Data, search & knowledge

RAG & retrieval pipelines

5,258 agents · most starred first

RAG & retrieval pipelines, page 51 of 53

jupyter-geoagent

A JupyterLab extension for interactive geospatial data exploration via STAC catalogs and MCP-powered queries.

kp-rag

My tiny package

langchain-opedd

LangChain integration for Opedd — licensed, rights-cleared content for AI: load your licensed corpus into RAG pipelines and give agents lookup/verify tools with a verifiable license key per article.

langchain-visual-retrieval

Provider-based visual retrieval for LangChain with PixelRAG support and native geospatial vector retrieval

llama-index-retrievers-opendma

LlamaIndex retrievers for OpenDMA - retrieve ECM content with LlamaIndex

llmkb

Local, folder-first LLM knowledge bases: format spec, CLI, MCP server, and agent skills.

llms-mirror

Mirror official docs (via llms.txt) as plain Markdown for LLM ingestion and RAG.

llms-txt-kit

Generate and validate llms.txt files — CLI and Python library, zero dependencies.

meridian-rag

A from-scratch grounded RAG engine over biomedical literature: every ML component trained in-house, every answer cited, verified, or refused.

metarag-sdk

Framework for benchmarking, evaluating, and orchestrating Retrieval-Augmented Generation pipelines.

minerva-rag

Evolutionary RAG system with holographic memory compression

mm-asset-rag

Multimodal knowledge base for documents and images with intent-aware retrieval, grounded answers, and evidence images.

mnemosyne-rag

A local, teaching-first RAG pipeline (Ollama + LangChain + FAISS) that turns any model into an instant expert.

mrta-rag

A local citation-aware research and teaching assistant for technical PDFs

multilingual-dev-rag

Local-first multilingual RAG for code and technical docs. In-process hybrid retrieval (vector + full-text) with FTS for Cyrillic and other non-ASCII scripts.

mzero-rag

Zero-Configuration RAG Framework and Embeddable SDK for Python

nepali-rag

All-in-one RAG framework for Nepali Documents.

nucliadb-agentic-api

NucliaDB Agentic API for Hyperforge

opendma-haystack

Integration of Enterprise Content Management (ECM) systems with Haystack through toolsets, fetchers, and retrievers

placeborag

Deterministic test doubles for the retrieval half of a RAG pipeline

qiro-rag

Local-first evidence substantiation/RAG for Qiro environmental claim review.

quackrag

Add your description here

rag-ablations

Reproducible retrieval benchmark: measures RAG design choices against a stated BM25 baseline

rag-anchor

Portable RAG for Python projects: ingestion, vector search and sourced answers, with no imposed infrastructure.

rag-assistant-ldxs

rag-assistant — AI Agent

rag-blocks

Composable building blocks for production RAG pipelines, with an auto-tuning evaluation suite.

rag-chunk-audit

Find common quality and safety issues in RAG chunks before indexing.

ragbrain

Bi-temporal RAG platform: cited, temporally-correct answers plus system-time replay. Self-hostable memory and audit layer for AI agents.

ragcompress

Extractive, provenance-preserving context compression for RAG pipelines.

ragdedup

Lightweight semantic cache for LLM and RAG pipelines. One class, one method, zero required dependencies, sync and async.

rager

Caching based RAG primitives

ragi-toolkit

ragi — Retrieval that rises. Eval-first, agent-agnostic RAG toolkit -- define, measure, iterate, ship as a portable retrieval contract (Python lib / MCP server) any agent consumes.

ragjson

遵循RAG-Storage-Spec的知识库构建工具

ragkit-vectorlite

A tiny, dependency-free in-memory vector store for prototyping RAG / semantic search.

ragl-lang

RAGL — a memory-safe, flexible-syntax, AI-native programming language

raglan-retrieval

A lightweight, highly configurable RAG retrieval engine. Framework-free, protocol-driven.

ragleap-rag

Self-hosted RAG engine: hybrid dense+sparse retrieval, 28-format ingestion (docs, URLs, images, audio, video), 6 vector backends, 8 embedding providers, 12+ generation providers with automatic fallback, query rewriting (HyDE/contextual/multi-query), structured JSON output, real per-call cost tracking, and standalone retrieval via retrieve(). Composable with the optional ragleap-graph package for knowledge-graph-augmented retrieval. BYOK, no vendor lock-in, no hardcoded model defaults.

raglite-toolkit

Build semantic search, multi-provider question answering, and REST APIs over your documents in a few lines of Python.

ragotron

Automated search over RAG-pipeline configurations with reusable trial artifacts for training and inference

ragsage

A sage that only speaks from your corpus — a reusable, tenancy-agnostic RAG engine behind ports

ragup

Build semantic search, question answering, and FastAPI-powered RAG applications in just a few lines of Python.

ragx-cli

Similarity-graph RAG CLI: index a corpus into a chunk-level embedding graph and query it

ragzen

Enterprise-grade, local-first RAG for Python

right-rag

Domain-structured RAG pipeline template

rustyrag

Python SDK for RustyRAG — fast, minimal RAG-as-a-Service client

scinexusrag

Local hybrid retrieval and faithfulness benchmark for scientific papers

tdw-rag

Temporal decay weighting for RAG. Rerank retrieval by similarity x document age, with adstock-derived decay kernels.

th2rag

Add your description here

vaultrag

Self-hosted, MCP-first RAG backend over Obsidian vaults.

verity-rag

Production-grade self-hosted document ingestion and retrieval service

wooma-rag-assistant

Une application RAG (Vectoriseur + Chat) créée pour la communauté de développeurs Python en Afrique.

@dudousxd/nestjs-agent-rag-media

Auto-ingest @dudousxd/nestjs-media uploads into agent RAG — extract, chunk, embed, index, owner-scoped, with delete kept in sync. Couples via the diagnostics channel, no hard media dependency

@vezlo/assistant-server

Production-ready AI Assistant Server with advanced RAG (chunk-based semantic search + adjacent retrieval), conversation management, real-time communication, and human agent handoff

arabic-pdf-rag

Arabic-First PDF Extraction, RTL Normalization & Table Chunking Engine for RAG Systems.

brainmarks-agent

Agentic RAG for your browser bookmarks — local-first, BYOM, privacy-focused.

claudesync-index

Hierarchical AI-generated index over a claudesync export of your claude.ai conversations.

cortex-local-rag

Local multi-client RAG server over the Model Context Protocol

lightrag-client

Python client SDK for InfraX RAGservicer — hybrid knowledge-base (vector + graph + keyword) retrieval

llama-index-postprocessor-needlepath

llama-index postprocessor needlepath context selection integration

rag-alpha

AI assistant for semantic search and chat with codebases

rag-intent-classifier

MiniLM-based intent classifier with 156 intents, including follow-up, negative sentiment, escalate intents detection for RAG systems. Python 3.9-3.13 supported.

ragmesh

Retrieval as a mesh of MCP services — an agentic RAG platform built on LangGraph. Under active development.

slm-rag

A lightweight, CPU-optimized RAG library powered by a local Small Language Model (SLM)

vaultrag-cli

Permission-aware RAG: access control enforced in the retrieval query, not after it.

llmwiki-chat

Accessible Agent Runtime console for Markdown/wiki Knowledge Source endpoints.

askme-rag

CLI RAG tool for local codebases

chonk-rag

A dairy-free RAG pipeline for delicious semantic similarity, clustering and NER.

datarobot-fastrag

Async FastAPI runner for DataRobot custom LLM and RAG models

local-semantic-rag

Production-grade local semantic search and RAG framework

pramana-rag

A grounding-first RAG library: threshold-gated retrieval, concern-based chunking, a locked grounding prompt, and built-in faithfulness evaluation as the default path, not an optional rail.

ragking

LlamaIndex 기반 RAG All-In-One 라이브러리

supabase-easy-rag

Production-ready, lightweight Hybrid RAG (Dynamic Vector + Full-Text Search + Facets) engine for Supabase.

vs-rag

Enterprise RAG framework with pluggable layers

@nestjs-agentic/rag

Production-grade, modular RAG engine for nestjs-agentic with advanced built-in strategies (Query Expansion, Hierarchical RAG, Late Chunking, Parent-Child Hydration, Contextual Compression, and Knowledge Graph RAG).

cairn-rag

Cairn reuses unchanged RAG chunks with content-defined identities, cache-aware planning, and transactional indexing.

git-rag

Retrieval-augmented search over an Obsidian vault managed as a git repository

langchain-tacnode

Tacnode integration for LangChain and LangGraph — multi-modal retrieval and a drop-in agent stack on one hybrid SQL plane

lumenrag

Local-first RAG studio powered by LumenVec

metamind-vault-rag

Markdown corpus retrieval engine: watcher, indexer, hybrid search, MCP server.

rag-system-core

Add your description here

ragbt

dbt for RAG — declarative, incremental, tested embedding pipelines

ragmodel

A modular, provider-independent execution kernel for building composable RAG systems.

ragoonx

A modular Retrieval-Augmented Generation framework.

langchain-pdfbot

A LangChain-based tool to answer questions strictly from PDF content using Groq LLM and local embeddings.

ahs-agentic

AHS-Core: the conflict-resolution and forensic-traceability layer for agentic RAG. Detects contradictions between retrieved premises, cascading hallucinations, and produces an auditable source-cited answer.

atlas-ragkit

Atlas — Local-First RAG Engineering Platform

pagedoc-rag

CPU-First Multimodal Document Chunking, Ingestion & Retrieval Engine using Native PDF Extraction, OCR, Multi-Vector Embeddings, and MaxSim Late Interaction

ragfold

Unified interface for RAG and information-extraction engines with built-in benchmarks.

ragfresh

Detect stale, drifted, and ghost documents in RAG vector indexes

ragground

Fast, deterministic & ONNX-powered hallucination guardrail & citation verifier for RAG

ragxray

A lightweight RAG debugging toolkit: understand why your RAG application gave a bad answer.

shaik-rag-library

Custom hybrid RAG library

datumrag

A retrieval substrate for AI agents: every query compiles to an explainable, replayable plan over one versioned, tenant-isolated store.

gatrag_text_splitter

Text chunking / splitting utilities for the GATRAG RAG framework

mistralai-workflows-plugins-search

Search Toolkit plugin for Mistral Workflows - durable document ingestion pipelines

protorag

Zero-infrastructure in-memory RAG prototyping framework for Python.

rag-hub

A visual debugger for RAG pipelines — see exactly where your pipeline breaks

rag-your-code

A local, explainable RAG index for codebases and coding agents

x-api-scraper-haystack

Haystack RAG components for Twitter search and public user timelines through TwexAPI. Not affiliated with X Corp.

@sota-agentic-ragx/agentic-core-react

React 19 chat, citation, and evidence preview components for Agentic Core.

More in Data, search & knowledge