AI Runtime & Agent Substrate
execution-policy
Policy rules that route agent tasks to compute backends — render → Vercel Sandbox, long → Lambda, internal → local-runner.
policy.execution · 4 rules
task.kind === "render"Vercel Sandbox
task.duration > 5minAWS Lambda
task.tenant === "internal"local-runner
defaultVercel Sandbox
evaluated per-task · 3ms p50
More in nebutra.com
- 3d-pipeline3D asset generation + render — text-to-mesh + USD export + Three.js preview, with GPU-pool routing on the backend.
- agent-runtimeLower-level agent execution — message reducer, tool invocation, streaming state machine. The kernel @nebutra/agents wraps.
- agentsMulti-step agent runtime — Vercel AI SDK foundation, tool registry, streaming UI, MCP integration. The skeleton for every Sailor agentic feature.
- ai-primitivesShared helpers used across all AI packages — token counting, prompt templating, stream-parser, retry-with-backoff. No provider dependency.
- ai-providersProvider metadata — pricing per million tokens, context windows, modalities. Drives model selection and cost estimates.
- atelier-canvasInfinite design canvas — multiplayer cursors, layer panel, frame export. The drawing surface every atelier play renders into.