Anthropic's Claude Code has revamped its Projects feature to enable users to manage multiple AI agents simultaneously in the cloud with shared memory, goals, and resources.
The updated Projects tool allows teams to run multiple agents under one workspace, each operating on parallel "threads" within dedicated Claude Code cloud sessions. A coordinator agent directs overall workflow across these threads, maintaining organization while agents work independently on separate repository branches.
Key features include shared memory systems, unified goal-setting, and a centralized library of files and artifacts accessible across all agents. This architecture mirrors existing multi-agent management tools like Grok Bot, positioning Claude Code as a competitive option for teams requiring coordinated AI agent deployment.
Each thread operates on its own repository copy, reducing conflicts and enabling simultaneous task execution. The coordinator ensures work stays organized and prevents duplicate efforts across parallel operations.
The relaunched Projects feature addresses growing demand for cloud-based multi-agent orchestration platforms as enterprises increasingly rely on AI-driven workflows requiring coordination across multiple specialized agents.
The United Nations is working with Google to restructure its global development data for AI agent compatibility after UNICEF testing revealed major accuracy issues with leading AI models accessing statistics.
Major AI companies including Anthropic, OpenAI, Google, and Microsoft are publicly advocating for a slowdown in frontier AI development following concerns about autonomous AI agents and existential risks.
Databricks CEO Ali Ghodsi dismissed concerns that AI poses an existential threat to humanity, rating that risk as negligible. He warned instead that AI's real danger lies in accelerating cybersecurity threats.
Base Labs, Baseten's research division, is collaborating with Hugging Face and Goodfire to develop methods for training and monitoring open-source AI models with a focus on safety.