Mem0 on Railway

An open-source memory layer for AI agents, with REST API, dashboard and pgvector, on Railway.

Official site · License: Apache-2.0 · 21 Railway templates

Deploy Mem0 on RailwayCompare templates

Mem0 is an open-source memory layer for AI agents and assistants. It extracts facts from conversations, stores them as embeddings, and returns the relevant ones per user, agent or session so that an application can remember earlier interactions.

Developers use it to give chatbots and agents long-term memory without building a retrieval pipeline themselves. Mem0 also offers a hosted Platform; the self-hosted server is what this page covers.

Mem0 is licensed under Apache-2.0.

What Mem0 can do

  • REST API with interactive docs at /docs
  • Dashboard for memories, entities, requests and API keys
  • Memory scoped to user, agent or session
  • Postgres with pgvector for storage
  • Configurable model provider

What people use it for

  • Long-term memory for a chatbot or assistant
  • Personalising agent responses per user
  • Keeping context across sessions in an AI app
  • Inspecting what an agent has stored about users

Videos

How to Build AI Agents that Remember with Mem0 – Memory Design Tutorial · Beau Carnes
Build AI Agents that EVOLVE Over Time · Cole Medin

Running Mem0 on Railway

The Railway template deploys the Mem0 v2.2.1 REST API, its dashboard and Postgres 17 with pgvector, plus a daily job that prunes request logs older than 30 days. You supply an OpenAI key or one for an OpenAI-compatible endpoint. The template notes measured about 217 MB for the API, 97 MB for the dashboard and 71 MB for Postgres after start; embedding and LLM calls are billed by your model provider.

Mem0 templates on Railway

Mem0 v2 AI Memory LayerMaintained by Tracklayer
Mem0 is an open-source memory layer for AI agents: it extracts facts from conversations, stores them as embeddings in Postgres with pgvector and returns relevant ones per user, age
6 deployments
Deploy
Mem0 | The Memory Layer for Personalized AI by an independent creator
Self Host Mem0. Give your AI agents persistent memory
31 deployments
Deploy
Mem0 Memory API + pgvector by an independent creator
Mem0 memory layer for AI agents: REST API, dashboard and pgvector Postgres
6 deployments
Deploy
Mem0 by an independent creator
Long-term memory for AI agents that remembers across conversations
3 deployments
Deploy
Mem0 self-hosted by an independent creator
Private AI memory platform with dashboard and persistent pgvector storage.
3 deployments
Deploy
Mem0 (w/ Dashboard) by an independent creator
Self-hosted Mem0 memory layer for AI agents, with dashboard and pgvector
2 deployments
Deploy
Mem0 by an independent creator
Mem0 2.2 self-hosted AI memory API and dashboard with Postgres pgvector.
1 deployments
Deploy
Mem0 by an independent creator
Self-hosted Mem0: long-term memory API for AI agents, with a dashboard.
0 deployments
Deploy
Mem0 by an independent creator
Self-hosted AI agent memory: REST API, dashboard and pgvector
0 deployments
Deploy
Mem0 | (Just Updated) Agent Memory REST API, Key Login On From Boot by an independent creator
Mem0 agent-memory REST API on pgvector, API key generated
0 deployments
Deploy
Mem0 | AI Memory Layer, Built From Source for amd64 by an independent creator
AI memory layer, built from source since the image has no amd64 build
0 deployments
Deploy
Mem0 Claude by an independent creator
Self-hosted agent memory powered by Anthropic Claude
0 deployments
Deploy
Mem0 CrewAI by an independent creator
Give CrewAI agents long-term memory backed by Mem0
0 deployments
Deploy
Mem0 Gemini by an independent creator
Gemini models and embeddings behind your Mem0 server
0 deployments
Deploy
Mem0 LangGraph by an independent creator
Long-term memory for LangGraph agents via the Mem0 API
0 deployments
Deploy
Mem0 OpenAI Agents by an independent creator
Long-term memory for OpenAI Agents SDK agents via Mem0
0 deployments
Deploy
Mem0 Postgres by an independent creator
Agent memory stored in pgvector on Railway Postgres
0 deployments
Deploy
Mem0 REST API by an independent creator
Add and search agent memories over plain HTTP
0 deployments
Deploy
Mem0 vs Hindsight by an independent creator
Self-hosted agent memory compared with Hindsight
0 deployments
Deploy
Mem0 vs Letta by an independent creator
Memory layer API vs a stateful agent framework
0 deployments
Deploy
Mem0 vs Supermemory by an independent creator
Self-hosted agent memory compared with Supermemory
0 deployments
Deploy

Tracklayer templates are listed first. Other Mem0 templates follow, ordered by total deployments on Railway. How this works.

Deployment numbers as of 2026-11-20.

Questions about Mem0

What do I need to provide?

An OpenAI API key in OPENAI_API_KEY, or a key for any OpenAI-compatible endpoint through OPENAI_BASE_URL. Anthropic and Google keys are optional for switching models in the dashboard.

How do I log in and get an API key?

Open the dashboard URL and sign in with MEM0_ADMIN_EMAIL and MEM0_ADMIN_PASSWORD from the Mem0 API service variables, then create a key under API Keys.

Does it include an MCP server?

No. Mem0's official MCP server is a hosted service for the Mem0 Platform, and the self-hosted OpenMemory MCP server was removed upstream. Connect agents through the REST API or the Mem0 SDKs.

Can it scale out?

The API runs as one replica because memory history is kept in a SQLite file on its volume. The dashboard is stateless.

How do I upgrade?

The release and checksum are build arguments in both Dockerfiles. Change them together, back up Postgres and the history volume, and redeploy.

Guides

Similar apps

Tracklayer maintains the templates marked as such; Mem0 is a trademark of its owners and this site is not affiliated with them.