chroma-core/chroma
Chroma is an open-source search and retrieval database specifically designed for AI applications, supporting document retrieval and vector embeddings.
Awesome AI Agents › RAG and Business Analytics
import-ai/omnibox
OmniBox is an open-source, cross-platform AI knowledge hub built from several components released as separate repositories: a web front end, a backend, an ingestion and reasoning service called Wizard, and a browser extension. The stated workflow is collect first, then ask. Content enters the system through a browser extension that saves the main content of a web page, through direct upload of files such as PDF, Word, PowerPoint and MP3 that are parsed and indexed end to end, through an iOS quick-capture feature called Flash for voice recordings and text notes, through the iOS share sheet, and through a WeChat bot that accepts files, web pages, videos, voice messages, text and chat records. Stored material can be edited and rendered as Markdown with support for formulas, mind maps, flowcharts, sequence diagrams, Gantt charts and music notation. On top of the indexed corpus the product provides question answering and writing assistance that can draw on both internet sources and the local database. The platform side includes a user and team system with permissions, sharing management, multi-tenancy, multiple interface languages, dark mode and a responsive mobile layout, plus public sharing of agents, folders and documents and an open API. A hosted service is offered at omnibox.pro with email, Google and WeChat login, and the repository documents local deployment as well as a development setup that clones the repository with submodules, copies an example environment file and brings the stack up with a Docker Compose script. The roadmap lists RSS subscription as the remaining planned feature after agent sharing, the WeChat bot, the open API and the mobile app. It targets individuals and teams who want a self-hosted personal or shared knowledge base with retrieval-augmented question answering.
https://github.com/import-ai/omnibox
Also in RAG and Business Analytics
vanna-ai/vanna
Vanna is an open-source Python framework that uses Retrieval-Augmented Generation and large language models to convert natural language questions into accurate SQL queries for various databases, simplifying data access and querying.
Canner/WrenAI
Wren AI is an open-source Generative Business Intelligence AI agent that enables data-driven teams to interact with their data using natural language to generate SQL queries, visualizations, and reports for smarter business insights.
apecloud/ApeRAG
Production-ready RAG platform combining graph, vector, and full-text retrieval with AI agents, multimodal document parsing, MCP support, and enterprise deployment features.
newrelic/newrelic-ruby-agent
The New Relic Ruby agent is a comprehensive performance monitoring tool for Ruby applications that helps identify issues, analyze business data, and improve customer experience.
zhongyu09/openchatbi
Open source chat-based business intelligence agent built on LangGraph and LangChain that converts natural language to SQL, runs Python analysis and returns plots, forecasts and anomaly explanations.
bagofwords1/bagofwords
Bag of Words is an open-source agentic analytics platform that connects any LLM to company data, giving each agent scoped data, tools, credentials and permissions for reports, dashboards and automations.
superagent-ai/super-rag
Super-Rag is a high-performance RAG pipeline offering summarization, retrieval, reranking, and code interpretation for AI applications through a simple and production-ready REST API.