Memori

Overview of Memori

What it is

Memori is agent-native memory infrastructure. It is an LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems. Memori works with existing data infrastructure, does not require rip-and-replace, and can be deployed across managed cloud, single-tenant cloud, VPC, and on-premises environments.

Key features

• LLM-agnostic and datastore-agnostic; integrates with frameworks including LangChain, Pydantic AI, and Agno.
• Automatically captures structured memory from agent execution and conversation, including tool calls, decisions, and outcomes.
• Supports multiple LLM providers: Anthropic, Bedrock, DeepSeek, Gemini, Grok (xAI), and OpenAI (Chat Completions & Responses API).
• Advanced Augmentation enriches memories at entity, process, and session levels with attributes, events, facts, people, preferences, relationships, rules, and skills.
• Offers plugins for OpenClaw and Hermes Agent, and an MCP interface for connecting with Claude Code, Cursor, Codex, Warp, and other clients.
• Provides a cloud service (Memori Cloud) with zero config, and a BYODB option for using your own database.

Use cases

Memori is designed for production AI agents that need to remember context across sessions and conversations. Use cases include persistent memory for chatbots, agentic workflows, coding assistants, and team collaboration tools. It can be used with solo developers or teams, capturing coding patterns, reviewer preferences, and project conventions over time.

Getting started

bash# TypeScript SDKnpm install @memorilabs/memori# Python SDKpip install memori# Quickstart requires signing up at app.memorilabs.ai, getting a Memori API key,# and setting MEMORI_API_KEY and your LLM API key (e.g. OPENAI_API_KEY).``````typescriptimport { OpenAI } from 'openai';import { Memori } from '@memorilabs/memori';const client = new OpenAI();const mem = new Memori().llm .register(client) .attribution('user_123', 'support_agent');``````pythonfrom memori import Memorifrom openai import OpenAIclient = OpenAI()mem = Memori().llm.register(client)mem.attribution(entity_id='user_123', process_id='support_agent')

License and pricing

The license is not stated. The README states that Memori Advanced Augmentation is always free and that Memori Cloud is available with zero config (an API key is required). No other pricing details are provided.

Based on the project's public README and repository metadata.