Kilntainers: Kilntainers provides isolated and ephemeral Linux sandboxes for LLM agents, enabling secure execution of shell commands without exposing sensitive data. It supports various backends like Docker, Podman, Modal, E2B, and WebAssembly, offering flexible and scalable agent environments.; verl-agent: `verl-agent` extends veRL to train LLM agents using reinforcement learning, featuring a novel step-independent multi-turn rollout mechanism. This design ensures high scalability for long-horizon tasks by allowing customizable per-step input structures and memory management.
Securely executing shell commands for LLM agents
Training large language model agents for complex multi-turn, long-horizon tasks.