Create text embeddings locally with EmbeddingGemma (ONNX)

n8n nodes for Ollama embeddings - Dynamic model loading + Support for Qwen, EmbeddingGemma, Nomic and more. Generate text embeddings for vector stores and AI applications.

Node.js wrapper for EmbeddingGemma — local vector embeddings for semantic search

<msc-built-in-ai-embedding /> is a web component based on Chrome Built-in AI Semantic Embedder API. Web developers could use <msc-built-in-ai-embedding /> to generate vector embeddings with EmbeddingGemma and provide vivid features like semantic search or

OpenClaw llama.cpp embedding provider plugin

High-performance local RAG for Markdown: contextual FTS5, HNSW vector search, weighted RRF, and on-device ONNX or llama.cpp embeddings. Bun-only.

Claude Embedding Search is an intelligent code search system that uses Google's EmbeddingGemma model and AST-based chunking to provide semantic search capabilities for Python codebases, integrated wit

Polyfills for the Built-in AI Task APIs (Summarizer, Writer, Rewriter, etc.)

picoLLM Inference Engine is a highly accurate and cross-platform SDK optimized for running compressed large language models.

First-class opt-in alternative to @graphorin/embedder-transformersjs for the Graphorin framework. Wraps the local Ollama HTTP API to produce dense embeddings via models such as `nomic-embed-text` (768-dim, multilingual default), `mxbai-embed-large` (1024-

On-device AI for Expo — run Gemma 4, Apple Foundation Models & ML Kit locally: streaming, structured output, tool calling, embeddings & RAG, Vercel AI SDK provider, zero API keys

Picovoice PicoLLM Node.js chat and completion demos

Picovoice picoLLM Node.js binding

Semantic code and docs search for pi, backed by OpenAI-compatible embeddings and repo-local SQLite indexes.

一个由Hevoon开发的智能个人助手，帮助你高效管理日常任务、知识和工作流程。

Distributed semantic memory + code RAG as an MCP plugin for Claude Code agents

Semantic PATH-aware CLI discovery for Bun-based Linux agent workflows.

Purpose-built session recall engine — persistent daemon with BM25 + vector hybrid search

On-device privacy gate for AI agents — MCP plugin

OpenCode plugin for hidden MemPalace retrieval and autosave via a local Python adapter.