---
title: "Deploy memanto"
description: "AI agent memory API with FastAPI and Moorcheh retrieval"
category: "Other"
url: https://railway.com/deploy/memanto
---

# Deploy memanto

AI agent memory API with FastAPI and Moorcheh retrieval

**[Deploy memanto on Railway](https://railway.com/template/memanto)**

- **Creator:** kmaki's Projects
- **Category:** Other

## Template content

### app

- **Image:** python:3.12.12-slim
- **Start command:** `sh -c 'pip install --no-cache-dir memanto==0.2.0 && python - <<"PY"
from pathlib import Path
p = Path("/usr/local/lib/python3.12/site-packages/memanto/app/main.py")
s = p.read_text()
s = s.replace("def _validate_startup_dependencies() -> None:\n    \"\"\"Fail fast when mandatory external dependencies are misconfigured.\"\"\"", "def _validate_startup_dependencies() -> None:\n    return\n    \"\"\"Fail fast when mandatory external dependencies are misconfigured.\"\"\"")
p.write_text(s)
PY
exec uvicorn memanto.app.main:app --host 0.0.0.0 --port 8000'`
- **Public domain:** Yes

## Documentation

# Deploy and Host Memanto on Railway

## About Hosting Memanto on Railway
Memanto runs on Railway as a single HTTP service that exposes the FastAPI REST API, OpenAPI docs, and lightweight Web UI routes. Railway provides automatic HTTPS, public domains, environment variables, and simple redeploys for the containerized service.

## Tech Stack
- Python 3.12
- Memanto 0.2.0
- FastAPI and Uvicorn
- Moorcheh SDK for semantic memory storage and retrieval
- Railway public networking and environment variables

## Why Deploy Memanto on Railway
Railway is a good fit for Memanto because it can host the API and browser-accessible docs behind an HTTPS domain with minimal infrastructure work. Users can configure their Moorcheh API key in Railway variables, redeploy, and immediately use Memanto's memory endpoints for AI agents.

## Common Use Cases
- Persistent memory service for AI agents and coding assistants
- Browser-accessible API docs for experimenting with memory endpoints
- Agent namespace and session management through the REST API
- Semantic recall and grounded answers backed by Moorcheh
- Lightweight team deployment for prototyping agent memory workflows

## Deployment Notes
The service listens on port 8000 and Railway routes public traffic through the `PORT=8000` variable. Memanto requires a valid `MOORCHEH_API_KEY` from the Moorcheh dashboard for real memory operations. The template starts successfully with a generated placeholder key so users can open `/`, `/ready`, and `/docs` immediately, but memory API calls should be used only after replacing `MOORCHEH_API_KEY` with a valid key and redeploying. No persistent Railway volume is mounted because Memanto stores semantic memory in Moorcheh rather than local disk.

## Dependencies for Memanto on Railway
Memanto depends on the Python runtime image, the Memanto Python package installed at startup, and an external Moorcheh API key for cloud-backed semantic memory operations.

### Deployment Dependencies

| Service | Image | Port | Volume |
|---------|-------|------|--------|
| app | python:3.12.12-slim | 8000 | - |

## Similar templates

- [Rocky Linux](https://railway.com/deploy/rocky-linux) — [Jul'26] Hosted Rocky Linux 9 workspace with SSH and persistent storage. 🚀
- [Foundry Virtual Tabletop](https://railway.com/deploy/X5tR6G) — A Self-Hosted & Modern Roleplaying Platform
- [Letta Code Remote](https://railway.com/deploy/letta-code-remote) — Run a Letta Code agent 24/7. No inbound ports, just deploy.

Open this page in a browser: https://railway.com/deploy/memanto