“data”

Data processing for and with foundation models

Pandas-ai: Conversational data analysis using LLMs and RAG

Incremental engine for long horizon agents

Git for Data

Evidently is an open-source ML and LLM observability framework.

API for searching, scraping, and interacting with the web at scale

Automating high-value generic R&D processes with AI

Event Driven Orchestration & Scheduling Platform for Mission Critical Applications

Open-Source Agentic AI Data Assistant

Multi-modal vector database supporting unified SQL access to structured and unstructured data

Ready-to-run cloud templates for RAG, AI pipelines, and enterprise search with live data.

Apache Hamilton helps define testable, modular, self-documenting dataflows.

The Virtual Feature Store. Turn your existing data infrastructure into a feature store.

A Python scraping library with LLM and direct graph logic

A high-performance observability data pipeline

AI-native HTAP database with Git-for-Data and built-in vector search

Unified multimodal backend for AI data apps

CrateDB is a distributed SQL database for real-time analytics of big data.

Code for Machine Learning for Trading, 3rd edition

Convert documents to structured data effortlessly

PaddleOCR: A powerful OCR toolkit for transforming PDFs/images into structured data

Infinispan is an open source data grid platform and highly scalable NoSQL cloud data store.

Prompt. Generate Synthetic Data. Train & Align Models.

Neum AI is a best-in-class framework for managing vector embeddings at large scale.

A modern finance application for advanced market analytics and investment research.

Interactive tutorials and examples for mastering Milvus with unstructured data applications.

Enterprise Data Warehouse for AI Agents

Deeplake: AI Data Runtime for Agents

Open Source Deep Research Alternative to Reason and Search on Private Data

Open-source context retrieval layer for AI agents

Advancing open-source language models with imperfect data

Agent Skills as a Memory Layer

Bionic, an on-premise ChatGPT replacement with strict data confidentiality.

Unified framework for scaling AI and Python applications

Python library for extracting structured information from unstructured text with precise source grounding and interactive visualization.

FastGPT is a knowledge-based platform for developing and deploying complex question-answering systems using LLMs, offering out-of-the-box capabilities like data processing, RAG retrieval, and visual A

PDF Parser for AI-ready data. Automate PDF accessibility.

Open-source document intelligence platform for building on unstructured data.

The AI search platform

AI-native proxy server and data plane for agentic apps