NodeJS implementation of @Qdrant/fastembed
FastEmbed embedding model adapter for Anvia.
Local embedding model integration for Mastra, powered by ONNX Runtime.
Fork of https://github.com/Anush008/fastembed-js/LICENSE using onnxruntime-web for greater compatibility
This package provides a FastEmbed embedding model integration for use with Mastra Memory.
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
Engram Memory Community Edition - Persistent semantic memory for AI agents via Qdrant + FastEmbed
OpenClaw native memory plugin powered by NEXO Brain — Atkinson-Shiffrin cognitive memory, semantic RAG, trust scoring, and metacognitive guard.
CLI for tmux session management, git workflow helpers, and an AI agent layer.
TS/JS implementation of Qdrant BM42
MCP server for memory management using Qdrant vector database
Local SQLite memory engine for Oh My Pi agents
Chain-of-Agents based article generation based on repository analysis.
MCP server for enhanced Qdrant vector database functionality
RAG module for the UBC GenAI Toolkit
TS/JS implementation of Qdrant BM42
Persistent, semantic memory for Claude Code via MCP — local-first, zero config.
MCP server providing Scryer Prolog RAG + debugging via Qdrant
SIMD-accelerated MaxSim (ColBERT/ColPali), cosine similarity, diversity (MMR/DPP), token alignment/highlighting for vector search and RAG. Supports text and multimodal late interaction.
Semantic router for nodejs for my personal use, pretty straightforward, inspired by semantic router by aureliolabs
Embeddings module for the UBC GenAI Toolkit, providing a unified interface for creating embeddings from text.
A persistent memory MCP server for AI coding agents — stores, searches, and retrieves atomic learnings per repository.
Autonomous AI agent with Mastra, memory, planning, and Telegram integration
Library for generating vector embeddings, reranking locally.
FastEmbed integration for LumosAI vector storage - local embedding generation
Rig vector store index integration for Fastembed. https://github.com/Anush008/fastembed-rs
Standalone ingest-to-pgvector: source -> chunker -> embedder -> extractor -> table. int8 BGE by default; bakeoff matrix evaluator built in. Cross-language wire-format compatible with the Python `chunkshop` package.
Clark Hash: stateless sparse Johnson-Lindenstrauss sketches for neural embeddings
Local embedding model backend for Blazen using fastembed-rs (ONNX Runtime)
Embedding providers (local + cloud) for Anamnesis. Local default: fastembed-rs.
Shared embedding infrastructure for Ixchel with pluggable providers
Shared embedding abstraction + fastembed-backed implementation for trusty-* projects
Anamnesis adapter for Claude Code (~/.claude/projects)
Anamnesis adapter for OpenAI Codex (~/.codex/sessions, ~/.codex/conversations)
Generic MCP adapter — import memory from any MCP-aware server
A Ruby port of FastEmbed - fast text embeddings using ONNX Runtime
Provides RobotLab::DocumentStore — a thread-safe, in-memory semantic search store backed by fastembed (BAAI/bge-small-en-v1.5). Store text documents by key and retrieve the closest matches to a natural-language query using cosine similarity. Works standalone or as a drop-in extension for robot_lab agents and networks.
LEANN (Lightweight Embedding-Aware Neural Neighbor) is a Ruby gem for building and searching vector indexes with minimal storage. It provides semantic search and RAG capabilities with a beautiful, simple API. Supports multiple embedding providers: RubyLLM, OpenAI, Ollama, and FastEmbed.