Found 385 results for vector-database
Self-learning vector memory for AI agents — single-file .rvf cognitive container with HNSW search, episodic Reflexion memory, causal graph + Cypher, 9 RL algorithms, Thompson Sampling bandit, 41 MCP tools, hybrid (BM25 + dense) retrieval, GNN attention. 1
Native Node.js bindings for RuVector Graph Database with hypergraph support, Cypher queries, and persistence - 10x faster than WASM
Self-learning LLM runtime — TurboQuant KV-cache (6-8x compression), SONA adaptive learning, FlashAttention, speculative decoding, GGUF inference
Ruflo CLI - Enterprise AI agent orchestration with 60+ specialized agents, swarm coordination, MCP server, self-learning hooks, and vector memory for Claude Code
RuvLLM native SIMD acceleration - linux-x64-gnu platform
Graph Neural Network capabilities for Ruvector - Node.js bindings
A lightweight, file-backed vector database for Node.js and browsers with Pinecone-compatible filtering and hybrid BM25 search.
High-performance vector database with HNSW indexing - 50k+ inserts/sec, built in Rust for AI/ML similarity search and semantic search applications
Portable WASM embedding generation with SIMD and parallel workers - run text embeddings in browsers, Cloudflare Workers, Deno, and Node.js
Self-learning vector database for Node.js — hybrid search, Graph RAG, FlashAttention-3, HNSW, 50+ attention mechanisms
Ruflo - Enterprise AI agent orchestration for Claude Code. Deploy 60+ specialized agents in coordinated swarms with self-learning, fault-tolerant consensus, vector memory, and MCP integration
RuvLLM native SIMD acceleration - darwin-arm64 (Apple Silicon) platform
RuvLLM native SIMD acceleration - win32-x64-msvc (Windows) platform
SocratiCode — MCP server for local codebase indexing, semantic search, and code dependency graphs. All private, all local via Docker.
VectoriaDB - A lightweight, production-ready in-memory vector database for semantic search
TypeScript port of tcvdb_text — BM25 sparse vector encoder for Tencent Cloud VectorDB
Retrivora AI is a plug-and-play AI engine for RAG chat experiences — generic vector DB + LLM provider, embeddable or standalone.
Memory layer for AI agents over your Obsidian vault. Hybrid retrieval (BM25 + TF-IDF + multilingual ML embeddings, RRF-fused) with BGE cross-encoder reranking, HNSW + int8 quantization, late-chunking, HyDE + sub-question decomposition, agentic RAG, PDFs (
Model Context Protocol server for Pinecone - enables AI assistants to interact with Pinecone indexes and documentation
SQLite vector search extension for Node.js - Cross-platform vector embeddings and similarity search
🦛 CHONK your texts in TS with Chonkie!✨The no-nonsense lightweight and efficient chunking library.
Tembory Memory node for n8n AI Agents with profile, tools, timeline, graph and semantic memory
OpenCode plugin that gives coding agents persistent memory using local vector database
Monomind - Enterprise AI agent orchestration for Claude Code. Deploy 60+ specialized agents in coordinated swarms with self-learning, fault-tolerant consensus, vector memory, and MCP integration
Node.js bindings for Infiniloom - AST-aware code context engine for RAG and vector databases. Tree-sitter parsing, PageRank ranking, BLAKE3 content-addressable chunks, 27+ tokenizers.
RuvLLM native SIMD acceleration - linux-arm64-gnu platform
Monomind CLI - Enterprise AI agent orchestration with 60+ specialized agents, swarm coordination, MCP server, self-learning hooks, and vector memory for Claude Code
RuvLLM native SIMD acceleration - darwin-x64 (Intel Mac) platform
Standalone vector database with SQL, SPARQL, and Cypher - powered by RuVector WASM
MCP server for agent automation: persistent memory and deterministic workflow execution for AI agents and chats
Native TypeScript AI memory system and MCP server (Zero-LLM, LanceDB)
Monomind CLI - Enterprise AI agent orchestration with 60+ specialized agents, swarm coordination, MCP server, self-learning hooks, and vector memory for Claude Code
Universal Knowledge Protocol™ - World's first Triple Intelligence database unifying vector, graph, and document search in one API. Stage 3 CANONICAL: 42 nouns × 127 verbs covering 96-97% of all human knowledge.
VelesDB for WebAssembly - Vector search in the browser
Official TypeScript/JavaScript SDK for CortexDB - Multi-modal RAG Platform with advanced document processing
n8n community node for Mem0 Self-Hosted with LangChain-compliant AI memory
Unified meta-package for RuVector WASM modules - learning, economy, exotic AI, nervous system, and attention
TypeScript/JavaScript SDK for Dakera AI memory platform
Tembory node for n8n AI Agents with profile, tools, timeline, graph and semantic memory
VelesDB TypeScript SDK: The Local Vector Database for AI & RAG. Microsecond semantic search in Browser & Node.js.
ChromaDB vector store adapter for semantic documentation search
MCP server exposing LogosDB semantic search to Claude Code and other MCP clients
Lightweight vector database with SQL, SPARQL, and Cypher - runs everywhere (Node.js, Browser, Edge)
OpenCode 跨会话记忆插件 — 本地优先、零配置的持久化 AI 记忆系统
Fast semantic vector database (HNSW + mmap) - Node.js bindings
Mnemo core — persistent semantic memory engine (ONNX embeddings + HNSW + sql.js)
Zero-boilerplate RAG for browser AI agents. WASM HNSW vector search + background ONNX embedding + OPFS-cached vROM cartridges.
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
Local-first memory and prompt-cache layer for Claude Code
Genkit plugin for Supabase pgvector vector-store indexing, semantic search, and retrieval in TypeScript RAG apps.
OpenCode plugin that gives coding agents persistent memory using local vector database
TypeScript SDK for Z3rno — AI agent memory database
Intelligent AI Gateway — Semantic cache, Privacy Firewall, and Autonomous Cost-Optimization for AI Agents.
Decentralized vector database for AI agents. Rust HNSW + Solana on-chain provenance.
Enterprise AI agent orchestration for Claude Code: 60+ specialized agents, swarm coordination, self-learning hooks, fault-tolerant consensus, vector memory, and MCP integration. Fork of Ruflo by @ruvnet (https://github.com/ruvnet/ruflo).
High-performance Node.js native bindings for Facebook FAISS with float and binary indexes, CLI tooling, optional GPU migration hooks, async operations, persistence, and vector utility helpers.
Buzo AI retrieval observability SDK — mirror your AI agent's vector retrievals and LLM generations to Buzo for usage-weighted findings, served-flagged alerts, cited-flagged attribution, and dead-vector detection.
OpenCode plugin that gives coding agents persistent memory using local vector database
Local-first memory and retrieval engine of NuOS — vector storage, four-layer hierarchical retrieval, provenance, temporal reasoning, write-intent support
A unified JavaScript/TypeScript SDK for seekdb that supports Server mode and OceanBase mode
DSPy.ts 2.0 - Advanced declarative AI framework with multi-agent orchestration, self-learning capabilities, and state-of-the-art optimizers. Powered by AgentDB, ReasoningBank, and Swarm architecture.
Monobrain - Enterprise AI agent orchestration for Claude Code. Deploy 60+ specialized agents in coordinated swarms with self-learning, fault-tolerant consensus, vector memory, and MCP integration
TypeScript SDK for Vectorizer - High-performance vector database. Ships the VectorizerRPC binary transport (default in v3.x) plus the legacy REST client.
A TypeScript framework for building hybrid GraphRAG applications using SAP HANA Cloud as the unified backend for knowledge graphs (RDF) and vector embeddings
Embedded vector store for local-first AI applications.
Anvil — AI-powered feature development pipeline (CLI + dashboard)
Advanced AI vector database CLI for PostgreSQL - pgvector drop-in replacement with 53+ SQL functions, 39 attention mechanisms, GNN layers, hyperbolic embeddings, and self-learning capabilities
Self-hosted agentic memory MCP server backed by Qdrant, inspired by supermemory. Provides semantic memory storage, entity/relation knowledge graph, and optional reranking as MCP tools.
Ultra-fast, 50KB vector database powered by Rust + WebAssembly. TTL-aware ephemeral memory for AI agents, 1-bit quantization, HNSW indexing, OPFS persistence.
Professional CLI for LanOnasis Memory as a Service (MaaS) with MCP support, seamless inline editing, and enterprise-grade security
AI-powered MCP server for codebase navigation and LLM prompt optimization
A high-performance, parallelized document ingestion and vectorization pipeline.
n8n node for LogosDB semantic vector database — insert, search, delete, info
A lightweight memory-based vector store with persistent storage support for both Node.js and browser environments. Efficiently store, retrieve, and search vector embeddings with minimal dependencies.
TypeScript library providing persistent memory for AI agents — conversation history, long-term memory with vector search, and automatic fact extraction.
High-performance WebAssembly theorem prover with dependent types, hash-consing (150x faster), Ed25519 proof signatures, MCP support for Claude Code, AgentDB vector search, episodic memory, and ReasoningBank learning. Formal verification with cryptographic
AI-powered Mongoose plugin for intelligent document processing with auto-summarization, semantic search, MongoDB Vector Search, and function calling
rill extension for Qdrant vector database integration
A plug-and-play AI accelerator for RAG chat experiences — generic vector DB + LLM provider, embeddable or standalone.
MCP server for Qdrant with OpenAI-compatible embedding API support (Mistral, OpenAI, Together, Voyage, etc.)
OpenCode plugin that gives coding agents persistent memory using local vector database
TypeScript SDK for Shilp Vector Database API
Standalone Memory SDK - drop into any project for multi-agent orchestration with persistent memory
Prototype MCP Server for CLL
Client-side vector search. Rust/WASM powered, works where pure JS breaks down.
A terminal UI for browsing vector databases (Qdrant, Pinecone, Chroma).
Node.js/TypeScript client for Actian VectorAI Database
Thalamus cognitive hub for OpenClaw: packet handoff, vector memory, routing telemetry, encoder daemon, and multimodal ingest.
Unified knowledge graph + vector memory system for AI agents
An MCP server for semantic documentation search and retrieval using vector databases to augment LLM capabilities.
Cencori - The unified infrastructure layer for AI applications. One SDK for AI Gateway, Compute, Workflow, and Storage.
Comprehensive Cloudflare Workers & Pages integration with config-based patterns, middleware, router, workflows, AI (with audio/music generation, TTS, ASR), React hooks, and multi-tenant support
CLI tool for managing knowledge stores with semantic search
MCP server for integrating Turso with LLMs
Enterprise-grade self-learning AI assistant with military-strength security, 150x faster vector search, and 12+ LLM models
AgentDB v3 - Intelligent agentic vector database with RVF native format, RuVector-powered graph DB, Cypher queries, ACID persistence. 150x faster than SQLite with self-learning GNN, 6 cognitive memory patterns, semantic routing, COW branching, and compreh
Agent Memory OS — semantic memory for AI agents
High-performance vector database with HNSW indexing - 50k+ inserts/sec, built in Rust for AI/ML similarity search and semantic search applications
rill extension for Pinecone vector database integration
SPARC 2.0 - Autonomous Vector Coding Agent + MCP. SPARC 2.0, vectorized AI code analysis, is an intelligent coding agent framework built to automate and streamline software development. It combines secure execution environments, and version control into a
AI-agnostic local memory layer for codebases. Index once, remember forever, switch AI freely.
MCP Server for Claude Code, Cursor, Cline, Copilot, Github Copilot, Windsurf - Visual AI Agent Plan Execution, Approval Workflow, Plan Visualization, Agent Orchestration. See what your AI is thinking before it writes code. Works with Claude, GPT, Gemini,
Official TypeScript SDK for HyperspaceDB gRPC API
Verifiable integrity for AI embedding stores. TypeScript reference implementation.
Ruflo CLI - Enterprise AI agent orchestration with 60+ specialized agents, swarm coordination, MCP server, self-learning hooks, and vector memory for Claude Code
rill extension for ChromaDB vector database integration
Official n8n community nodes for IONOS Cloud services (Infrastructure, Certificate Manager, DNS, CDN, AI Model Hub)
Production-ready RAG (Retrieval-Augmented Generation) for JavaScript & React - Built on official Ollama & LM Studio SDKs with Hybrid Search, Reranking, Query Transformation, Caching, Conversation Management & Evaluation
AI agent orchestration for Claude Code — swarm coordination, vector memory, self-learning hooks, and MCP tools
CortexDB JavaScript/TypeScript SDK — A RAG-powered memory database client.
Official TypeScript/JavaScript SDK for the Hypersave API - Your AI-powered memory layer
PostgreSQL + pgvector provider for Khavee AI SDK
A comprehensive n8n community node for Upstash providing Redis, Kafka, QStash, and Vector database operations. Includes 12 resource categories and 80+ operations for serverless data management.
Milvus vector database configuration generator CLI
MCP server for enhanced Qdrant vector database functionality
📚 Model Context Protocol server for AI-powered storytelling with Narrative Knowledge Graph - extract characters, locations, relationships and search your stories semantically.
Ezra (עזרא) - The Scribe Who Restores and Enforces Standards. Enterprise AI agent orchestration for Claude Code. Deploy 60+ specialized agents in coordinated swarms with self-learning, fault-tolerant consensus, vector memory, and MCP integration
Seven-layer code memory — benchmarked. AST-aware chunking, symbol graph with PageRank, semantic + BM25 retrieval. Personal, team-shared, offline-first, any embedding or LLM provider. MCP server + CLI.
ACORN predicate-agnostic filtered HNSW in WebAssembly — high-recall vector search with arbitrary metadata filters, for browsers, Cloudflare Workers, Deno, and Bun
AST-aware code context engine for RAG, vector databases, and AI assistants. Tree-sitter parsing, PageRank ranking, BLAKE3 content-addressable chunks. Integrates with Pinecone, Weaviate, Qdrant. Supports Claude, GPT-5, GPT-4o, Gemini, Llama (27+ tokenizers
Local code indexing tool with semantic search for Claude Code - MCP server and CLI
MCP client configuration for REMBR - semantic memory for AI agents, RLMs, and multi-agent systems
Zero-dependency vector store for Node.js and browser. Float32, Int8, and 1-bit quantization with IVF indexing and Matryoshka search.
RAG (Retrieval Augmented Generation) library for MongoDB Vector Search
Professional AI/ML Engineering toolkit: Prompt engineering, LLM integration, RAG systems, AI safety with 12 expert plugins
A production-ready, provider-agnostic Node.js SDK for End-to-End RAG pipelines.
VS Code RLM integration - Recursive Language Model patterns with GitHub Copilot agents, skills, and semantic memory
Local-first chat memory with vector search for LLM applications. No cloud. No API keys. Your data stays on your device.
AgentDB with optimized ONNX embeddings - 100% local, GPU-accelerated AI agent memory
A Model Context Protocol server for fetching and storing documentation in a vector database, enabling semantic search and retrieval to augment LLM capabilities with relevant documentation context.
Official TypeScript SDK for Vorkath (distributed OLTP + vector + BM25). Works on Node.js, Bun, Deno, Cloudflare Workers, and modern browsers.
Weaviate vector database configuration generator CLI
MCP server for AI memory management using Letta - Standard MCP format
A complete Retrieval-Augmented Generation system using pgvector, LangChain, and LangGraph for Node.js applications with dynamic embedding and model providers, structured data queries, and chat history - supports OpenAI, Anthropic, HuggingFace, Azure, Goog
Local RAG system for AI agent memory using ChromaDB and sentence-transformers
JavaScript & TypeScript Client SDK for CyborgDB: The Confidential Vector Database
MCP server for Morphik multimodal database
A RAG (Retrieval-Augmented Generation) package that integrates multiple data sources (CSV, Database, Pinecone, Elasticsearch) with Groq LLM for intelligent Q&A
MCP Server for Qdrant Vector Database - Search, manage collections, and points
MCP server for INECTA Food Knowledge Base - semantic search and dependency analysis for Business Central AL code and documentation
n8n community node for Zilliz vector database with full RAG support
Pinecone vector database configuration generator CLI
A high-performance local MCP server for semantic code search, summarization, and RAG.
Lightweight semantic search database with text embeddings for Node.js and Bun
MCP server for RuVector Format (RVF) vector database — stdio and SSE transports
Auxta SDK is a library to interact with Auxta, an AI-powered vector database. It provides a simple and intuitive interface for developers to perform operations such as querying, inserting, and managing data in Auxta.
MCP server for memory management using Qdrant vector database
Enhanced vector database with HNSW indexing, WAL, error recovery, and production-ready features. Based on Vectra by Steven Ickman.
Native TypeScript AI memory system and MCP server (Zero-LLM, LanceDB)
Official SDK for Jabrod Cloud API - RAG as a Service
Unified AI Context Engineering - Intelligent context for Claude, Copilot, Cline, and more with OpenRouter-powered initialization
An MCP server for semantic documentation search and retrieval using vector databases to augment LLM capabilities.
Triple-layer memory system for AI agents — SQLite + Qdrant + Postgres/AGE
Semantic memory search core library for TypeScript/Node.js
🎨 Professional Angular architecture diagram builder with 47+ pre-built components, drag-and-drop interface, nested grouping, custom shapes, and JSON export. Perfect for cloud infrastructure, AI/ML systems, and technical diagrams.
TypeScript/JavaScript SDK for PersistQ - AI-powered persistent memory storage
Enterprise-grade self-learning AI assistant with military-strength security, 150x faster vector search, and 12+ LLM models
Neo4j-compatible hypergraph database in WebAssembly - Cypher queries, SIMD optimization, knowledge graphs
MCP server for semantic code search using Tree-sitter, embeddings, and Qdrant vector database
Modern desktop chat interface for Ollama with RAG, code canvas, tool calling, and advanced thinking modes
🍎 MCP server for semantic search through Apple developer documentation, WWDC transcripts, and code examples. 16K+ documents indexed for AI agents.
N8N community node package — full assistant set: Mem0 memory, Gotenberg PDF, Telegram Bot, Outline Wiki, Qdrant vector store (regular + AI tools)
AI-Native, PostgreSQL-compatible database with vector search, HNSW indexing, and full ACID compliance. All 421 tests passing. NEW: Window Functions, CTEs, Subqueries, JOINs, GROUP BY/HAVING!
N8N community node for Mem0 - intelligent memory layer for AI applications
Ruflo CLI - Enterprise AI agent orchestration with 60+ specialized agents, swarm coordination, MCP server, self-learning hooks, and vector memory for Claude Code
Official TypeScript/JavaScript SDK for AINative Studio APIs
MCP server for indra_db - a content-addressed graph database for versioned thoughts
AINative ZeroDB Memory MCP Server - 6 optimized tools for agent memory with smart context management, semantic search, and automatic pruning. 92% smaller than monolithic server. Production-ready for Claude, Windsurf, and AI assistants.
WebAssembly bindings for SimpleVectorDB - A fast HNSW-based vector database
React Hook for [`indexed-vector-store`](https://github.com/danielivanovz/indexed-vector-store) package. Used for [demo](https://github.com/danielivanovz/indexed-vector-store-demo) and deployed at my [website](https://app.danielivanov.me/vector-database/).
MCP Server for AI Embedding and RAG functionality
MCP Server for Claude Code, Cursor, Cline, Copilot, Github Copilot, Windsurf - Visual AI Agent Plan Execution, Approval Workflow, Plan Visualization, Agent Orchestration. See what your AI is thinking before it writes code. Works with Claude, GPT, Gemini,
JavaScript/TypeScript client for Aquiles-RAG
The memory layer for AI applications — hybrid RAG retrieval, PII shield, polyglot storage
The memory layer for Personalized AI in Typescript
An MCP server for semantic documentation search and retrieval using vector databases to augment LLM capabilities.
Engram - High-performance hierarchical, temporal, multi-modal AI memory format with neural-inspired architecture
MCP-сервер для поиска UI-компонентов с использованием RAG на базе LanceDB и GigaChat
A lightweight web-based viewer for LanceDB databases with advanced table browsing, column filtering, and SQL WHERE clause support
MCP persistent memory service — let AI assistants remember across sessions. Powered by Qdrant vector search + official embeddings (via OpenAI-compatible relay or Gemini Vertex AI) with Ollama fallback and hybrid retrieval (vector + BM25).
OpenCode Orchestrator - Enterprise AI agent orchestration platform. Deploy 60+ specialized agents in coordinated swarms with self-learning, fault-tolerant consensus, vector memory, and MCP integration
LangChain integration for LambdaDB vector database
Official Node.js SDK for Devabase - Backend for RAG/LLM Applications
A Node.js TypeScript module for RAG functionality using nomic-embed-text-v1.5 and sqlite-vec
CLI tool for memsearch-ts - semantic memory search
Lightweight semantic search database with text embeddings for Node.js and Bun
N8N community node for Qdrant vector store — semantic search, embedding storage, and full collection management for AI Agent workflows
n8n community nodes for GitLab Code Splitter API with Stem4 GCP integration
HyperspaceDB integration for n8n (Vector Store, Embeddings, API)
n8n community node for Mem0 – intelligent memory layer for AI applications
Advanced RAG (Retrieval-Augmented Generation) knowledge base nodes for n8n
Lightweight In-Memory Vector Database for Fast Similarity Search
Universal memory layer MCP server for Zilliz Cloud - enables continuous conversations across all LLMs and agents
Memory infrastructure for AI agents. Your Qdrant, your hardware, our intelligence.
BaseGrid SDK - Memory Infrastructure for AI Agents | Sub-200ms Retrieval
High-performance Node.js client for Antarys vector database with HTTP/2, connection pooling, and intelligent caching
Global, AI-Powered Translation CLI for every project.
MCP server for eustore.dev — autonomous sovereign storage + vector database for AI agents. S3-compatible storage and semantic vector search, fully API-driven, no dashboard needed.
Universal Dev AI — AI-agnostic context engineering + RAG for game development
MCP for adding semantic memory to AI coding agents
CLI tool to create modern Node.js projects with TypeScript, AI capabilities, and more
HTTP/gRPC server for RuVector - REST API with streaming support
RAG (Retrieval-Augmented Generation) system for Moodle development with Claude Code CLI
Admin UI components for Deno AI Toolkit workspace management
A Model Context Protocol (MCP) server that provides semantic search over Pinecone vector databases using hybrid search (dense + sparse) with reranking.
Unified integration layer combining ultra-fast symbolic AI reasoning with intelligent synthetic data generation for context-aware applications
数字永生服务 | 认知延续基础设施 - Personal memory management system for digital immortality with conversation memory
Módulo de indexação e busca semântica para CodeRAG - Suporta embeddings locais (Ollama) e bancos vetoriais
The Agent-Native Retrieval Engine — Hybrid Vector + Reasoning + Memory for AI Agents. HNSW indexing, tree-based reasoning retrieval, built-in RAG, MCP server, multi-agent orchestration, and agent memory architecture.
Simple, lightweight RAG / memory layer using LanceDB + local embeddings (Xenova/all-MiniLM-L6-v2)
An AI memory system enabling personalized, context-aware interactions through advanced memory management and emotional intelligence
Semantic Web Memory for Intelligent Agents
A Model Context Protocol server for fetching and storing documentation in a vector database, enabling semantic search and retrieval to augment LLM capabilities with relevant documentation context.
SQL-Native AI Memory Fabric for JavaScript/TypeScript, powered by sqlite-vec and Google GenAI.
In-browser vector database with pluggable storage and Rust WASM compute modules
WASM bindings for ruvector-verified: proof-carrying vector operations in the browser
Vector database abstraction layer for Neural Tools
A reusable Backstage backend plugin that provides RAG (Retrieval-Augmented Generation) capabilities including embedding providers and vector stores for knowledge retrieval.
Angular bindings for SimpleVectorDB - A fast HNSW-based vector database
Memphora SDK - Persistent memory layer for AI agents (JavaScript/TypeScript)
AI memory system for Claude Code - Three-layer architecture with semantic search, knowledge graphs, and intelligent retrieval
Give your AI a memory — mine projects and conversations into a searchable palace. No API key required.
An MCP server for semantic documentation search and retrieval using vector databases to augment LLM capabilities.
Distributed clustering and coordination for RuVector - auto-sharding, Raft consensus integration
CortexDB JavaScript/TypeScript SDK — A RAG-powered memory database client.
Privacy-first LLM integration with SQL visualization, local knowledge base, comprehensive privacy monitoring, and API connections dashboard
n8n community node for Milvus vector database with enhanced metric type switching
TypeScript SDK for FerresDB vector database
Stratus SDK - TypeScript client for the Stratus API with embedding compression utilities
MCP server for enhanced Qdrant vector database functionality
N8N community node for Mem0 - intelligent memory layer for AI applications
N8N community node for Mem0 - intelligent memory layer for AI applications
Brain-inspired, model-agnostic persistent memory for LLMs. Learn, recall, forget — like a brain. Works with OpenAI, Claude, Gemini, Llama.
Context-aware semantic search MCP server for OpenCode and other MCP clients
Scrape and chunk websites into AI-ready training data for RAG, LLM fine-tuning, and vector databases
Advanced memory management system for AI agents with semantic retrieval, hierarchical structures, and multi-agent support
ClawMemory plugin for OpenClaw - cloud-based semantic memory for AI agents
TypeScript/JavaScript client for d-vecDB - High-performance vector database with persistent metadata, WAL corruption protection and GPU acceleration
Embedded vector database for JS/TS — like SQLite for vectors. WASM-powered, runs in browser, Workers, and Node.js.
Hierarchical markdown chunking for RAG systems with AI-powered context summarization
A TypeScript/JavaScript module for implementing Retrieval-Augmented Generation (RAG) using Qdrant vector database, Google's Generative AI embeddings, and Groq LLM.
Minimal, dependency-free vector database with pluggable ANN strategies (bruteforce, HNSW, IVF), attribute filtering, and persistence. Powered by MoonBit WASM. Runs in Node.js, browsers, and edge runtimes.
MCP server for Milvus knowledge base integration with semantic search capabilities
Unified Vector Search service for 0G Storage — decentralized HNSW index on 0G's sharded KV layer
Easy-to-use semantic search plugin for Supabase with automatic embedding generation and vector similarity search
A tool to process markdown files from GitHub repositories and store them in Upstash Vector
OrbitalMCP - Headless RAG & MCP Service for AI agent long-term memory
MCP server for Recall vector database with background indexing - search and index your code repositories and documentation
A Model Context Protocol server for fetching and storing documentation in a vector database, enabling semantic search and retrieval to augment LLM capabilities with relevant documentation context.
MiniVectorDB with HNSW (AssemblyScript WASM) + Local embedder