Developer tools

RAG & AI memory: the tech stack of 55 real products

Retrieval engines, knowledge-graph RAG and memory layers for AI apps.

What sets them apart

Picks at least twice as common here as among products overall, in decisions at least 10 of them show.

Neo4jDatabase14×as often as overall16 of the RAG & AI memory that show database (38%)Qwen APILLM API4.8×as often as overall5 of the RAG & AI memory that show LLM API (11%)

LiteLLMLLM API4.1×as often as overall17 of the RAG & AI memory that show LLM API (38%)

GitHub PagesHosting3.3×as often as overall8 of the RAG & AI memory that show hosting (44%)

MinIOFile Storage2.9×as often as overall8 of the RAG & AI memory that show file storage (80%)

SQLiteDatabase2.8×as often as overall14 of the RAG & AI memory that show database (33%)

The typical stack

The leading pick where at least 8 of them show the decision and the leader has at least a quarter of it.

Decision	Most common pick	Share	At default usage
LLM API	OpenAI API	38 of 45 · 84%	$10/mo · GPT-6 Luna
Database	PostgreSQL	26 of 42 · 62%	—
Frontend Framework	React	20 of 33 · 61%	—
Vector Database	pgvector	16 of 33 · 48%	—
AI SDK & Agent Framework	LangChain	18 of 29 · 62%	—
Backend Framework	FastAPI	26 of 29 · 90%	—
Database Access & ORMs	SQLAlchemy	18 of 19 · 95%	—
Hosting	GitHub Pages	8 of 18 · 44%	—
LLM Observability & Evals	LangSmith	9 of 16 · 56%	$475/mo · Developer
Transactional Email	Resend	11 of 15 · 73%	$20/mo · Pro 50k
File Storage	MinIO	8 of 10 · 80%	—
Background Jobs & Cron	RabbitMQ	4 of 9 · 44%	—
Payments	Stripe	8 of 8 · 100%	fees on revenue · $410 on $10,000/mo

Monthly bills add up to about $505 at the calculators' default usage, list prices; fees on revenue (Stripe) come on top. Set your own usage →

What they chose, decision by decision

Among the RAG & AI memory that show each choice, from makers' products and open-source code alike.

LLM API45 products

Database42 products

Frontend Framework33 products

Vector Database33 products

AI SDK & Agent Framework29 products

Backend Framework29 products

Database Access & ORMs19 products

Hosting18 products

Amazon Web Services3 · 17%

LLM Observability & Evals16 products

Transactional Email15 products

File Storage10 products

MinIO8 · 80%

Amazon S33 · 30%

UploadThing1 · 10%

Background Jobs & Cron9 products

Payments8 products

Small samples, fewer than 8 products: Error Monitoring (Sentry 7) · Product Analytics (PostHog 5, Mixpanel 1) · Web Analytics (Google Analytics 3, Plausible Analytics 1) · Authentication (Clerk 1, Better Auth 1)

RAG & AI memory we track

26 makers' products and 29 open-source projects. Makers' products first.

cogneeMemory for AI Agents in 6 lines of code

VectorizeAgents that remember. Agents that learn.

ByteroverFile-based memory for agents with >92% retrieval accuracy

CloudglueLet your AI understand videos and audio

WeavableGive every AI agent persistent work context

NiaAPI for grounded agent context

SupavecThe open source RAG as a Service.

IgnitionRAGMultimodal RAG platform, from POC to production in minutes

Actx0Memory infrastructure for AI agents.

Supametas.AIStreamline unstructured data into LLM RAG-ready datasets

TrieveAll-in-one AI Infrastructure Suite

agentsetThe open-source RAG platform: built-in citations, deep research, 22+ file formats, partitions, MCP server, and more.

+12

semanticaGraph-Native Infrastructure for Context and Accountable AI Systems

+17

puppyone-cloudContext drive for your AI agents

+15

FastGPTFastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI workflow orchestration, letti

+11

m_flowA bio-inspired cognitive memory engine — a new paradigm for Graph RAG.

cocoindexIncremental engine for long horizon agents 🌟 Star if you like it!

AcontextAgent Skills as a Memory Layer

MemoriMemori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems. Built for enterprise, Memori wo

mossThe retrieval layer for production AI systems. Lightning-fast (<10ms) search without vector databases. Built for browser, edge, on-device, and cloud.

vectara-ingestAn open source framework to crawl data sources and ingest into Vectara

PageIndex📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG

ai-optimizerGenAI/RAG Optimizer and Toolkit for experimentation using Oracle Database AI Vector Search and NL2SQL

memobaseUser Profile-Based Long-Term Memory for AI Chatbot Applications.

ragflowRAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

SAGA new SOTA for RAG — an original retrieval architecture and an open-source knowledge base for humans and agents.

MemOS Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.

+15

ApeRAG ApeRAG: Production-ready GraphRAG with multi-modal indexing, AI agents, MCP support, and scalable K8s deployment

+11

KnowFlow KnowFlowRAG

+11

LightRAG [EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation

+10

Yuxi 可私有部署的多租户知识智能体平台：统一 RAG、知识图谱、多智能体、MCP/Skills、沙盒与权限管理。Yuxi = Cloud Agents + Knowledge RAG, Self-hosted knowledge agent platform for RAG, knowledge graphs and multi-agent workflows.

MemoryBear MemoryBear Equip AI with human-like memory capability

ragflow-plus Ragflow-Plus 是 Ragflow 的二次开发版本，使其更为简洁实用

embedbase A dead-simple API to build LLM-powered apps

R2R SoTA production-ready AI retrieval system. Agentic Retrieval-Augmented Generation (RAG) with a RESTful API.

trustgraph The Semantic Intelligence Layer for Ontologies

atomicmemory Portable semantic memory for AI agents: core engine, TypeScript SDK, framework adapters, MCP server, CLI, and host plugins.

honcho Memory library for building stateful agents

Langchain-Chatchat Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and Ll

vektori Memory that remembers the story not just the facts. File System Memory and Three layer sentence graph for AI agents -> Facts, Episodes, raw Sentences. One DB. Zero config.

graphiti Build Real-Time Knowledge Graphs for AI Agents

nexus Nexus, the shared context plane where every agent and human connect, collaborate, and evolve together.

NeMo-Retriever NeMo Retriever Library is a scalable, performance-oriented document content and metadata extraction microservice. NeMo Retriever Library uses specialized NVIDIA NIM microservices to find, contextualiz

openrag OpenRAG is a comprehensive, single package Retrieval-Augmented Generation platform built on Langflow, Docling, and Opensearch.

WeKnora Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.

dsRAG High-performance retrieval engine for unstructured data

data-prep-kit Open source project for data preparation for GenAI applications

GraphRAG-Local-UI GraphRAG using Local LLMs - Features robust API and multiple apps for Indexing/Prompt Tuning/Query/Chat/Visualizing/Etc. This is meant to be the ultimate GraphRAG/KG local LLM app.

LEANN [MLsys2026 Best Paper]: https://arxiv.org/abs/2506.08276. RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal devi

redis-vl-python Redis Vector Library. The AI-native Python client for Redis.

chonkie 🦛 CHONK docs with Chonkie ✨ — The lightweight ingestion library for fast, efficient and robust RAG pipelines

langmem

mempalace The best-benchmarked open-source AI memory system. And it's free.

dialog RAG LLM Ops App for easy deployment and testing

graphrag A modular graph-based Retrieval-Augmented Generation (RAG) system