Data, search & knowledge

RAG & retrieval pipelines

5,258 agents · most starred first

RAG & retrieval pipelines, page 50 of 53

proofrag

Point your agent at your docs and your RAG app; get a golden test set + an LLM-as-judge & retrieval scorecard, in one command.

ragstack-core

Enterprise-grade Python RAG stack — loaders, cleaning, chunking, embedding, and vector store in one composable library

ragzero

Production-ready RAG with near-zero hallucination. Pluggable providers (OpenAI, Anthropic, Gemini, OpenRouter, Azure, Voyage, ...), graph + agentic + multilingual strategies, a FastAPI server with a bundled React UI, and one-click publishing of a configured setup as a public ask-only assistant.

verifiable-rag

Document-grounded Q&A with sentence-level citations and faithfulness verification

RAG-I-Q-Pipeline
embedrag

Production-grade read/write split RAG retrieval system

ragloop-agentic

A pluggable, self-correcting agentic RAG framework with MCP-native retrieval.

lupa-rageval

Framework-agnostic RAG evaluation library — fully local, no LLM API required

unison-langchain

Stream-optimized, x402-gated grounding retrievers for LangChain and CrewAI

mmrag-eval

Benchmark for evaluating grounding quality in multimodal RAG systems

rag-llm-infra

Vendor-neutral RAG + LLM serving infrastructure: swappable LLM protocol and vector store (FAISS/NumPy/Qdrant), cached embedding index, and observability.

claude-tinderbox

Personal claude.ai conversation archive — ingest, embed, search, and MCP server

maskyrag

RAG implementation pipeline with GPU support

tortus-rag

Toroidal semantic graph retrieval for measurable multi-hop RAG trade-offs.

llama-index-readers-lyrenth

LlamaIndex reader for Lyrenth: read URLs as clean AIDocuments.

turborag-ahx47

My own RAG library built on turbovec

@reneza/ats-core

Adapter-agnostic core for Agentic Task System — retrieval (RRF parallel fan-out), corpus cache, usage logging, conformance kit, adapter interface

aiar-rag

AIAR — local retrieval-augmented generation with LLM-judge grounding loop

arch-rag

RAG-поиск по архитектурным нормативам

transformers-haystack

Haystack integration for transformers

@convex-dev/rag

Convex component for RAG: chunk and embed documents, then run semantic search to build LLM context.

ragkit-adhitya

Production RAG pipelines without the abstraction tax

guarded-rag

Guarded RAG: grounded answers, refuse-when-unsupported, PII redaction, and an eval harness with metrics. Stdlib core, bring-your-own model.

image-rag
matrx-rag

Multi-tenant RAG: hybrid retrieval, chunking, embeddings, ingestion, PDF + image + repo pipelines, agent-extraction indexing, priority-aware ranking.

@crewai-ts/rag

RAG, knowledge, memory, and file-ingestion features for CrewAI TypeScript.

multi-rag

A module to facilitate local testing of RAG pipeline for multiple datatypes

rag-bridge-kit

Plug-and-play RAG pipeline library for Python. Load, chunk, embed, store, retrieve, and generate — all in one clean API.

raglab_bak

Backend of a system to explore RAG operations (formerly published as raglab)

arabic-rag-toolkit

Arabic-first Retrieval-Augmented Generation (RAG) toolkit with local-first fallbacks

asag-rag

Add your description here

cgs-rag

Composite Grounding Score: multi-signal hallucination detection for production RAG systems

garrison-rag

Reserved for Garrison, Agile Defense's secure agentic AI platform. Placeholder release.

llamaindex-omega

LlamaIndex integration with OmegaEngine governance - RAG safety and compliance

slurp-rag

Distributed RAG QA-evaluation dataset generator for local files and Confluence.

context-rag-cli

Privacy-preserving CLI AI agent for querying local code repositories using RAG

rag-timetravel

Event-sourced RAG pipeline with time-travel debugging and index versioning

@vivantel/virage-skills

Redistributable AI agent skills for the Virage RAG pipeline

swiftrag

Set up retrieval-augmented generation from your own text in one call. Pass your documents and a model, and get a RAG-backed LLM.

mcpaisuite-ragmcp

Plug-and-play RAG with native MCP support. LLM-agnostic, swappable at every level.

mothrag

MothRAG: adaptive multi-arm subset routing for multi-hop retrieval-augmented generation — high-level Python API with auto-defaults.

ragfly

RAGfly Python SDK — RAG service for your AI agents

repolens-rag

A local-first RAG engine that answers questions about any repository, grounded exclusively in the checked-out code with verifiable file:line citations.

prismrag-patch

Free OSS RAG library — ingest, graph RAG search, communities, bridges, append (API parity)

rag-cachex

A context-aware, multi-level caching system for Retrieval-Augmented Generation (RAG) applications.

rag-spine

Framework-free backend RAG: deterministic dual-channel retrieval + agent orchestration with built-in anti-fabrication and source provenance.

ragpicker

Generate filesystem-based agentskills.io skill around a haiku-rag RAG database

ring-fenced-rag

Self-hosted, zero-trust RAG with role-based access control enforced at the database level

tabrag-xai-imputer

Retrieval-Augmented Generation for Missing Data Imputation in Tabular Data

ragforge-ml

Local-first RAG pipeline — PDF/Markdown ingestion, Qdrant retrieval, bge reranking, and an answer-quality eval harness. Pairs with turboquant-ml for quantized LLM serving.

scdl-rag

SCDL-RAG: Detect and fix RAG hallucinations with 97% recall and 100% precision.

nonebot-plugin-llm-qa-system

基于 Ollama + RAG 的智能问答系统

ragfly-cli

RAGfly CLI — operate RAGfly from the terminal and CI (login + cloud API). Lightweight, no desktop dependencies.

microsoft-sharepoint-haystack

Haystack integration for microsoft_sharepoint

ragpeek

A lightweight debugger for RAG pipelines

spinerag

Reserved name for the Spine family (RAG). Placeholder — see homepage.

google-drive-haystack

Haystack integration for google_drive

godot-rag

Hybrid RAG search for Godot documentation

agentic-web3-rag

Agentic RAG over consent-gated Web3 documentation — search and answer developer questions from Ethereum, Solidity, and ecosystem docs.

agentum-cloud-sdk

Типизированный async-клиент Agentum Cloud (/v1): загрузка документов, поиск и RAG-вопросы по вашим файлам.

arabic-rag-kit

Prepare Arabic (and mixed Arabic/English) documents for RAG and search: normalization, sentence-aware chunking, and a provider-agnostic vector index.

chunkbench-rag

A chunk-source-agnostic evaluation harness for RAG chunking strategies

cogwright-rag

Local-first retrieval engine for technical documentation.

gllm-rag-binary

A library containing RAG pipeline builders and presets for Gen AI applications.

klea-rag

Domain-configurable RAG pipeline for scientific research

ms-rags-all-in-one

MS-RAGS(ALL-IN-ONE) — production-grade RAG framework builder terminal CLI

nrag

Embedding-free RAG. An LLM compiles your documents once; every query stays pure BM25.

rag-fanuc

FANUC RAG Knowledge Base — pluggable retrieval + SAG hybrid search + OKF concepts

ragaas

SDK Python oficial do RAGaaS (ragaas.com.br) — RAG, memória de agente e gateway OpenAI-compatible

ragatini

Semantic-velocity document chunker — cuts where meaning changes, then snaps to real sentence/paragraph boundaries.

ragentkit

A clean-architecture RAG library with graph orchestration, multi-provider LLMs, and a low-code facade.

raggity

Local-first, top-tier RAG over your notes, docs, and PDFs — answered by Claude.

ragkit-sdk

Universal RAG framework SDK for Python developers

ragpy-core

A modular Retrieval-Augmented Generation (RAG) pipeline for Python.

llmframe-rag

Production-grade RAG + multi-LLM framework — hybrid search, streaming, cross-encoder reranking, and a REST API

sightrag

SightRAG: Image and Video RAG. See. Search. Retrieve. Track.

aiagentrag

Reusable AI Agent library with RAG, streaming, and long-term memory

bharatrag

RAG evaluation library for Indian languages (Hindi, Marathi, Tamil, Bengali, Telugu, Gujarati, Punjabi)

graphsearch-rag

GraphSearch: a GraphQL API server for Retrieval-Augmented Generation (RAG) over your documents

rag-python

Production-grade RAG for Python: ingest documents, hybrid search, streaming, multi-LLM, guardrails. CLI + Python API.

noirag

Noise-Aware Retrieval-Augmented Generation preprocessing engine

ragmill

A lightweight, zero-config local pipeline engine for AI data ingestion, semantic chunking, embeddings, and vector search — with optional cloud backends and a REST API.

slimx-rag

SlimX-RAG: a slim, deterministic RAG indexing pipeline (ingest -> chunk -> embed -> index).

@xflawlessdev/alnair-ai

Self-hosted AI agent platform with local RAG, workspace tools, and CLI

ragit

RAG for git-based AI agent workflows

groq-rag

Extended Groq TypeScript SDK with RAG, web browsing, and agent capabilities - 100% groq-sdk API compatible

@alextis59/athena

Local-first agentic documentation RAG command.

Rag-System

A production-quality Retrieval Augmented Generation (RAG) Python Framework.

adaptive-rag-engine

Adaptive Retrieval-Augmented Generation (RAG) Engine with Hybrid Retrieval, LangChain, Cross-Encoder Reranking, FAISS Vector Search, Gemini LLM Integration and FastAPI.

agentic-rag-lib

RAG library: file(s) -> mocked text recognition -> hierarchical on-disk index -> multi-tool search (BM25, FAISS vector, hybrid, TOC, grep, agentic)

agentic-rag-toolkit

Provider-agnostic, drop-in agent primitives for agentic RAG pipelines: classification, retrieval routing, sub-question retrieval, quality gating, self-validation, and tone personalization.

ai-rete-rag-mcp

MCP server for ai·rete·rag — deterministic rule-based decisions with RAG-powered explanations

codebase-rag

Symbol-aware, staleness-tracking RAG over a codebase, exposed over MCP; layers on rag-timetravel.

darwin-rag

Local-first RAG knowledge base with hybrid search (BM25 + embeddings), exposed to AI agents via MCP — fully offline-capable.

demystify-rag

Client SDK for dmstfy-rag: grounded RAG queries with citations, groundedness, abstention and SSE streaming

docforge-rag

Automatically discovers, crawls, versions, chunks, and indexes official software documentation into a RAG-ready knowledge base.

haystack-salesforce-npsp

Haystack 2.x component that ingests Salesforce Nonprofit Success Pack (NPSP) donor data as Documents for RAG.

haystack-unirate

Haystack integration for the UniRate currency-exchange API — components for FX rate lookups, conversion, and currency listings in Haystack pipelines.

hyperforge-nucliadb-agentic

NucliaDB Hyperforge agent

ibm-db-haystack

Haystack integration for IBM Db2

More in Data, search & knowledge