Why Choose EdgeOne Makers for AI Agent Hosting
Fully managed ai hosting that provides everything your agent needs — runtime, tools, memory, models, and observability. Just host agent code and go.
One-Command Deployment
Deploy with `git push` for auto-deploy or `edgeone makers deploy` via CLI — no Docker, no Kubernetes, no server provisioning.
Built-in Agent Runtime
Managed runtime with session-sticky routing, up to 1-hour execution time, and in-memory state reuse — purpose-built for LLM calls and multi-step agent loops.
Integrated AI Models
Access DeepSeek, MiniMax, Hunyuan, and more through a unified AI gateway. New accounts receive 500K free tokens with zero configuration.
Full Observability
Zero-instrumentation distributed tracing — view complete call chains, LLM interactions, tool invocations, and latency metrics in local and cloud dashboards.
How to Host an AI Agent on EdgeOne Makers
Get your AI agent hosted and running in production with three simple steps — the platform handles all ai hosting complexity.
1
Write Your Agent
Build in the `agents/` directory with any framework (OpenAI SDK, Claude SDK, LangGraph, CrewAI, DeepAgents).
2
Deploy to Production
Push to Git (GitHub/GitLab/Gitee) for auto-deploy, or run `edgeone makers deploy` via CLI.
3
Go Live
Deploys globally in minutes with automatic SSL and edge routing.
Complete AI Agent Hosting Features
Everything included in your managed ai hosting environment — from runtime to observability, all designed for production AI workloads.
Feature | Description |
|---|---|
| Agent Runtime | Hosts LLM calls, Agent loop orchestration, and business logic, with session-based routing and automatic scaling. |
| Sandbox Tools | Provides two separate yet interoperable API layers for both LLMs and developers. Browser automation, code execution, Shell, and file operations all run in an isolated sandbox environment. |
| Conversation Storage | Provides framework-compatible memory management, with unified APIs for sessions and messages. |
| Observability | Automatically collects call traces with zero-intrusion instrumentation, enabling unified trace viewing in both local and cloud dashboards. |
| Built-in Models | Access Hunyuan and other mainstream Chinese models through AI Gateway with a limited-time free token quota. |
Is AI agent hosting on EdgeOne Makers really free?
Yes. Free ai hosting includes 200,000 monthly executions, 100,000 GB-s memory time, 500K model tokens, and 40 concurrent sessions. No hidden charges, no credit card required.
What's included when I host agent workloads?
Every hosted agent gets: session-sticky runtime (up to 1-hour execution), isolated sandbox tools, conversation memory, pre-integrated AI models, and zero-config tracing — complete ai hosting stack.
How does AI agent hosting handle scaling?
The ai hosting infrastructure auto-scales to handle traffic spikes. Up to 40 concurrent sessions per project on the free tier, with sticky routing per user.
Do I need to manage servers to host agent workloads?
No. EdgeOne Makers provides fully managed ai hosting — no servers, containers, or orchestration. Deploy your agent and the platform handles all infrastructure.
Can I host agents built with any framework?
Yes. AI agent hosting supports OpenAI SDK, Claude SDK, LangGraph, CrewAI, and DeepAgents. Both JavaScript and Python are supported for ai hosting.