A rag component for Convex.

A a collection of languages stemmers and stopwords for Lunr Javascript library

No description provided.

Command-line interface for vibe-agent-toolkit

Convex component for AI agents with persistent chat threads, tool calling, streaming, and RAG.

A robust, strictly-typed Node.js and Browser library for parsing office files (.docx, .pptx, .xlsx, .odt, .odp, .ods, .odg, .pdf, .rtf, .csv, .md, .html, .epub, .tex) and generating high-fidelity outputs in DOCX, ODT, LaTeX, Markdown, HTML, CSV, RTF, PDF,

Local-first memory & context harness for coding agents

Local RAG MCP Server - Easy-to-setup document search with minimal configuration

> LlamaCloud is a new generation of managed parsing, ingestion, and retrieval services, designed to bring production-grade context-augmentation to your LLM and RAG applications.

DuckDB vector store provider for Mastra - embedded high-performance vector storage with HNSW indexing

OpenCode plugin for local-first RAG-based semantic code search

LLM-agnostic document indexing for js/ts - bring your own LLM and text

Semantic Intelligence for Large-Scale Engineering.

The official Pinecone TypeScript SDK for building full-text and vector search applications.

htmlparser2 tree adapter for parse5.

Declare LLM prompts with TSX

A TypeScript library for Retrieval-Augmented Generation (RAG) within the QVAC ecosystem. Build powerful, context-aware AI applications with seamless document ingestion, vector search, and LLM integration.

Dataset package for Workglow.

A tree-based markdown text splitter that understands document structure to create semantically meaningful chunks for RAG applications

Extract clean, timestamped YouTube captions, subtitles, transcripts, and video metadata for AI summaries, RAG, search, and slide-ready workflows.