RAG & retrieval pipelines
5,258 agents · most starred first
RAG & retrieval pipelines, page 50 of 53
Point your agent at your docs and your RAG app; get a golden test set + an LLM-as-judge & retrieval scorecard, in one command.
Enterprise-grade Python RAG stack — loaders, cleaning, chunking, embedding, and vector store in one composable library
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.
Document-grounded Q&A with sentence-level citations and faithfulness verification
Production-grade read/write split RAG retrieval system
A pluggable, self-correcting agentic RAG framework with MCP-native retrieval.
Framework-agnostic RAG evaluation library — fully local, no LLM API required
Stream-optimized, x402-gated grounding retrievers for LangChain and CrewAI
Benchmark for evaluating grounding quality in multimodal RAG systems
Vendor-neutral RAG + LLM serving infrastructure: swappable LLM protocol and vector store (FAISS/NumPy/Qdrant), cached embedding index, and observability.
Personal claude.ai conversation archive — ingest, embed, search, and MCP server
RAG implementation pipeline with GPU support
Toroidal semantic graph retrieval for measurable multi-hop RAG trade-offs.
LlamaIndex reader for Lyrenth: read URLs as clean AIDocuments.
My own RAG library built on turbovec
Adapter-agnostic core for Agentic Task System — retrieval (RRF parallel fan-out), corpus cache, usage logging, conformance kit, adapter interface
AIAR — local retrieval-augmented generation with LLM-judge grounding loop
RAG-поиск по архитектурным нормативам
Haystack integration for transformers
Convex component for RAG: chunk and embed documents, then run semantic search to build LLM context.
Production RAG pipelines without the abstraction tax
Guarded RAG: grounded answers, refuse-when-unsupported, PII redaction, and an eval harness with metrics. Stdlib core, bring-your-own model.
Multi-tenant RAG: hybrid retrieval, chunking, embeddings, ingestion, PDF + image + repo pipelines, agent-extraction indexing, priority-aware ranking.
RAG, knowledge, memory, and file-ingestion features for CrewAI TypeScript.
A module to facilitate local testing of RAG pipeline for multiple datatypes
Plug-and-play RAG pipeline library for Python. Load, chunk, embed, store, retrieve, and generate — all in one clean API.
Backend of a system to explore RAG operations (formerly published as raglab)
Arabic-first Retrieval-Augmented Generation (RAG) toolkit with local-first fallbacks
Add your description here
Composite Grounding Score: multi-signal hallucination detection for production RAG systems
Reserved for Garrison, Agile Defense's secure agentic AI platform. Placeholder release.
LlamaIndex integration with OmegaEngine governance - RAG safety and compliance
Distributed RAG QA-evaluation dataset generator for local files and Confluence.
Privacy-preserving CLI AI agent for querying local code repositories using RAG
Event-sourced RAG pipeline with time-travel debugging and index versioning
Redistributable AI agent skills for the Virage RAG pipeline
Set up retrieval-augmented generation from your own text in one call. Pass your documents and a model, and get a RAG-backed LLM.
Plug-and-play RAG with native MCP support. LLM-agnostic, swappable at every level.
MothRAG: adaptive multi-arm subset routing for multi-hop retrieval-augmented generation — high-level Python API with auto-defaults.
RAGfly Python SDK — RAG service for your AI agents
A local-first RAG engine that answers questions about any repository, grounded exclusively in the checked-out code with verifiable file:line citations.
Free OSS RAG library — ingest, graph RAG search, communities, bridges, append (API parity)
A context-aware, multi-level caching system for Retrieval-Augmented Generation (RAG) applications.
Framework-free backend RAG: deterministic dual-channel retrieval + agent orchestration with built-in anti-fabrication and source provenance.
Generate filesystem-based agentskills.io skill around a haiku-rag RAG database
Self-hosted, zero-trust RAG with role-based access control enforced at the database level
Retrieval-Augmented Generation for Missing Data Imputation in Tabular Data
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: Detect and fix RAG hallucinations with 97% recall and 100% precision.
基于 Ollama + RAG 的智能问答系统
RAGfly CLI — operate RAGfly from the terminal and CI (login + cloud API). Lightweight, no desktop dependencies.
Haystack integration for microsoft_sharepoint
A lightweight debugger for RAG pipelines
Reserved name for the Spine family (RAG). Placeholder — see homepage.
Haystack integration for google_drive
Hybrid RAG search for Godot documentation
Agentic RAG over consent-gated Web3 documentation — search and answer developer questions from Ethereum, Solidity, and ecosystem docs.
Типизированный async-клиент Agentum Cloud (/v1): загрузка документов, поиск и RAG-вопросы по вашим файлам.
Prepare Arabic (and mixed Arabic/English) documents for RAG and search: normalization, sentence-aware chunking, and a provider-agnostic vector index.
A chunk-source-agnostic evaluation harness for RAG chunking strategies
Local-first retrieval engine for technical documentation.
A library containing RAG pipeline builders and presets for Gen AI applications.
Domain-configurable RAG pipeline for scientific research
MS-RAGS(ALL-IN-ONE) — production-grade RAG framework builder terminal CLI
Embedding-free RAG. An LLM compiles your documents once; every query stays pure BM25.
FANUC RAG Knowledge Base — pluggable retrieval + SAG hybrid search + OKF concepts
SDK Python oficial do RAGaaS (ragaas.com.br) — RAG, memória de agente e gateway OpenAI-compatible
Semantic-velocity document chunker — cuts where meaning changes, then snaps to real sentence/paragraph boundaries.
A clean-architecture RAG library with graph orchestration, multi-provider LLMs, and a low-code facade.
Local-first, top-tier RAG over your notes, docs, and PDFs — answered by Claude.
Universal RAG framework SDK for Python developers
A modular Retrieval-Augmented Generation (RAG) pipeline for Python.
Production-grade RAG + multi-LLM framework — hybrid search, streaming, cross-encoder reranking, and a REST API
SightRAG: Image and Video RAG. See. Search. Retrieve. Track.
Reusable AI Agent library with RAG, streaming, and long-term memory
RAG evaluation library for Indian languages (Hindi, Marathi, Tamil, Bengali, Telugu, Gujarati, Punjabi)
GraphSearch: a GraphQL API server for Retrieval-Augmented Generation (RAG) over your documents
Production-grade RAG for Python: ingest documents, hybrid search, streaming, multi-LLM, guardrails. CLI + Python API.
Noise-Aware Retrieval-Augmented Generation preprocessing engine
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: a slim, deterministic RAG indexing pipeline (ingest -> chunk -> embed -> index).
Self-hosted AI agent platform with local RAG, workspace tools, and CLI
RAG for git-based AI agent workflows
Extended Groq TypeScript SDK with RAG, web browsing, and agent capabilities - 100% groq-sdk API compatible
Local-first agentic documentation RAG command.
A production-quality Retrieval Augmented Generation (RAG) Python Framework.
Adaptive Retrieval-Augmented Generation (RAG) Engine with Hybrid Retrieval, LangChain, Cross-Encoder Reranking, FAISS Vector Search, Gemini LLM Integration and FastAPI.
RAG library: file(s) -> mocked text recognition -> hierarchical on-disk index -> multi-tool search (BM25, FAISS vector, hybrid, TOC, grep, agentic)
Provider-agnostic, drop-in agent primitives for agentic RAG pipelines: classification, retrieval routing, sub-question retrieval, quality gating, self-validation, and tone personalization.
MCP server for ai·rete·rag — deterministic rule-based decisions with RAG-powered explanations
Symbol-aware, staleness-tracking RAG over a codebase, exposed over MCP; layers on rag-timetravel.
Local-first RAG knowledge base with hybrid search (BM25 + embeddings), exposed to AI agents via MCP — fully offline-capable.
Client SDK for dmstfy-rag: grounded RAG queries with citations, groundedness, abstention and SSE streaming
Automatically discovers, crawls, versions, chunks, and indexes official software documentation into a RAG-ready knowledge base.
Haystack 2.x component that ingests Salesforce Nonprofit Success Pack (NPSP) donor data as Documents for RAG.
Haystack integration for the UniRate currency-exchange API — components for FX rate lookups, conversion, and currency listings in Haystack pipelines.
NucliaDB Hyperforge agent
Haystack integration for IBM Db2