Mem0
Agent Memory & RAG-as-a-Service
- 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
AI Agents & Automation (12)
12 free AI agent memory and RAG services and 0 more — pricing tier and real capabilities on every entry. No ads, no sponsored placement.
AllGeneral Autonomous AgentsWorkflow AutomationAgent Frameworks (Developers)Real-Time Voice AgentsBrowser & Computer-Use AgentsMCP EcosystemAgent Memory & RAG-as-a-Service
freemium
Zep
Agent Memory & RAG-as-a-Service
- 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
Supermemory
Agent Memory & RAG-as-a-Service
- 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
Letta
Agent Memory & RAG-as-a-Service
- 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
- 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
- Simple, fast graph-based RAG from HKU Data Science lab (EMNLP 2025)
- Combines knowledge-graph and vector retrieval
- Works with local or hosted LLMs
- 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
- 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
- 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
- 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
- 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
- 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
Agent Memory & RAG-as-a-Service — straight answers
What are the best free AI agent memory and RAG services?
Flocci AI Tools lists 12 AI agent memory and RAG services, ordered free tiers first: MemOS, RAGFlow, Basic Memory, Cognee and Graphiti. All of them are free or have a free tier. Every entry states what it uniquely does, not a score.
Are there completely free AI agent memory and RAG services?
Yes — 7 of these are marked fully free with no paid plan attached: MemOS, RAGFlow, Basic Memory, Cognee and Graphiti. The rest are freemium, trial or paid, and each row states which.
What should I look for in AI agent memory and RAG services?
Start with what you need to do: give an assistant durable memory across sessions. Then check the pricing tier, because "free" here means no paid plan at all while "freemium" means a free tier under paid plans. Every tool on this page lists both.
See the full list →Head-to-head comparisons
MemOS vs RAGFlowBasic Memory vs MemOSCognee vs MemOSGraphiti vs MemOSLightRAG vs MemOSBasic Memory vs RAGFlowCognee vs RAGFlowGraphiti vs RAGFlow
Free alternatives
Mem0 alternativesZep alternativesSupermemory alternativesLetta alternativesRAGFlow alternativesLightRAG alternativesCognee alternativesGraphiti alternatives
Looking for a ranked shortlist instead? See the best free AI agent memory and RAG services.