---
title: "Deploy Agentfield Deep Research"
description: "AI powered multi-agent deep research by Agentfield on Railway"
category: "AI/ML"
url: https://railway.com/deploy/agentfield-deep-research
---

# Deploy Agentfield Deep Research

AI powered multi-agent deep research by Agentfield on Railway

**[Deploy Agentfield Deep Research on Railway](https://railway.com/template/agentfield-deep-research)**

- **Creator:** Agentfield
- **Category:** AI/ML
- **Total deploys:** 11

## Template content

### Postgres https://devicons.railway.app/i/postgresql.svg

- **Image:** pgvector/pgvector:pg17

### control-plane

- **Image:** agentfield/control-plane:latest
- **Public domain:** Yes

### deep-research-agent

- **Source:** https://github.com/Agent-Field/af-deep-research

## Documentation

# Deploy and Host Agentfield Deep Research on Railway

Agentfield Deep Research is an AI-powered research agent that performs iterative, multi-stream investigations on any topic. It autonomously searches the web, extracts entities and relationships, evaluates source quality, and generates comprehensive research documents with full citations and audit trails.

## About Hosting Agentfield Deep Research

Deploying Agentfield Deep Research involves running two services: the AgentField control plane (orchestration layer) and the deep research agent node. The control plane manages agent registration, workflow execution, and provides observability. The research agent connects to the control plane on startup and handles research requests asynchronously. Both services communicate over internal networking, with the control plane exposing a public API for submitting research queries and streaming progress via Server-Sent Events.

## Common Use Cases

- **Investment Research**: Analyze companies, markets, and competitive landscapes with bear/bull tension analysis
- **Knowledge Graph Building**: Extract entities (companies, people, products) and relationships for graph databases
- **Competitive Intelligence**: Track competitor moves, product launches, and strategic positioning
- **Compliance & Due Diligence**: Audit-ready research with strict source tracking and citation trails

## Dependencies for Agentfield Deep Research Hosting

- **OpenRouter API Key** - For LLM inference (supports DeepSeek, Claude, GPT-4, Gemini, Llama)
- **Search Provider API Key** - At least one of: Jina AI, Tavily, Firecrawl, or Serper

### Deployment Dependencies

- [OpenRouter](https://openrouter.ai/keys) - Get your API key for LLM access
- [Jina AI](https://jina.ai/) - Recommended search provider (free tier available)
- [Tavily](https://tavily.com/) - Alternative AI-native search (1000 free/month)
- [Agentfield Deep Research](https://github.com/Agent-Field/af-deep-research) - Source code and documentation

## Why Deploy Agentfield Deep Research on Railway?

Railway is a singular platform to deploy your infrastructure stack. Railway will host your infrastructure so you don't have to deal with configuration, while allowing you to vertically and horizontally scale it.

By deploying Agentfield Deep Research on Railway, you are one step closer to supporting a complete full-stack application with minimal burden. Host your servers, databases, AI agents, and more on Railway.

## 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/agentfield-deep-research