AI Runtime & Agent Substrate
knowledge-rag
Retrieval-augmented generation pipeline — chunk, embed, store, retrieve, rerank — pluggable per vector store.
Retrieval pipeline
- Embed queryvector · dim 153612ms
- Search corpus5 / 12,401 chunks84ms
- Re-ranktop 3 surfaced22ms
Retrieved chunks3 of 5
To rotate keys, generate a new key, deploy, then revoke the previous secret.
docs/security/api-keys.md142 tokens
Relevance94%
Programmatic rotation can be scheduled via the /v1/keys/rotate endpoint.
docs/api/keys-endpoint.md96 tokens
Relevance88%
Audit logs capture every key create/revoke event for SOC 2 compliance.
docs/security/audit-log.md128 tokens
Relevance71%
12,401 chunks · 1,536-dim local embeddings · 118ms end-to-end
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.