NodeJS implementation of @Qdrant/fastembed

FastEmbed ONNX-based local embedding provider for @vivantel/rag-core

FastEmbed embedding model adapter for Anvia.

Local embedding model integration for Mastra, powered by ONNX Runtime.

Local QQL execution for Node.js with qdrant-edge and FastEmbed.

Local QQL execution for Node.js with qdrant-edge and FastEmbed.

Local QQL execution for Node.js with qdrant-edge and FastEmbed.

Local QQL execution for Node.js with qdrant-edge and FastEmbed.

Fork of https://github.com/Anush008/fastembed-js/LICENSE using onnxruntime-web for greater compatibility


Python sidecars for Agon AI — semantic embeddings (fastembed/MiniLM) and tree-sitter syntax validation. Bridged from KERN via stdin/stdout JSON. Ships .py files that the @kernlang/agon-core bridges spawn at runtime.

This package provides a FastEmbed embedding model integration for use with Mastra Memory.

Engram Memory Community Edition - Persistent semantic memory for AI agents via Qdrant + FastEmbed

Retrieval — chunk · embed · search. Zero runtime deps: the vector store (Qdrant) and embedder (fastembed) are injected via ports; namespace is injected. Case + firm-archive RAG.

Pluggable text→vector embedding provider — generic EmbeddingProvider interface, config-driven model resolution, async batch-first API (AsyncIterable). Default: fastembed (local ONNX, >=3 model dims proven). Loud-fail: createEmbeddingProvider() throws Reso

MCP Server para busca semântica na Knowledge Base do Claude Agents v1.4.6 (ChromaDB + FastEmbed BGE-small-en-v1.5 — ADR-001). v1.1.6 alinha com release MAJOR v1.4.6 — Code Hygiene (Pacote A: file-size-guard, executor-file-scope, agents.md per-subdir; Paco

TS/JS implementation of Qdrant BM42

Local SQLite memory engine for Oh My Pi agents

TeamBrain hybrid retrieval: SQLite FTS5 + sqlite-vec + RRF behind a RetrievalBackend interface

Hosted enterprise Tandem engine binary distribution for Linux x64