
Open-source RAG engine with a document pipeline, hybrid search and visual agent workflows
- Freemium
- Open-source agent
- 94.3K GitHub stars
- Knowledge and memory

Open-source RAG engine with a document pipeline, hybrid search and visual agent workflows

Private on-device AI assistant for chatting with documents, with local models

Vectorless RAG engine that finds answers by reasoning over a document's page tree

Open-source knowledge framework for RAG Q&A, agent tasks and auto-built wikis

Open-source Python framework for building production RAG pipelines and agents

List, inspect and query Agent Platform RAG Engine corpora and ground Gemini answers

Open-source enterprise agent platform with RAG knowledge bases and workflows

Gives agents a persistent wiki, knowledge graph and raw-source store that grows with each

Guides agents through building Pinecone-backed RAG pipelines and persistent agent memory

Guides moving a Qdrant collection to a new embedding model without taking search offline

Guides an agent through diagnosing and reducing Qdrant memory usage

Guides keeping Qdrant searches fast by rotating or expiring time-based data

Diagnoses weak Qdrant search results and recommends fixes for relevance

Guides choosing Qdrant search strategies: hybrid search, reranking, diversity and feedback

Guides designing and deploying a RAG enterprise search system on GKE with a vector SQL

Lets your agent ingest, index and query document collections with the NeMo Retriever CLI

Lets an agent search and ingest documents through the NeMo Retriever MCP server

Deploys, configures, troubleshoots and tears down the NVIDIA RAG Blueprint stack

Benchmarks a RAG pipeline's answer quality on local corpus and train.json datasets

Benchmarks a deployed NVIDIA RAG server for latency, throughput and citation quality
Local-first Markdown vault memory and semantic search for AI coding assistants
Local MCP server that searches and answers questions over your own Markdown wiki
Runs locallyCompany memory MCP server in your own cloud that answers within each person's access
Not checked yetSearches your own code, PDFs and Office files and returns exact source citations
Runs locallyIndex code, docs, PDFs and data in a local SQLite file and serve context to agents
Runs locallyTurn YouTube captions, PDFs and web pages into clean Markdown for RAG
Hosted persistent memory for AI agents, with hybrid keyword and vector search
Not checked yetSearch and manage company knowledge with cited answers from MCP clients
Not checked yetSelf-hosted MCP memory server with hybrid search and a learning memory graph
Not checked yetSelf-hosted MCP server: shared agent memory, document search and a code index
Not checked yetThe most popular AI tools, agents, MCP servers and skills for rag on AI-Powered right now are ragflow, anything-llm, PageIndex, WeKnora and haystack. Rankings combine upvotes, recent activity and, for open-source projects, GitHub stars.
Yes. Of the 81 AI tools, agents, MCP servers and skills for rag listed, 47 are free or open source and 19 have a free plan. Use the Pricing filter to see only those.
AI-Powered lists 81 AI tools, agents, MCP servers and skills for rag. New listings are added daily from the official MCP Registry, GitHub and maker submissions.