Engineering writing about agent workspace runtimes, execution boundaries, and the design behind agentvfs.https://agentvfs.neullabs.com/en-ushttps://agentvfs.neullabs.com/blog/agentvfs-vs-bare-docker-for-agent-code-execution/https://agentvfs.neullabs.com/blog/agentvfs-vs-bare-docker-for-agent-code-execution/A side-by-side walkthrough: what it looks like to run an agent's code-execution step on raw Docker, what it looks like on agentvfs, and where the workspace-runtime model earns its keep — plus where Docker still wins.Wed, 20 May 2026 00:00:00 GMThttps://agentvfs.neullabs.com/blog/designing-for-agent-aware-filesystem-access/https://agentvfs.neullabs.com/blog/designing-for-agent-aware-filesystem-access/What a filesystem looks like when its primary user is an LLM, not a human. Vaults, forks, checkpoints, structured output, and the small set of invariants that make an agent loop survive contact with concurrent state.Wed, 06 May 2026 00:00:00 GMThttps://agentvfs.neullabs.com/blog/execution-boundary-patterns/https://agentvfs.neullabs.com/blog/execution-boundary-patterns/A guide to the boundary options for agent code execution. Linux namespaces, MicroVMs, WASI, and the workspace-runtime model agentvfs implements — what each one enforces, where each one costs you, and how they compose.Wed, 22 Apr 2026 00:00:00 GMThttps://agentvfs.neullabs.com/blog/why-agents-need-a-different-sandbox/https://agentvfs.neullabs.com/blog/why-agents-need-a-different-sandbox/CI sandboxes optimize for hermetic, single-pass builds. Agent sandboxes need cheap forks, rollback, policy at the command line, and a workspace that survives across turns. They look different — and treating them as the same is where most failures live.Wed, 08 Apr 2026 00:00:00 GMT