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
zhongyu09/openchatbi
OpenChatBI is a conversational business intelligence tool that lets a user query, analyse and visualise warehouse data by asking questions in plain language. It is built on the LangGraph and LangChain ecosystem and now targets LangGraph v1, exposing both chat agents and workflows. The text-to-SQL path uses schema linking and organised prompt engineering to turn a question into a statement against a supported warehouse such as Presto, PostgreSQL or MySQL. A data catalog component discovers and indexes table structures, stores business explanations for tables and columns, and retrieves them either through vector search when an embedding model is available or through BM25 when it is not. Results can be visualised with Plotly, and a code execution tool runs Python for analysis steps that SQL cannot express, optionally inside Docker. Conversation state and user characteristics persist through LangGraph checkpointing, and the agent asks clarifying questions when a request lacks the context needed to answer it. A specialised data analysis sub-agent built on deepagents takes over complex requests and orchestrates text-to-SQL, in-house time series forecasting, anomaly detection, Adtributor-based multi-dimensional drill-down for root cause investigation, and Python execution, covering trend forecasting, anomaly explanation, multi-metric correlation and combined business analysis. MCP tool integration is configuration driven and also provides access to external knowledge bases alongside the catalog-based retrieval. Two sample web interfaces ship with the project, one simple and one streaming, built with Gradio and Streamlit and intended to be embedded into other applications. The project requires Python 3.11 or newer and an LLM provider, is installed with uv or pip, and is aimed at data teams who want a self-hosted natural language layer over an existing data warehouse.
https://github.com/zhongyu09/openchatbi
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.
import-ai/omnibox
Cross-platform self-hostable AI knowledge hub that collects web pages, files and voice notes, indexes them end to end, and answers questions or drafts text over the local and internet corpus.
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.
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.