Python agents

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

A medley of tools to make RAG-based applications.

A modular RAG library with embeddings and vector store support

RAG-LAB is an open-source lighter, faster and cheaper RAG toolkit supported by Target Pilot, designed to transform the latest RAG concepts into stable and practical engineering tools. The project currently supports GraphRAG and HybridRAG.

Python tools to create a custom top down raglan sweater

Embedding diagnostics toolkit for RAG systems

RAGLens CLI for debugging retrieval behavior in RAG systems

Portable memory for small text corpora - create searchable .raglet files

Librería para consultas RAG

Modular Retrieval-Augmented Generation: hybrid search, reranking, CRAG, Self-RAG, agentic and GraphRAG pipelines

RAGLight is a lightweight and modular Python library for implementing Retrieval-Augmented Generation (RAG). It enhances the capabilities of Large Language Models (LLMs) by combining document retrieval with natural language inference.

Lineage-aware RAG engine for auditable, reproducible, versioned retrieval and answers

Production-ready RAG pipeline evaluation and observability platform

A Python toolkit for Retrieval-Augmented Generation (RAG) with DuckDB or PostgreSQL.

Local-first RAG-lite CLI: condense docs into structured Markdown, then index/query with Chroma + hybrid search

Local-first RAG toolkit backed by a single SQLite database

A tool for uploading and embedding documents for RAG systems

Local-first, provider-agnostic RAG toolkit

Stateful RAG kernel with corpus nectar — agents know what's in the corpus before any query runs

RAGmap is a simple RAG visualization package for exploring document chunks and queries in embedding space

A package for creating retrieval-augmented generation apps

RAGMax - Advanced RAG memory system for AI platforms via MCP

Monitor your LLM calls. Test your LLM app.

A package for integrating RagMetrics with LLM calls

A modular framework for evaluating and optimizing RAG pipelines.

AWS extensions for Ragna

lightweight Extract-Transform-Load (ETL) framework for Python 3+

A lightweight personal AI assistant framework

RAGNARDoc (RAG Native Automatic Reingestion for Documents) is a tool that runs natively on a developer workstation and automatically ingests local documents into various Retrieval Augmented Generation indexes. It is designed as a companion app for workstation RAG applications which would benefit from maintaining an up-to-date view of documents hosted natively on a user's workstation.

Local-first evaluation framework for RAG pipelines and AI agents

Hybrid structure-aware retrieval — BM25 + embeddings + document graph expansion. Runs fully offline, no API key required.

Python SDK for the Ragnerock API.

Multi-knowledge-base RAG system with MCP integration

Documentation RAG pipeline with a Textual dashboard and MCP server

LLM-retrieval based knowledge grounding

RAG framework

Handle Bottle.py errors with love <3

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

Official Python SDK for the Ragora RAG API - Build AI-powered knowledge bases

Common utilities

Rag

Scrapper

A tool for reference-assisted assembly

A Python package for RAG pipelines using OpenAI and FAISS.

Portable Retrieval-Augmented Generation Library

Portable Retrieval-Augmented Generation Library

A comprehensive document parser for RAG applications with support for PDF, DOCX, PPTX, XLSX, and more

Retrive PDF files context for your LLMs

This library allows for granular testing of llm-applications based on expert input.

ragpipe: iterate quickly on your RAG pipelines.

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

ragpipe-lite: unified RAG ingestion pipeline (loaders, chunking, embeddings, vector store export).

Lightweight, production-ready RAG toolkit with 50-70% accuracy improvements. Enhanced BM25, BGE-Base embeddings, and semantic chunking - 100% offline.

Pre-deployment domain difficulty diagnostic for RAG. Know if your benchmark transfers — before you deploy.

Retrieval diagnostics and regression testing for RAG systems.

Unified RAG service abstraction for vector stores like Qdrant.

This project implements a local-first RAG chat system that reads and processes various text-based log files. It splits the content into manageable chunks, generates embeddings using Ollama or OpenAI, and allows users to interactively query the logs for specific information. The application features a customizable response format and supports configuration for user preferences.

Local multimodal semantic search CLI for technical documentation (text, PDFs, images) using ColQwen3 late-interaction embeddings.

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

An evaluation library for RAG models

Ratio graph handling in Python.

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

Local semantic code recall with mxbai embeddings and SQLite

Lightweight evaluation framework for Retrieval Augmented Generation systems, focused on simplicity and long-term consistency.

This library is to search the best parameters across different steps of the RAG process.

retrieval-augmented generation made simple

Zero-config RAG integration for LangChain, LlamaIndex, and AI agents

A comprehensive suite for evaluating 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.

RAG over CSVs and documents, with citations, ingestion diagnostics, and a built-in evaluation harness.

Async RAG toolkit on top of Postgres/pgvector and Voyage AI.

Ragstack is a one-click solution to deploy the retrieval augmented generation stack on your own infrastructure with open-source LLMs.

DataStax RAGStack

DataStax RAGStack Colbert implementation

DataStax RAGStack Knowledge Graph

DataStax RAGStack Graph Store

DataStax RAGStack Langchain

RAGStack Langflow

RAGStack Langflow base

DataStax RAGStack Llama Index

A tool for evaluating RAG pipelines

MCP server for RAGStack knowledge base - search, chat, upload, and scrape

RAG based LLM chatbot for dbt projects.

CLI tool to help retrieve RAG context from a corpus of documents.

RAG pipelines

Develop highly-concurrent web scrapers, easily.

Fetch, distill, and store authoritative references for external libraries

ragstruct - A Pseudo-Finetuning RAG Framework for structured JSON-based retrieval

Crossing Minds RAGsys python library

Table extraction from images to Markdown for RAG systems

PDF table extraction for RAG and LLM — convert PDF tables to clean HTML. Fast, local, no GPU. Handles merged cells, line-wrapped text, no serialization.

Python bindings for the Ragtastic API

A comprehensive Python library for testing and evaluating Retrieval-Augmented Generation (RAG) systems with LLM-generated questions and automated evaluation metrics

Ragtime 🎹 is an LLMOps framework to automatically evaluate Retrieval Augmented Generation (RAG) systems and compare different RAGs / LLMs

Local-first memory and RAG system for Claude Code - semantic search over code, docs, and team knowledge

Modular toolkit for building Retrieval-Augmented Generation (RAG) pipelines.