A lightweight and efficient vector database for storing and searching text embeddings in the browser's local storage. The package uses OpenAI's API to generate embeddings for text documents and provides functionality for similarity search, filtering, and
DuckDB vector store provider for Mastra - embedded high-performance vector storage with HNSW indexing
No description provided.
Vector storage, embedding, and semantic search for Semiont
Lightweight vector storage for KB Labs Mind RAG pipeline.
The `@orion-js/vectors` module provides a provider-agnostic interface for vector storage and similarity search, with built-in support for local file-system storage and AWS S3 Vectors.
Knowledge base with document chunking, vector storage, and RAG retrieval
Local-first semantic codebase search for AI coding assistants using MCP, Tree-sitter parsing, and LanceDB vector storage
🔍 LanceDB vector storage for FlowRAG - embedded semantic search, no server required
Retrieval Augmented Generation (RAG) library for document indexing, vector storage, and AI-powered question answering
A Directus extension to integrate vector storage capabilities
Isomorphic storage client for Supabase.
High-performance vector search with HNSW indexing for Bun, Node.js, and Browser. High-recall ANN, 4x vector storage reduction with Int8 quantization.
⚡ Redis storage for FlowRAG - KV and vector storage on Redis Stack
OpenClaw memory plugin using Alibaba Cloud RDS MySQL vector storage
AI Kit - AINative ZeroDB integration for vector storage and memory
🗃️ SQLite graph and vector storage for FlowRAG - knowledge graph with traversal, path finding, and vector search via sqlite-vec
ChromaDB integration for the DaydreamsAI memory system. This package provides persistent vector storage using ChromaDB while using in-memory providers for key-value and graph operations.
Mango queries are sweet ... Chocolate Mango queries are even sweeter! Extended query capability, vector storage, live objects, and triggers for PouchDB
Core library for embedding, chunking, vector storage, and hybrid search
A lightweight LanceDB wrapper for vector storage, memory management, and schema retrieval
No description provided.
MCP server for codebase indexing with Voyage AI embeddings and Qdrant vector storage
Built-in support for popular icon fonts and the tooling to create your own Icon components from your font and glyph map. This is a wrapper around react-native-vector-icons to make it compatible with Expo.
A library for storing and handling vectors with optional quantization.
LLM Chain is a powerful Ruby framework that provides tools for building sophisticated LLM-powered applications. It includes support for prompt management, conversation chains, memory systems, vector storage integration, and seamless LLM provider connections. Key features: • Chain-based conversation flows • Memory management with Redis • Vector storage with Weaviate • Multiple LLM provider support • Prompt templating and management • Easy integration with existing Ruby applications
Lancelot provides a Ruby-native interface to Lance, enabling efficient storage and search of multimodal data including text, vectors, and more.
A batteries-included RAG framework that orchestrates document loading, chunking, embedding, vector storage, retrieval, and generation. Think LangChain for Ruby — simpler, more opinionated, and Rails-native.
Add semantic search and AI-powered chat to any ActiveRecord model. Uses pgvector for vector storage, OpenAI for embeddings, and your existing PostgreSQL database.
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.
pikuri-memory gives a pikuri-core agent durable, long-lived memory: facts about the user and their work that persist across conversations. It wires a +recall+ tool plus an automatic per-turn prefetch onto an agent via +c.add_extension Pikuri::Memory::Extension.new(...)+ inside the +Agent.new+ block — same opt-in shape as +pikuri-tasks+ / +pikuri-vectordb+. Recall is automatic and synchronous (embed + vector search, milliseconds); capture is automatic and asynchronous (an off-the-interaction-path extraction queue), so a turn never blocks on "what should I remember?". Storage is mem0 (https://github.com/mem0ai/mem0) reached over a thin Faraday HTTP client — the append-only +add+ / read-time +search+ model. Only the *user's own words* are fed to extraction (a write-side hygiene rule that structurally drops system/assistant/tool-sourced junk), and recalled context enters the chat as a +:system+ message so it is provenance-tagged and excluded from the next extraction pass. This release ships the Ruby client + extension + tool against a *bring-your-own* mem0 endpoint; a self-managed mem0 sidecar supervisor (the +ChromaServer+-style docker pattern) is a follow-on.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.