on Thursday, a new product interface that enables users to create AI coding agents for task completion. Developed under the code name Glass, the tool positions the AI coding startup to challenge competitors. It responds directly to recent successes by Anthropic’s Claude Code and OpenAI’s Codex.

Reportado por IA

The Trump administration directed Anthropic to revoke access to its advanced AI models following concerns about ties to China. The move led the company to take its most powerful offerings offline last week.

Este sitio web utiliza cookies

Utilizamos cookies para análisis con el fin de mejorar nuestro sitio. Lee nuestra política de privacidad para más información.
Rechazar