Why Choose EdgeOne Makers as Your AI Agent Framework Platform
Deploy agents built with any agentic ai frameworks — the platform adapts to your framework, not the other way around.
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 Deploy Any AI Agent Framework in 3 Steps
From any ai agent frameworks to production in minutes — bring your code, we handle the infrastructure.
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.
Everything You Need for Any AI Agent Framework
A framework-agnostic platform with runtime, tools, memory, and models — supporting all major ai agent frameworks out of the box.
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 AI agent frameworks does EdgeOne Makers support?
EdgeOne Makers supports all major ai agent frameworks including OpenAI SDK, Claude SDK, LangGraph, CrewAI, and DeepAgents, in both JavaScript and Python. The platform adapts its interfaces automatically.
Can I switch between ai agent frameworks without redeploying?
You can change your framework by updating the `framework` field in `edgeone.json`. The platform automatically adjusts tool and storage interfaces to match your chosen ai agent framework.
Is there framework lock-in on EdgeOne Makers?
No. EdgeOne Makers is designed to be framework-agnostic. You can use any agentic ai frameworks and migrate between them freely without changing your deployment setup.
Do all ai agent frameworks get the same platform features?
Yes. Regardless of which ai agent framework you use, every deployment includes session-sticky runtime, sandbox tools, conversation memory, AI model access, and distributed tracing.
Is deploying with any ai agent framework free?
Yes. The free tier supports all frameworks equally: 200,000 executions/month, 100,000 GB-s memory time, 500K model tokens, and 40 concurrent sessions.