The best free AI agent memory and RAG services (12)

Every option in the catalog for when you need to give an assistant durable memory across sessions — 12 AI agent memory and RAG services, 12 of them free or freemium, with the pricing tier printed on every row.

12tools listed
12free or freemium
7with no paid plan at all
1sub-categories covered

Best Free AI agent memory and RAG services — straight answers

What are the best free AI agent memory and RAG services?

Flocci AI Tools lists 12 of them, ordered free tiers first: MemOS, RAGFlow, Basic Memory, Cognee and Graphiti. Every one of them is free or has a free tier. Each entry states what it uniquely does rather than a score.

Which of these are completely free?

7 on this page are marked fully free with no paid plan at all: MemOS, RAGFlow, Basic Memory, Cognee and Graphiti. The remaining 5 are freemium, trial or paid, and each is labelled with its exact tier so nothing surprises you at sign-up.

How is this list ordered?

Free tools first, then freemium, then trial, then paid, and alphabetically inside each tier. Nobody pays to appear higher: Flocci AI Tools carries no ads, no sponsored slots and no paid listings, so the order reflects price and nothing else.

Best Free AI agent memory and RAG services — quick picks

Which AI agent memory and RAG services work in a browser with no install?

MemOS, RAGFlow, Letta, Mem0 and Memori all work in a browser tab with no install needed — just open the site and go. 7 of the 12 free AI agent memory and RAG services listed here are browser-based.

Which AI agent memory and RAG services let you sign in with Google?

Mem0, Memori and Supermemory support Google sign-in, so you can start without creating a new account. That's 3 of the 12 free AI agent memory and RAG services on this page.

Which AI agent memory and RAG services can you self-host or run offline?

Basic Memory, Graphiti, LightRAG and Memvid can be self-hosted or run locally without a browser — useful for privacy, air-gapped networks, or avoiding API rate limits. 4 of the 12 free AI agent memory and RAG services here run offline.

All 12 tools, free tiers first

Browse Agent Memory & RAG-as-a-Service →
Best Free AI agent memory and RAG services: pricing tier, category and the capability each tool is listed for.
ToolPricingTypeListed for
MemOSFreeAgent Memory & RAG-as-a-ServiceMemory operating system for LLM agents with hybrid retrieval and persistent memory
RAGFlowFreeAgent Memory & RAG-as-a-ServiceOpen-source RAG engine with deep document parsing and agent workflows
Basic MemoryFreeAgent Memory & RAG-as-a-ServiceMCP server that stores AI conversation memory as local Markdown notes
CogneeFreeAgent Memory & RAG-as-a-ServiceOpen-source memory platform that turns data into a knowledge graph plus vectors for agents
GraphitiFreeAgent Memory & RAG-as-a-ServiceFramework for building real-time temporal knowledge graphs for AI agents
LightRAGFreeAgent Memory & RAG-as-a-ServiceSimple, fast graph-based RAG from HKU Data Science lab (EMNLP 2025)
MemvidFreeAgent Memory & RAG-as-a-ServicePacks agent memory into a single portable file with no server or database
LettaFreemiumAgent Memory & RAG-as-a-ServiceFree BYOK plan supporting up to 3 stateful agents
Mem0FreemiumAgent Memory & RAG-as-a-ServiceFree Hobby tier: unlimited end users, 10K add / 1K retrieval requests/month
MemoriFreemiumAgent Memory & RAG-as-a-ServiceLLM-agnostic memory layer that captures agent context as structured state
SupermemoryFreemiumAgent Memory & RAG-as-a-ServiceFree monthly usage allowance plus a Supermemory MCP server
ZepFreemiumAgent Memory & RAG-as-a-ServiceFree plan: 10,000 monthly credits, 2 projects, 200ms retrieval

MemOS

Agent Memory & RAG-as-a-Service
freeNew
  • Memory operating system for LLM agents with hybrid retrieval and persistent memory
  • Open source and self-hostable, with a cloud option
  • Built for multi-agent and personal assistants
  • Backed by MemTensor, a Shanghai team

RAGFlow

Agent Memory & RAG-as-a-Service
freeNew
  • Open-source RAG engine with deep document parsing and agent workflows
  • Grounded citations and template-based chunking
  • Self-host with Docker; bring your own LLM

Basic Memory

Agent Memory & RAG-as-a-Service
freeNew
  • MCP server that stores AI conversation memory as local Markdown notes
  • Works with Claude Desktop and other MCP clients, and is readable in Obsidian
  • Everything stays on your disk
  • Open source core is free; optional paid cloud sync

Cognee

Agent Memory & RAG-as-a-Service
freeNew
  • Open-source memory platform that turns data into a knowledge graph plus vectors for agents
  • Python API with pluggable graph, vector and relational stores
  • Self-host free; cloud option exists

Graphiti

Agent Memory & RAG-as-a-Service
freeNew
  • Framework for building real-time temporal knowledge graphs for AI agents
  • Powers Zep's memory layer; runs standalone
  • Open source, works with Neo4j and other graph DBs

LightRAG

Agent Memory & RAG-as-a-Service
freeNew
  • Simple, fast graph-based RAG from HKU Data Science lab (EMNLP 2025)
  • Combines knowledge-graph and vector retrieval
  • Works with local or hosted LLMs

Memvid

Agent Memory & RAG-as-a-Service
freeNew
  • Packs agent memory into a single portable file with no server or database
  • Offline retrieval with no cloud dependency
  • Open source with SDKs
  • Aimed at replacing complex RAG pipelines

Letta

Agent Memory & RAG-as-a-Service
freemium
  • Free BYOK plan supporting up to 3 stateful agents
  • Stateful-agent runtime with persistent memory, desktop app, CLI and API
  • Open-source framework (formerly MemGPT) plus a managed cloud

Mem0

Agent Memory & RAG-as-a-Service
freemium
  • Free Hobby tier: unlimited end users, 10K add / 1K retrieval requests/month
  • Graph memory and entity linking for agent context
  • Open-source core plus managed cloud API

Memori

Agent Memory & RAG-as-a-Service
freemiumNew
  • LLM-agnostic memory layer that captures agent context as structured state
  • Works with LangChain, Pydantic AI, Agno and MCP clients such as Claude Code
  • Open source under Apache 2.0, with free self-host
  • Hosted cloud with an always-free development tier

Supermemory

Agent Memory & RAG-as-a-Service
freemium
  • Free monthly usage allowance plus a Supermemory MCP server
  • Native connectors for Google Drive, Notion, OneDrive as memory sources
  • Deduplication so repeated content isn't rebilled

Zep

Agent Memory & RAG-as-a-Service
freemium
  • Free plan: 10,000 monthly credits, 2 projects, 200ms retrieval
  • Graph RAG with automated context assembly from chat + business data
  • Temporal knowledge graph for tracking how facts change over time

Related collections

All collections →