AI runtimepackages/ai/local-embedding
local-embedding package
On-device embedding via ONNX / WebGPU. Avoids the round-trip when the embed is short, private, or rate-limited at the provider.
- Stability
- Stable
- Scope
- Global
- Boundary
- packages/ai/local-embedding
local-embedding
packages/ai/local-embeddingAI runtime · tool registry · MCP boundary
Ready
Capability graph
ai/local-embeddinglocal-embedding
Tool policy
Stream UI
Output
Run ledger
- 1Inputpackages/ai/local-embedding/request
- 2Planmessage reducer -> model turn
- 3Tool policytool schema · auth scope · rate limit
- 4Stream UIevents -> UI state machine
- 5Output@nebutra/agents response envelope
p50 latency
93 ms
events/sec
686/s
providers
2
eval score
88
Usagelocal-embedding.ts
typescriptlocal-embedding.ts
1import { localEmbedding } from "@nebutra/local-embedding";
2
3const result = await localEmbedding.run({
4 tenantId: org.id,
5 // local-embedding is part of the AI runtime — composable with other AI primitives.
6 input: payload,
7});