Data agents

Easily create LLM vectors for existing Postgres data

ProteoGenomics CLI — terminal-first multi-agent research assistant

Integration of soil metagenomic data for correlation of microbial markers with plant biochemical indicators

AgentFolio integration for Phidata — agent identity, trust & reputation tools

AI agent for F1 data analysis using Claude Agent SDK and FastF1

A modular AI agent framework supporting OpenAI and Anthropic models

An AI-powered data visualization assistant using Plotly

Convert figures from visualization libraries into formats optimized for Large Language Models (LLMs)

A tiny ai to help you visualize data

Visualize your data with Langchain and Plotly through a Plotly agent

Plott Analytics SDK for LangGraph - Automatic analytics tracking for LangGraph

A library for easy integration with Groq API, including web scraping, image handling, and Chain of Thought reasoning

A SciKit for process oriented data science

Parallel inference calls to LLM APIs using Polars dataframes with Pydantic-based structured outputs

Call LLMs, decision models, and embedding models from a Polars DataFrame using native Polars expressions.

Official CLI for the Entity Market Data API.

Official Python SDK for the Entity Market Data API.

A lean GraphRAG library using Postgres/pgvector as the sole database

Python SDK for the Pounce v2 Entity API — search, look up, and enrich 65M+ verified B2B companies.

An open-source python library designed to enhance RAG application performance during data ingestion by skipping files that have already been processed for Dell PowerScale storage.

PQC-signed RAG pipeline chunks. Sign document chunks with ML-DSA at ingestion, verify at retrieval. Prevents vector database poisoning.

Hybrid-reasoning knowledge engine: atomic-fact extraction with semantic nuance, ontology normalization, and agentic multi-hop synthesis. No vector database required.

ProcessGPT Agent Utilities - 도구 로더, 지식 관리, 이벤트 로깅, 데이터베이스 유틸리티

ClickHouse AI Agent - Natural language interface for ClickHouse databases

Self-hosted personal-data context layer for agents (MCP)

`putkoff_chatGPT_API` is a Python module for interacting with OpenAI's GPT models. It simplifies the process of making API calls, managing API keys, and parsing responses, while also providing utility functions to work with timestamps and organize response data.

NER training-data generation built on py-agent-lib. Bring your own labels, LLM, and downstream trainer.

Parallel Python Averager for Climate Data

Fragility function fitting for any data type, with misspecification-robust uncertainty.

pyJsonStorage is a Python package designed to implement basic database functionalities using JSON (JavaScript Object Notation). This package provides various features such as creating a new database, inserting rows, updating, and deleting rows. It leverages the JSON module from Python's core libraries for managing JSON files.

Simple data storages package

A Python package to read/write Minecraft Bedrock leveldb data

Pydantic AI integration for Strale — 250+ business capabilities as agent tools

Use your pydantic models as an ORM, storing data in Redis.

Benign slopsquatting research package

A Python library for managing Airtable data using Pydantic objects

A lightweight, type-safe storage system for Pydantic models with support for multiple backends and persistent storage.

A python data storage backend library.

Python wrapper library providing LoL ddragon data asynchronously

Build agent workflows with memory & tools. Autonomous AI agents toolkit. Perfect for AI agents and LLM applications.

A package to store data on the hard disk (HD) and make it available to all Python applications running locally!

Python wrapper of metfrag 2.3 for ms/ms based identification of LCMS data

A simple python package to convert geo data to OpenAir format

A Python package for querying Hive data and processing with AIGC applications

Python Client for Pyronear data curation API

A research toolkit for Swarm Robotics

A set of helper classes that abstract some of the more common tasks of a typical RAG process including document loading/web scraping.

Python Ragic API client for data loading and manipulation.

Tool to calculate technical analysis indicators in a continuous time series data

AI-Powered Test Intelligence SDK for Python - pytest plugin with automatic failure analysis

An integration of Qdrant ANN vector database backend with Haystack

MCP server for reading LlamaIndex documents stored in Qdrant vector database

An integration of Qdrant ANN vector database backend with txtai

AI-powered quant research knowledge base & brainstorm agent

A collection of storage modules like for file management, metadata and more

A Python package for preprocessing and augmenting data for large language models by quantum Neural networks.

Synchronize users and data between radosgw clusters

A project to show good CLI practices with a fully fledged RAG system.

The rag-core-api contains the API layer for the RAG template for document retrieval, question answering, knowledge base management in the vector database and more.

Agentic RAG pipeline failure diagnosis — no database, no LLM API, no cloud

Generate QA pairs from JSON documents to evaluate RAG pipelines

Enterprise-grade data poisoning detection & alerting for RAG systems

This repository contains a project that implements a Retrieval-Augmented Generation (RAG) system using the LLaMA3 model. The project focuses on creating embeddings for instructions of a professional bioinformatic software to help users conduct biology research.

PostgreSQL pgvector-based RAG memory system with MCP server

AI-powered document analysis and query generation tool with RAG capabilities

Scan RAG documents for hidden prompt injections, invisible text attacks, and data exfiltration payloads before they enter your vector database.

Generate startup ideas grounded in real YC data using Retrieval-Augmented Generation (RAG).

A Python SDK for sending RAG trace node data

RAGCAR: Retrieval-Augmented Generative Companion for Advanced Research

RagChat transforms unstructured data for LLM interaction.

Datagen & RagEval for various LLM (Large Language Model) for RAG Apps

Build knowledge bases for RAG

A patent-pending, embedded, multimodal RAG database that performs automated ingestion, hybrid vector+keyword search, and offline retrieval entirely inside a portable single-file SQLite container.

Useful Tools for Database, RAG and LLM

A library for generating dataset and evaluating these datasets on RAG based solutions

Efficient RaggedBuffer datatype that implements 3D arrays with variable-length 2nd dimension.

RAG dataset generator

Simple vector database operations with Qdrant

Version control for your RAG pipeline — compare embedding models on your own data

Permission-aware retrieval for RAG applications

scraping stuff

A simple, clean Python library for Retrieval-Augmented Generation (RAG)

MCP Server for RAG documentation search with Qdrant and Ollama

ragl: retrieval-augmented generation (RAG) for text.

Local-first RAG toolkit backed by a single SQLite database

RAGoon : High level library for batched embeddings generation, blazingly-fast web-based RAG and quantized indexes processing ⚡

A RAG system for creating knowledge bases from different document formats

RAG in 3 functions. Ingest any data source into vector databases.

A modular RAG SDK for ingesting web, document, and API sources, chunking them, and storing embeddings in pluggable vector databases.

Unified data extraction and preprocessing toolkit for Retrieval-Augmented Generation (RAG) pipelines.

The Fastest Way to Audit Your RAG - Generate QA datasets & evaluate RAG systems in Colab, Jupyter, or CLI. Privacy-first, any LLM, visual reports.

ragsearch is a Python library designed for building a Retrieval-Augmented Generation (RAG) application that enables natural language querying over both structured and unstructured data. This tool leverages embedding models and a vector database (FAISS or ChromaDB) to provide an efficient and scalable search engine.

DataStax RAGStack

DataStax RAGStack Colbert implementation

DataStax RAGStack Knowledge Graph

DataStax RAGStack Graph Store

DataStax RAGStack Langchain

DataStax RAGStack Llama Index

A package that abstracts most of the utilities used in RAG applications

Production-grade RAG toolkit for document ingestion and retrieval with hybrid search support