voyage-ai

Code search MCP for Claude Code. Make entire codebase the context for any coding agent.

Agentic event-venue operator demo built on MongoDB Atlas. Showcases three-layer memory (long-term, short-term, shared), hybrid retrieval with Voyage AI multimodal embeddings, optional Langfuse traces, and persona-segmented agent decisions during a rain delay scenario at a.

An interactive RAG agent built with LangChain and MongoDB Atlas. Manage your knowledge base, switch embedding models, and tune retrieval parameters on-the-fly through a conversational interface.

Reproducible benchmark and reference pipeline for reranked long-term memory retrieval

This Node.js project contains scripts you can run or refer to as starter code for your chatbot application.

MCP server for University Learning Management System (KLAS).

Semantic code-search (semcode) MCP. Indexes code symbols and commit history. Combines dense embeddings with sparse BM25 vectors for hybrid search that balances semantic understanding with keyword precision.

Polymarket, bulit for Move, powered by AI

A retriever pipeline Python web application that allows users to chat with PDFs and web articles using AI. Combines FAISS vector similarity search and BM25 keyword matching for accurate document retrieval and uses Voyage AI embeddings and LLaMA hosted on Cloudflare Workers AI for question answering.

Python client for embedding and querying documents using VoyageAI and MongoDB Vector Search.

Voice AI for life after hospital discharge. It knows your care plan, answers recovery questions, books follow-ups, and escalates red-flag symptoms to your care team in real time.

An autonomous, state-persistent recovery agent for stranded travelers. Powered by MongoDB Atlas Vector Search & LangGraph.

Citation-grounded, refusal-bounded retrieval for regulated-domain corpora. Citation grounding and refusal-on-low-confidence enforced as deterministic checks in code, not prompt instructions. v0.1: FDCPA.

MongoDB-backed persistent memory for the Vercel AI SDK. Gives your agent five structured memory tiers — Session , Semantic , Procedural , Episodic , and Scratchpad — all stored in MongoDB Atlas with automatic vector search indexes and per-type retention policies.

This demo showcases a store associate application built on MongoDB Atlas, created to streamline product discovery and inventory visibility as part of a unified commerce strategy.

Local BYOK research assistant for PDF libraries with cited answers, hybrid search, and private on-device storage.

A runnable companion to the blog post *"Building E-commerce AI Agents on MongoDB."* A CrewAI shopping agent backed by MongoDB Vector Search, atomic inventory checkout with Change Streams, and (as deploy-ready artifacts) an Atlas Trigger and an Atlas Stream Processing pipeline for post-purchase intelligence.

Build a banking workflow app with Django, MongoDB Atlas Vector Search & Voyage AI using featuring semantic search and retrieval augmented generation (RAG) for document-heavy banking tasks.

This repo is built on top of Google's a2a code example with LangGraph integration. Code origin: https://github.com/google-a2a/a2a-samples/tree/main/samples/a2a-adk-app.

Local document indexer MCP server for semantic search over PDF, Excel, SQL, Markdown, and HTML files using Qdrant and Voyage AI embeddings.