Anaconda adds agent swarms and AI security tools

Anaconda is expanding its enterprise AI platform beyond Python distribution with tools for coordinating AI agent swarms, security testing, and production deployment. The release draws on three acquisitions: Kilo Code for AI coding, Enkrypt AI for security, and Outerbounds for orchestration. Agent swarms let task agents delegate work to subagents that operate simultaneously and select different models for different jobs. Security features include autonomous red-teaming agents covering over 300 attack categories and a least-privilege access model. Enkrypt research found vulnerabilities in 73% of agent tools examined across more than 25,000 MCP servers.