Execution environment
An execution environment is the declared container template an AI agent runs in: its network egress policy (unrestricted, host-allowlist or offline), pre-installed packages and metadata. Declaring environments makes an agent's operational surface reviewable before it ever runs, instead of discovered in production.
In NeoXam Agents
The environment registry is shipped (V0) as governance metadata: each descriptor references a declared environment, auditable in the Catalog. Egress enforcement lands in Beta; per-run hardened sandboxes are a stated direction, not a current feature.
Related terms
See how these concepts come together in a governed agentic platform for investment operations.
Explore the platform