---
title: "Deploy Aegra agent backend"
description: "Durable agent backend with LangGraph APIs, pgvector, and Redis workers."
category: "AI/ML"
url: https://railway.com/deploy/aegra-agent-backend
---

# Deploy Aegra agent backend

Durable agent backend with LangGraph APIs, pgvector, and Redis workers.

**[Deploy Aegra agent backend on Railway](https://railway.com/template/aegra-agent-backend)**

- **Creator:** Anton Orel's Projects
- **Category:** AI/ML
- **Total deploys:** 2

## Template content

### Aegra Redis

- **Image:** redis:8-alpine@sha256:e8eb6f2980c06c6a25c08f62cb2e00dc7d2fead9aa492cfdd8b54a42109ae0f2
- **Start command:** `/bin/sh -ec 'exec redis-server --appendonly yes --requirepass "$REDIS_PASSWORD"'`

### Aegra PostgreSQL

- **Image:** pgvector/pgvector:pg18@sha256:691673308c99d2161ba298736f3147f1f22d79de2fb7ec93ae9b4afcab870b62

### Aegra

- **Source:** tech-progress/railway-template-aegra
- **Health check:** /ready
- **Public domain:** Yes

## Documentation

# Deploy and Host Aegra on Railway

Deploy Aegra `0.9.24` as an authenticated, self-hosted Agent Protocol backend with durable PostgreSQL checkpoints and Redis-backed job execution. The template includes a working echo graph, generated bearer authentication, automatic database migrations, and crash recovery without requiring an LLM key.

## About Hosting Aegra

Aegra serves LangGraph applications through the Agent Protocol used by LangGraph clients. This Railway topology keeps PostgreSQL and Redis on the private network while exposing one managed-TLS API domain for threads, runs, streaming events, crons, and store operations.

## Why Deploy Aegra on Railway

Railway supplies the public domain, private service discovery, generated secrets, and persistent volumes. Aegra starts its API and queued workers together, so a graph run can be accepted over HTTP, executed through Redis, checkpointed in PostgreSQL, and recovered after a process restart.

## Common Use Cases

- Host LangGraph agents behind the standard Agent Protocol.
- Give internal applications a persistent threads-and-runs backend.
- Test streaming, cron, store, and human-in-the-loop integrations on infrastructure you control.
- Start from the included key-protected graph and replace it with an application-specific agent.

## Dependencies for Aegra

### Deployment Dependencies

- Aegra CLI and API `0.9.24`, installed from hash-locked official PyPI artifacts
- pgvector on PostgreSQL 18 with a persistent volume
- Redis 8 with password authentication, AOF persistence, and a persistent volume
- No external model credential for the included echo graph


## Similar templates

- [Chat Chat](https://railway.com/deploy/-WWW5r) — Chat Chat, your own unified chat and search to AI platform.
- [stella](https://railway.com/deploy/stella) — Self-host stella with web, API, Postgres, Redis, and object storage.
- [Hermes Agent | OpenClaw Alternative with Dashboard](https://railway.com/deploy/hermes-agent-or-openclaw-alternative-wit) — Self-Hosted Hermes AI Agent for Telegram, Discord & Slack

Open this page in a browser: https://railway.com/deploy/aegra-agent-backend