Run This Ai
EN DE

AgentField

Build, run and scale AI agents like APIs and microservices — observable and identity-aware from day one

★ 2,264 GitHub Apache-2.0 agentmulti-agentai-backendmicroservicescloud-native AI Agents

Overview

AgentField is an open-source platform for building, running, and scaling AI agents as if they were APIs and microservices. Unlike traditional agent frameworks that treat agents as monolithic scripts, AgentField provides a cloud-native architecture with built-in identity management, authentication, observability, and horizontal scaling. Agents are deployed as independent services with their own identity, can be orchestrated through a control plane, and integrate seamlessly with existing infrastructure. Built in Go with TypeScript/Python SDKs, it supports multi-agent systems, RAG pipelines, and enterprise-grade deployment.

Requirements

Min vCPU
2
Min RAM
4096 MB
Min Disk
10 GB
Rec vCPU
4
Rec RAM
8192 MB
Rec Disk
20 GB

Recommended VPS

Hostinger · KVM 4

4 vCPU · 16384 MB · 200 GB

$11.99
View plan

Hostinger · KVM 4

4 vCPU · 16384 MB · 200 GB

$11.99
View plan

Hostinger · KVM 8

8 vCPU · 32256 MB · 400 GB

$20.00
View plan

Affiliate disclosure

Docker Compose

# Generated by Run This Ai — docker-compose.yml
services:
  agentfield:
    image: agentfield/control-plane:latest
    restart: unless-stopped
    ports:
      - 8080:8080
    volumes:
      - ./data/agentfield:/data

Best VPS for AgentField →

Related tools

Guides & articles