Integrations

GPT-4, embeddings, and all OpenAI models with persistent memory.

Claude models with persistent memory across conversations.

Gemini Pro and Ultra models with long-term memory integration.

Mistral and Mixtral models with persistent memory support.

Command, Embed, and Rerank models with memory augmentation.

Local model memory. Run Llama, Mistral, Phi locally with persistent context.

Open-source model inference with cross-session memory.

LPU-accelerated inference with persistent memory layer.

Fast serverless inference with memory-augmented completions.

Run any open model on Replicate with persistent memory.

Import conversations and sync memories across ChatGPT sessions.

Import Claude conversations and maintain context across chats.

Works with any model or service that speaks the OpenAI chat format.

Drop-in memory provider for LangChain Python and JS agents.

RemRetriever and RemChatMemory for RAG pipelines and ReAct agents.

Persistent memory for LangGraph stateful agent workflows.

Persistent memory for multi-agent CrewAI orchestration.

Continuity layer for AutoGen multi-agent conversations.

Memory middleware for Vercel AI SDK streaming responses.

Memory-backed RAG pipelines with deepset Haystack framework.

Microsoft Semantic Kernel plugin for persistent agent memory.

Memory provider for Phidata agent functions and tools.

Memory integration for multi-model Agno agent workflows.

TypeScript agent framework with persistent memory support.

HTTP Request nodes wired to REM — every workflow run remembers.

Visual LLM flow builder with drag-and-drop memory nodes.

LLMOps platform integration for memory-augmented AI apps.

One-command migration tool to import all your Mem0 data into REM.

Pull pages, databases, and wikis into your memory layer.

Sync Docs, Sheets, and files from Google Drive into memory.

Import documents and files from Dropbox into your memory.

Sync Microsoft 365 and SharePoint files into AI memory.

Import wiki pages and knowledge base articles into memory.

Sync project issues, tickets, and sprint context into memory.

Ingest issues, projects, and engineering context from Linear.

Import issues, PRs, and repo context from GitHub into memory.

Pull customer conversations and support context into memory.

CRM contacts, deals, and interaction history as AI memory.

Ingest Salesforce CRM records, contacts, and case history.

Import support tickets and customer interactions into memory.

Sync Airtable records and bases into your memory layer.

Bulk-import Slack workspace history and channel archives.

Crawl and import content from any URL or website into memory.

Bot that captures and recalls team knowledge in Slack channels.

Discord bot for shared memory across server conversations.

Extract and store key context from your email conversations.

Meeting context and event history synced into memory.

Capture team chats and meeting context into AI memory.

Telegram bot for memory-powered conversations and groups.

WhatsApp Business API with persistent customer memory.

Connect any email inbox via IMAP for memory ingestion.

Extension that gives your coding AI persistent project memory.

Native MCP server — Composer remembers across every session and repo.

Persistent memory for Claude Code CLI agentic coding sessions.

Long-term memory for Aider AI pair programming sessions.

Memory-backed autonomous coding with Cline in VS Code.

Persistent context for Continue open-source AI code assistant.

Long-term memory for Google Gemini CLI agent sessions.

Memory-backed AI coding with the OpenCode terminal editor.

Store and query memories using Supabase Postgres with pgvector.

Direct PostgreSQL storage backend with pgvector embeddings.

MongoDB Atlas vector search as a memory storage backend.

Redis vector search for high-speed memory caching and retrieval.

Migrate from Pinecone or use as an alternative vector backend.

Migrate from Weaviate or use as a vector storage backend.

Migrate from Qdrant or use as a vector storage backend.

Plugin and vault sync. Your notes become long-term AI memory.

Import your Apple Notes directly into the memory layer.

Sync tasks and reminders from Apple Reminders into memory.

Import projects and tasks from Todoist for memory context.

Markdown notes from Bear imported into your memory layer.

Graph-based knowledge from Roam imported as interconnected memory.

Open-source knowledge graph notes synced into memory.

Book highlights and article annotations as long-term memory.

Import notebooks and clips from Evernote into AI memory.

Save and recall memories from any webpage as you browse.

Firefox add-on for browser-based memory capture.

Full memory access from your terminal. Pipe-friendly.

Model Context Protocol server for standardized AI memory access.

Direct HTTP API. Works with any language, any platform.

Official Python SDK. pip install remlabs and start storing memories.

Official Node.js/TypeScript SDK. npm install @remlabs/sdk (private beta -- request in Discord).

Push events to any endpoint when memories are created or updated.

Webhooks by Zapier store and recall memory across every Zap trigger.

Visual automation scenarios with Make (Integromat) and REM memory.