Why Choose EdgeOne Makers for Agentic Workflow
Purpose-built for complex agent workflows — session-sticky routing, 1-hour execution, stateful branching, and built-in observability for every ai agent workflow step.
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 Build an Agentic Workflow in 3 Steps
From agent workflow code to production agentic workflow in minutes — the platform handles state management, routing, and scaling.
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 Agentic Workflow Platform Features
Everything your ai agent workflow needs — stateful runtime, long execution, memory persistence, and full observability for complex orchestration.
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. |
What is an agentic workflow on EdgeOne Makers?
An agentic workflow is a multi-step AI agent process with stateful execution, branching logic, and tool orchestration. EdgeOne Makers provides the runtime and infrastructure to deploy complex agent workflows to production.
How long can an agentic workflow run?
Each agent workflow execution supports up to 1 hour (3,600 seconds), suitable for complex multi-step orchestration including deep research, data processing, and iterative agent loops.
Does the agentic workflow platform support stateful execution?
Yes. Session-sticky routing ensures the same workflow instance handles all requests within a conversation, preserving in-memory state between steps of your ai agent workflow.
Is building agentic workflows free?
Yes. Free tier: 200,000 executions/month, 500K model tokens, 40 concurrent sessions, and 1-hour max runtime. No credit card required to start building agent workflows.
Can agentic workflows use multiple AI models?
Yes. The AI gateway supports 8+ model providers (DeepSeek, MiniMax, Hunyuan, OpenAI, Anthropic, etc.). Your ai agent workflow can call different models at different steps by simply changing the `model` parameter.