Memori

What is Memori?

Memori, from Memori Labs, adds persistent memory to LLM applications, agents and copilots. It wraps your existing model client, records conversations and agent execution such as tool calls, decisions and outcomes, and a background process called Advanced Augmentation turns them into facts, preferences and relationships. Intelligent Recall then ranks memories by relevance and importance, lets older ones decay, and injects the right ones into later prompts. It works with OpenAI, Anthropic, Gemini, Grok and others through Python and TypeScript SDKs, and with frameworks such as LangChain, Agno and Pydantic AI. You can use the managed Memori Cloud with just an API key or bring your own database with the open-source option. Developers building production agents are the target audience. Cloud Free allows 5,000 new memories and 15,000 recalls each month, while production plans start from $60K per year.

Use cases

• Add long-term memory to an LLM agent
• Remember user preferences across sessions
• Learn from agent tool calls and outcomes
• Run self-hosted agent memory on your database
• Share memory across several LLM providers
• Control which agents can read which memories

Who it's for

• AI engineers
• Agent builders
• Startups
• Enterprise AI teams

Why use Memori

• Wrapping your existing LLM client means memory can be added without rebuilding the agent.
• Memories come from agent actions as well as chat text, so agents recall what actually happened.
• Intelligent Recall decays stale facts, which helps keep prompts focused as memory grows.
• The same SDK works with Memori Cloud or your own database, so you can start free and change hosting later.
• Access control and audit logging address enterprise needs around multiple agents and governance.

Memori features

• Wrapper that registers memory on an existing LLM client
• Advanced Augmentation extracts facts, preferences and relationships
• Agent Trace and Execution memory from tool calls and outcomes
• Intelligent Recall with relevance ranking and decay
• Python and TypeScript SDKs
• Support for OpenAI, Anthropic, Gemini, Grok and Bedrock
• LangChain, Agno and Pydantic AI integrations
• Playground for watching memories extract in real time
• Agent access control with ReBAC memory pools
• Observability dashboards and immutable audit logging
• MCP server access in the open-source option

Memori integrations

• OpenAI
• Anthropic
• Google Gemini
• xAI Grok
• AWS Bedrock
• LangChain
• Agno
• Pydantic AI
• DeepSeek
• Nebius AI Studio

How to get started with Memori

1. Sign up at app.memorilabs.ai and create an API key, or choose the open-source option with your own database.
2. Install the Python or TypeScript SDK and register your LLM client with Memori.
3. Set an entity ID for the user and a process ID for the agent so memories are scoped correctly.
4. Use your model as normal while Memori captures context and extracts memories in the background.
5. Recalled memories are injected into later calls, and you can inspect usage in the dashboard.

Memori limitations

• Cloud Free allows only 5,000 new memories and 15,000 recalls a month
• TypeScript supports only OpenAI, Anthropic and Gemini, fewer providers than Python
• Existing memories do not transfer automatically between Cloud and your own database
• Production plans start from $60K per year and need a sales conversation

Memori pricing

Yes, Memori has a free plan.

Memori plans

• Open Source

  Free

  self-host

  • Bring your own database
  • Full SDK and MCP server access
  • Discord support

• Cloud Free

  $0

  managed and hosted

  • 5,000 memories created
  • 15,000 memories recalled
  • Advanced Augmentation and Intelligent Recall
  • Trace-native memory execution

• Team

  $60K

  per year, from

  • Single production agent
  • Managed, multi-tenant cloud
  • Unlimited memories created and recalled

• Business

  $150K

  per year, from

  • Multiple production agents
  • Single-tenant, Memori-managed cloud
  • Unlimited memories created and recalled

• Enterprise

  Custom

  private offer

  • Org-wide, unlimited agents
  • Customer-VPC or on-prem deployment
  • Dedicated infrastructure
  • Custom SLA

Plans as listed on the official pricing page on 24 Oct 2026. Prices can change and may vary by country or exclude tax. Check the official pricing page.

Memori alternatives

The main Memori alternatives listed on Debuly are Mem0, Zep, Letta, Supermemory, Cognee and LangMem. The table compares pricing and platforms; order is A–Z.

1. 

   Cognee

   Open-source memory engine for AI agents that combines vector search, knowledge graphs and relational storage, with a hosted cloud.

   Developer platformsAutomation and agentsResearch and search
   FreemiumVisit Cognee (official site)
2. 

   LangMem

   Python library from LangChain that gives AI agents long-term memory and lets them refine behavior from past conversations.

   Developer platformsAutomation and agents
   Open sourceVisit LangMem (official site)
3. 

   Letta

   Platform, formerly MemGPT, for building stateful AI agents with persistent memory, from a terminal app, SDK or API.

   Developer platformsAutomation and agentsCoding
   FreemiumVisit Letta (official site)
4. 

   Mem0

   Memory layer for AI agents and apps, available as an open-source package or a managed platform that keeps user context across sessions.

   Developer platformsAutomation and agentsCoding
   FreemiumVisit Mem0 (official site)
5. 

   Supermemory

   Memory and context API for AI agents with user profiles, a memory graph, retrieval and connectors, billed by usage.

   Developer platformsAutomation and agentsCoding
   FreemiumVisit Supermemory (official site)
6. 

   Zep

   Managed memory and context platform for AI agents, built on the Graphiti knowledge graph, with Python, TypeScript and Go SDKs.

   Developer platformsAutomation and agents
   FreemiumVisit Zep (official site)

Memori FAQ

Sources & verification

Facts on this page come from the official sources below, each with the date we read it. Written by Debuly; the vendor did not review this page.

Image credits

• Logo: from memorilabs.ai · fetched 24 Oct 2026 · Vendor trademark, used only to identify the product; removed on request
• Cover: none collected yet, so a generated tile is shown.

Spot an error? Report an issue with this listing. We also remove a logo or image on the owner's request.