Data, search & knowledge

RAG & retrieval pipelines

5,258 agents · most starred first

RAG & retrieval pipelines, page 53 of 53

legal-rag-router

Deterministic coordinate pre-routing and epistemic abstention for legal RAG

legal-rag-verifier

Sentence-level claim and NLI verification with KV-cache rollback during generation, for legal RAG

llama-index-postprocessor-trimwise

Shared-budget extractive context trimming for LlamaIndex text nodes.

local-rag-qa

A small, fully local retrieval-augmented Q&A CLI — no internet needed at query time, no data leaves your machine.

noema-rag

Convert text into compact logical form for token-efficient RAG

ollama-response-generator-tayra

A response generator run with Ollama and ChromaDb.

openstax-llm

LLM dataset preparation, pedagogical semantic chunking, and RAG ingestion from OpenStax textbooks

pkmrag

Local-first Hybrid GraphRAG retrieval engine and MCP server for linked knowledge bases

polyrag

A modular, multi-paradigm Retrieval-Augmented Generation (RAG) framework supporting Vector, Agentic, and Graph RAG architectures.

proofrag-ai

Evidence-backed RAG with verified citations and refusal on insufficient evidence.

pyragx

Agentic retrieval at scale: an agent ranks and reads passages, a chain of sub-questions names the evidence the question leaves unnamed, and one call answers with exact citations.

rag-core-sdk

Optional Python client SDK for witty-rag / rag_core REST APIs

rag-quality-check

Measure whether a retrieval system is actually retrieving the right things

rag-search-local

Private, local document search: PDFs, Office files and images, with page-level citations.

rag-workflow

The project for RAG example workflow

rag-wright

A domain-retargetable, open-core engine for hybrid retrieval + knowledge-graph RAG: parsing, chunking, embedding, hybrid search, reranking, graph extraction, entity resolution, ontology-driven knowledge, and a capability runtime.

ragfuse

Load and chunk documents, create embeddings, and retrieve context for RAG applications

ragmechanic

A framework for building, evaluating, and diagnosing RAG systems.

ragnarok-api

Python SDK for the RAGnarok HTTP API (/api/v1): auth, streaming queries, ingest, graph and sources.

ragnor

Domain-agnostic RAG toolkit: embeddings, chunking, vector stores, retrieval, ingestion, evaluation, and jobs.

ragpreflight

Pre-ingestion diagnostic for RAG knowledge bases, grounded in the Garani 2026 taxonomy of 33 RAG failure modes

raguard-svkmsr6

Evaluation-first RAG pipeline: retrieval, generation, deterministic metrics, and guardrails for sensitive domains.

ragvidence

Evidence-first RAG retrieval diagnostics, built to run locally.

sift-rag

Local RAG search engine and MCP server for AI agents (Claude Code, Cursor, VS Code): hybrid BM25 + semantic search with reranking over Markdown and Obsidian notes, PDF, Office files and emails, fast at tens of millions of passages. Backlinks, metadata filters, browser UI. Runs on your own GPU or CPU: no cloud, no API keys.

textbook-rag

Grounded question answering over technical books, with citation and code verification.

tunarag-python

Tune LangChain, LangGraph, and Google ADK RAG pipelines

turkish-rag-eval

Measure which parts of a Turkish RAG pipeline pay off: chunking, stemming, embedding model, fusion.

vikingrag

Production hierarchical RAG: structure-aware Search, agentic retrieval, experience edges

RAG-HPO

HPO RAG as implemented by Brandon T. Garcia 2025.

aoguan-rag

Retrieval augmented generation composition for the Aoguan Python SDK

pydantic-rag-agent

A RAG agent built on Pydantic.

rag-verifier

Chunk-level quality verification for RAG ingestion: independence, completeness, traceability, semantic independence, template completeness

visualrag

Multimodal visual context extraction from screen shares, meeting recordings and real-world videos for Video RAG pipelines

@entrogic-net/knowledge

RAG knowledge base and long-term memory for BanglaClaw (Bangla-aware chunking, Qdrant)

agent-raw-rag-mcp

Cross-agent Raw-RAG incremental memory indexer and MLX two-stage retrieval MCP server for Claude Code, Codex, OpenCode, Oh My Pi, and Antigravity

ollama-lc-agent-tayra

An AI agent CLI package with Web UI and the RAG.

ragdoc

Headless diagnostic for PDF RAG pipelines: attributes a lost answer to the pipeline stage that lost it.

fastrag-ai

SDK for building RAG chatbots from dynamic sources

langchain-antfly

Persistent retrieval, inference, documents and graphs for LangChain with Antfly

mimirag

Retrieval-augmented generation with verifiable citations over technical documentation, source code and immutable records.

mosaic-rag

Production-grade modular RAG framework

naiyue-rag

Local Markdown knowledge retrieval with versioned evidence

ragscene

Placeholder: name reserved for RagScene, a docs-retrieval (RAG) product. No functionality yet.

sea-rag-sdk

Python SDK for SeaArt RAG and RAGFlow APIs

base90-rag

超极速、零算力、零幻觉的纯文本 RAG 检索结构 (Base90 极简硬路由)

cerebrollm

Local retrieval over your own authoritative documents. Every answer carries a quote that a check confirms, or says it is not in the sources.

mediarag

Multimodal local search over documents and media — pdf, office files, notes, images, audio and subtitles — from any MCP-capable agent.

olive-rag-eval

Native Rust RAG evaluation with Odia-first multilingual, BM25/RRF and local reranking support

parsrag

Build, evaluate, and ship Retrieval-Augmented Generation (RAG) for Persian text — offline-first, with a free Persian course.

persian-rag

Persian-first retrieval-augmented generation toolkit

rag-hygiene

Find and automatically repair broken RAG chunks before you embed them. Zero dependencies.

ragwell-agent-tools

Evidence search tools and workflows for agents using Ragwell

@xandreed/plugin-rag

Efferent composable agent framework, 0.22.0. Node 24 or Bun.

@xandreed/plugin-knowledge-postgres

Efferent composable agent framework, 0.22.0. Node 24 or Bun.

cragkit

Native Python retrieval with source-linked evidence, coverage estimates and execution diagnostics.

cragkit-langchain

LangChain adapter for Cragkit retrieval with access scope bound by the application.

pydantic-ai-asyntai

Pydantic AI capability for Asyntai: give your agent a whole website's knowledge, chats and leads

spectrag

Unofficial implementation of SpectRAG (Sahinoglu, Mohammed, Kazangirler and Kazangirler, arXiv:2610.36991): spectral graph-augmented retrieval for multi-hop RAG. Official code: github.com/SightAndCite/SpectRAG

More in Data, search & knowledge